US20190329782A1 - Pass on command feature for a navigation system - Google Patents

Pass on command feature for a navigation system Download PDF

Info

Publication number
US20190329782A1
US20190329782A1 US16/507,971 US201916507971A US2019329782A1 US 20190329782 A1 US20190329782 A1 US 20190329782A1 US 201916507971 A US201916507971 A US 201916507971A US 2019329782 A1 US2019329782 A1 US 2019329782A1
Authority
US
United States
Prior art keywords
vehicle
host vehicle
navigational
images
image capture
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US16/507,971
Other languages
English (en)
Inventor
Shai Shalev-Shwartz
Amnon Shashua
Shaked SHAMMAH
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mobileye Vision Technologies Ltd
Original Assignee
Mobileye Vision Technologies Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Mobileye Vision Technologies Ltd filed Critical Mobileye Vision Technologies Ltd
Priority to US16/507,971 priority Critical patent/US20190329782A1/en
Assigned to MOBILEYE VISION TECHNOLOGIES LTD. reassignment MOBILEYE VISION TECHNOLOGIES LTD. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: SHASHUA, AMNON, SHALEV-SHWARTZ, Shai, SHAMMAH, SHAKED
Publication of US20190329782A1 publication Critical patent/US20190329782A1/en
Priority to US17/861,533 priority patent/US20220363248A1/en
Abandoned legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3602—Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/14—Adaptive cruise control
    • B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
    • B60W30/162—Speed limiting therefor
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/14—Adaptive cruise control
    • B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
    • B60W30/165—Automatically following the path of a preceding lead vehicle, e.g. "electronic tow-bar"
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/18—Propelling the vehicle
    • B60W30/18009—Propelling the vehicle related to particular drive situations
    • B60W30/18163—Lane change; Overtaking manoeuvres
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/0097—Predicting future conditions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/10—Interpretation of driver requests or demands
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0015—Planning or execution of driving tasks specially adapted for safety
    • B60W60/0016—Planning or execution of driving tasks specially adapted for safety of the vehicle or its occupants
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
    • B60W60/00276—Planning or execution of driving tasks using trajectory prediction for other traffic participants for two or more other traffic participants
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3626—Details of the output of route guidance instructions
    • G01C21/3658—Lane guidance
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • G05D1/0253—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/20—Control system inputs
    • G05D1/24—Arrangements for determining position or orientation
    • G05D1/243—Means capturing signals occurring naturally from the environment, e.g. ambient optical, acoustic, gravitational or magnetic signals
    • G05D1/2437—Extracting relative motion information
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/60—Intended control result
    • G05D1/617—Safety or protection, e.g. defining protection zones around obstacles or avoiding hazards
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/60—Intended control result
    • G05D1/65—Following a desired speed profile
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/80—Arrangements for reacting to or preventing system or operator failure
    • G05D1/81—Handing over between on-board automatic and on-board manual control
    • G06K9/00791—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2300/00—Indexing codes relating to the type of vehicle
    • B60W2300/15—Agricultural vehicles
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2300/00—Indexing codes relating to the type of vehicle
    • B60W2300/17—Construction vehicles, e.g. graders, excavators
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/408—Radar; Laser, e.g. lidar
    • B60W2420/42—
    • B60W2540/04—
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2540/00—Input parameters relating to occupants
    • B60W2540/215—Selection or confirmation of options
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2540/00—Input parameters relating to occupants
    • B60W2540/30—Driving style
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/05—Type of road, e.g. motorways, local streets, paved or unpaved roads
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/50—Barriers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/53—Road markings, e.g. lane marker or crosswalk
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/20—Static objects
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/402—Type
    • B60W2554/4029—Pedestrians
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4041—Position
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4046—Behavior, e.g. aggressive or erratic
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4048—Field of view, e.g. obstructed view or direction of gaze
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/60—Traversable objects, e.g. speed bumps or curbs
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/801—Lateral distance
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/802—Longitudinal distance
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/804—Relative longitudinal speed
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/20—Control system inputs
    • G05D1/24—Arrangements for determining position or orientation
    • G05D1/247—Arrangements for determining position or orientation using signals provided by artificial sources external to the vehicle, e.g. navigation beacons
    • G05D1/249—Arrangements for determining position or orientation using signals provided by artificial sources external to the vehicle, e.g. navigation beacons from positioning sensors located off-board the vehicle, e.g. from cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle
    • G06T2207/30256—Lane; Road marking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/08—Detecting or categorising vehicles

Definitions

  • the present disclosure relates generally to autonomous vehicle navigation.
  • this disclosure relates to systems and methods for navigating using reinforcement learning techniques.
  • an autonomous vehicle may need to take into account a variety of factors and make appropriate decisions based on those factors to safely and accurately reach an intended destination.
  • an autonomous vehicle may need to process and interpret visual information (e.g., information captured from a camera), information from radar or lidar, and may also use information obtained from other sources (e.g., from a GPS device, a speed sensor, an accelerometer, a suspension sensor, etc.).
  • an autonomous vehicle may also need to identify its location within a particular roadway (e.g., a specific lane within a multi-lane road), navigate alongside other vehicles, avoid obstacles and pedestrians, observe traffic signals and signs, travel from one road to another road at appropriate intersections or interchanges, and respond to any other situation that occurs or develops during the vehicle's operation.
  • a particular roadway e.g., a specific lane within a multi-lane road
  • Embodiments consistent with the present disclosure provide systems and methods for autonomous vehicle navigation.
  • the disclosed embodiments may use cameras to provide autonomous vehicle navigation features.
  • the disclosed systems may include one, two, or more cameras that monitor the environment of a vehicle.
  • the disclosed systems may provide a navigational response based on, for example, an analysis of images captured by one or more of the cameras.
  • the navigational response may also take into account other data including, for example, global positioning system (GPS) data, sensor data (e.g., from an accelerometer, a speed sensor, a suspension sensor, radar, lidar, etc.), and/or other map data.
  • GPS global positioning system
  • a navigation system for a host vehicle may comprise, at least one processing device.
  • the processing device may be programmed to receive, from a camera, a plurality of images representative of an environment of the host vehicle.
  • the processing device may also be programmed to analyze the plurality of images to identify at least one navigational state of the host vehicle.
  • the processing device may also be programmed to identify a jurisdiction in which the host vehicle is traveling based on at least one indicator of a location of the host vehicle, the at least one indicator based at least in part on an analysis of the plurality of images.
  • the processing device may also be programmed to determine at least one navigational rule specific to the identified jurisdiction.
  • the processing device may also be programmed to cause a navigational change for the host vehicle based on the identified navigational state of the host vehicle and based on the determined at least one navigational rule specific to the identified jurisdiction.
  • a method of navigation for a host vehicle may comprise receiving, from a camera, a plurality of images representative of an environment of the host vehicle.
  • the method may further comprise analyzing the plurality of images to identify at least one navigational state of the host vehicle.
  • the method may further comprise identifying a jurisdiction in which the host vehicle is traveling based on at least one indicator of a location of the host vehicle, the at least one indicator based at least in part on an analysis of the plurality of images.
  • the method may further comprise determining at least one navigational rule specific to the identified jurisdiction.
  • the method may further comprise causing a navigational change for the host vehicle based on the identified navigational state of the host vehicle and based on the determined at least one navigational rule specific to the identified jurisdiction.
  • a navigation system for a host vehicle may comprise an autonomous vehicle, the vehicle comprising a body, at least one image capture device configured to acquire at least one image representative of an environment of the vehicle, and at least one processor.
  • the processor may be programmed to receive, from a camera, a plurality of images representative of an environment of the host vehicle.
  • the processor may also be programmed to analyze the plurality of images to identify at least one navigational state of the host vehicle.
  • the processor may also be programmed to identify a jurisdiction in which the host vehicle is traveling based on at least one indicator of a location of the host vehicle the at least one indicator based at least in part on an analysis of the plurality of images
  • the processor may also be programmed to determine at least one navigational rule specific to the identified jurisdiction.
  • the processor may also be programmed to cause a navigational change for the host vehicle based on the identified navigational state of the host vehicle and based on the determined at least one navigational rule specific to the identified jurisdiction.
  • a navigation system for a host vehicle may comprise at least one processing device.
  • the at least one processing device may also be programmed to receive, from a camera, a plurality of images representative of an environment of the host vehicle.
  • the at least one processing device may also be programmed to analyze the plurality of images to identify at least one target vehicle in the environment of the host vehicle.
  • the at least one processing device may also be programmed to analyze the plurality of images to identify at least one adverse characteristic of the target vehicle relative to the host vehicle.
  • the at least one processing device may also be programmed to cause at least one navigational change of the host vehicle to initiate a pass of the target vehicle after identifying the at least one characteristic of the target vehicle.
  • a method of navigation for a host vehicle may comprise receiving, from a camera, a plurality of images representative of an environment of the host vehicle. The method may also comprise analyzing the plurality of images to identify at least one target vehicle in the environment of the host vehicle. The method may also comprise analyzing the plurality of images to identify at least one characteristic of the target vehicle. The method may also comprise causing at least one navigational change of the host vehicle to initiate a pass of the target vehicle after identifying the at least one characteristic of the target vehicle.
  • a navigation system for a host vehicle may comprise an autonomous vehicle, the vehicle comprising a body, at least one image capture device configured to acquire at least one image representative of an environment of the vehicle, and at least one processor.
  • the processor may be programmed to receive, from a camera, a plurality of images representative of an environment of the host vehicle.
  • the processor may also be programmed to analyze the plurality of images to identify at least one target vehicle in the environment of the host vehicle.
  • the processor may also be programmed to analyze the plurality of images to identify at least one characteristic of the target vehicle.
  • the processor may also be programmed to cause at least one navigational change of the host vehicle to initiate a pass of the target vehicle after identifying the at least one characteristic of the target vehicle
  • a navigation system for a host vehicle may comprise at least one processing device programmed to receive, from a camera, a plurality of images representative of an environment of the host vehicle.
  • the at least one processing device may also be programmed to analyze the plurality of images to identify at least one target vehicle in the environment of the host vehicle.
  • the at least one processing device may also be programmed to determine based, at least in part, on analysis of the plurality of images that the target vehicle and the host vehicle have a similar navigational priority resulting in a navigational tie situation.
  • the at least one processing device may also be programmed to cause at least one action by the host vehicle to establish navigational priority with the host vehicle or the target vehicle.
  • the at least one processing device may also be programmed to cause control of at least one navigational actuator of the host vehicle in accordance with the established navigational priority.
  • a method of navigation for a host vehicle may comprise receiving, from a camera, a plurality of images representative of an environment of the host vehicle. The method may also comprise analyzing the plurality of images to identify at least one target vehicle in the environment of the host vehicle. The method may also comprise determining based, at least in part, on analysis of the plurality of images that the target vehicle and the host vehicle have a similar navigational priority resulting in a navigational tie situation. The method may also comprise causing at least one action by the host vehicle to establish navigational priority with the host vehicle or the target vehicle. The method may also comprise causing control of at least one navigational actuator of the host vehicle in accordance with the established navigational priority.
  • a navigation system for a host vehicle may comprise an autonomous vehicle, the vehicle comprising a body, at least one image capture device configured to acquire at least one image representative of an environment of the vehicle, and at least one processor programmed to receive, from a camera, a plurality of images representative of an environment of the host vehicle.
  • the at least one processor may also be programmed to analyze the plurality of images to identify at least one target vehicle in the environment of the host vehicle.
  • the at least one processor may also be programmed to determine based, at least in part, on analysis of the plurality of images that the target vehicle and the host vehicle have a similar navigational priority resulting in a navigational tie situation.
  • the at least one processor may also be programmed to cause at least one action by the host vehicle to establish navigational priority with the host vehicle or the target vehicle.
  • the at least one processor may also be programmed to cause control of at least one navigational actuator of the host vehicle in accordance with the established navigational priority.
  • a navigation system for a host vehicle may comprise at least one processing device programmed to receive, from a camera, a plurality of images representative of an environment of the host vehicle.
  • the at least one processing device may also be programmed to analyze the plurality of images to identify a presence in the environment of the host vehicle a navigation rule suspension condition.
  • the at least one processing device may also be programmed to temporarily suspend at least one navigational rule in response to identification of the navigation rule suspension condition.
  • the at least one processing device may also be programmed to cause at least one navigational change of the host vehicle unconstrained by the temporarily suspended at least one navigational rule.
  • a method of navigation for a host vehicle may comprise receiving, from a camera, a plurality of images representative of an environment of the host vehicle. The method may also comprise analyzing the plurality of images to identify a presence in the environment of the host vehicle a navigation rule suspension condition. The method may also comprise temporarily suspending at least one navigational rule in response to identification of the navigation rule suspension condition. The method may also comprise causing at least one navigational change of the host vehicle unconstrained by the temporarily suspended at least one navigational rule.
  • a navigation system for a host vehicle may comprise an autonomous vehicle, the vehicle comprising a body, at least one image capture device configured to acquire at least one image representative of an environment of the vehicle, and at least one processor programmed to receive, from a camera, a plurality of images representative of an environment of the host vehicle.
  • the at least one processor may also be programmed to analyze the plurality of images to identify a presence in the environment of the host vehicle a navigation rule suspension condition.
  • the at least one processor may also be programmed to temporarily suspend at least one navigational rule in response to identification of the navigation rule suspension condition.
  • the at least one processor may also be programmed to cause at least one navigational change of the host vehicle unconstrained by the temporarily suspended at least one navigational rule.
  • non-transitory computer-readable storage media may store program instructions, which are executed by at least one processing device and perform any of the methods described herein.
  • FIG. 1 is a diagrammatic representation of an exemplary system consistent with the disclosed embodiments.
  • FIG. 2A is a diagrammatic side view representation of an exemplary vehicle including a system consistent with the disclosed embodiments.
  • FIG. 2B is a diagrammatic top view representation of the vehicle and system shown in FIG. 2A consistent with the disclosed embodiments.
  • FIG. 2C is a diagrammatic top view representation of another embodiment of a vehicle including a system consistent with the disclosed embodiments.
  • FIG. 2D is a diagrammatic top view representation of yet another embodiment of a vehicle including a system consistent with the disclosed embodiments.
  • FIG. 2E is a diagrammatic top view representation of yet another embodiment of a vehicle including a system consistent with the disclosed embodiments.
  • FIG. 2F is a diagrammatic representation of exemplary vehicle control systems consistent with the disclosed embodiments.
  • FIG. 3A is a diagrammatic representation of an interior of a vehicle including a rearview mirror and a user interface for a vehicle imaging system consistent with the disclosed embodiments.
  • FIG. 3B is an illustration of an example of a camera mount that is configured to be positioned behind a rearview mirror and against a vehicle windshield consistent with the disclosed embodiments.
  • FIG. 3C is an illustration of the camera mount shown in FIG. 3B from a different perspective consistent with the disclosed embodiments.
  • FIG. 3D is an illustration of an example of a camera mount that is configured to be positioned behind a rearview mirror and against a vehicle windshield consistent with the disclosed embodiments.
  • FIG. 4 is an exemplary block diagram of a memory configured to store instructions for performing one or more operations consistent with the disclosed embodiments.
  • FIG. 5A is a flowchart showing an exemplary process for causing one or more navigational responses based on monocular image analysis consistent with disclosed embodiments.
  • FIG. 5B is a flowchart showing an exemplary process for detecting one or more vehicles and/or pedestrians in a set of images consistent with the disclosed embodiments.
  • FIG. 5C is a flowchart showing an exemplary process for detecting road marks and/or lane geometry information in a set of images consistent with the disclosed embodiments.
  • FIG. 5D is a flowchart showing an exemplary process for detecting traffic lights in a set of images consistent with the disclosed embodiments.
  • FIG. 5E is a flowchart showing an exemplary process for causing one or more navigational responses based on a vehicle path consistent with the disclosed embodiments.
  • FIG. 5F is a flowchart showing an exemplary process for determining whether a leading vehicle is changing lanes consistent with the disclosed embodiments.
  • FIG. 6 is a flowchart showing an exemplary process for causing one or more navigational responses based on stereo image analysis consistent with the disclosed embodiments.
  • FIG. 7 is a flowchart showing an exemplary process for causing one or more navigational responses based on an analysis of three sets of images consistent with the disclosed embodiments.
  • FIG. 8 is a block diagram representation of modules that may be implemented by one or more specifically programmed processing devices of a navigation system for an autonomous vehicle consistent with the disclosed embodiments.
  • FIG. 9 is a navigation options graph consistent with the disclosed embodiments.
  • FIG. 10 is a navigation options graph consistent with the disclosed embodiments.
  • FIGS. 11A, 11B, and 11C provide a schematic representation of navigational options of a host vehicle in a merge zone consistent with the disclosed embodiments.
  • FIG. 11D provide a diagrammatic depiction of a double merge scenario.
  • FIG. 11E provides an options graph potentially useful in a double merge scenario.
  • FIG. 12 provides a diagram of a representative image captured of an environment of a host vehicle, along with potential navigational constraints consistent with the disclosed embodiments.
  • FIG. 13 provides an algorithmic flow chart for navigating a vehicle consistent with the disclosed embodiments.
  • FIG. 14 provides an algorithmic flow chart for navigating a vehicle consistent with the disclosed embodiments.
  • FIG. 15 provides an algorithmic flow chart for navigating a vehicle consistent with the disclosed embodiments.
  • FIG. 16 provides an algorithmic flow chart for navigating a vehicle consistent with the disclosed embodiments.
  • FIGS. 17A and 17B provide a diagrammatic illustration of a host vehicle navigating into a roundabout consistent with the disclosed embodiments.
  • FIG. 18 provides an algorithmic flowchart for navigating a vehicle consistent with the disclosed embodiments.
  • FIG. 19 is an exemplary block diagram of a memory configured to store instructions for performing one or more operations consistent with the disclosed embodiments.
  • FIG. 20 provides a diagram of a representative environment of a host vehicle, consistent with the disclosed embodiments.
  • FIG. 21 provides an algorithmic flowchart for navigating a vehicle consistent with the disclosed embodiments.
  • FIG. 22 is an exemplary block diagram of a memory configured to store instructions for performing one or more operations consistent with the disclosed embodiments.
  • FIG. 23 provides a diagram of a representative environment of a host vehicle, consistent with the disclosed embodiments.
  • FIG. 24 provides an algorithmic flowchart for navigating a vehicle consistent with the disclosed embodiments.
  • FIG. 25 is an exemplary block diagram of a memory configured to store instructions for performing one or more operations consistent with the disclosed embodiments.
  • FIGS. 26A and 26B provide diagrams of representative environments of a host vehicle, consistent with the disclosed embodiments.
  • FIG. 27 provides an algorithmic flowchart for navigating a vehicle consistent with the disclosed embodiments.
  • FIG. 28 is an exemplary block diagram of a memory configured to store instructions for performing one or more operations consistent with the disclosed embodiments.
  • FIG. 29 provides a diagram of a representative environment of a host vehicle, consistent with the disclosed embodiments.
  • FIG. 30 provides a diagram of a representative environment of a host vehicle, consistent with the disclosed embodiments.
  • FIG. 31 provides an algorithmic flowchart for navigating a vehicle consistent with the disclosed embodiments.
  • autonomous vehicle refers to a vehicle capable of implementing at least one navigational change without driver input.
  • a “navigational change” refers to a change in one or more of steering, braking, or acceleration/deceleration of the vehicle.
  • a vehicle need not be fully automatic (e.g., fully operational without a driver or without driver input). Rather, an autonomous vehicle includes those that can operate under driver control during certain time periods and without driver control during other time periods.
  • Autonomous vehicles may also include vehicles that control only some aspects of vehicle navigation, such as steering (e.g., to maintain a vehicle course between vehicle lane constraints) or some steering operations under certain circumstances (but not under all circumstances), but may leave other aspects to the driver (e.g., braking or braking under certain circumstances). In some cases, autonomous vehicles may handle some or all aspects of braking, speed control, and/or steering of the vehicle.
  • steering e.g., to maintain a vehicle course between vehicle lane constraints
  • some steering operations under certain circumstances but may leave other aspects to the driver (e.g., braking or braking under certain circumstances).
  • autonomous vehicles may handle some or all aspects of braking, speed control, and/or steering of the vehicle.
  • an autonomous vehicle may include a camera and a processing unit that analyzes visual information captured from the environment of the vehicle.
  • the visual information may include, for example, images representing components of the transportation infrastructure (e.g., lane markings, traffic signs, traffic lights, etc.) that are observable by drivers and other obstacles (e.g., other vehicles, pedestrians, debris, etc.).
  • an autonomous vehicle may also use stored information, such as information that provides a model of the vehicle's environment when navigating.
  • the vehicle may use GPS data, sensor data (e.g., from an accelerometer, a speed sensor, a suspension sensor, etc.), and/or other map data to provide information related to its environment while it is traveling, and the vehicle (as well as other vehicles) may use the information to localize itself on the model.
  • sensor data e.g., from an accelerometer, a speed sensor, a suspension sensor, etc.
  • map data e.g., from an accelerometer, a speed sensor, a suspension sensor, etc.
  • Some vehicles can also be capable of communication among them, sharing information, altering the peer vehicle of hazards or changes in the vehicles' surroundings, etc.
  • FIG. 1 is a block diagram representation of a system 100 consistent with the exemplary disclosed embodiments.
  • System 100 may include various components depending on the requirements of a particular implementation.
  • system 100 may include a processing unit 110 , an image acquisition unit 120 , a position sensor 130 , one or more memory units 140 , 150 , a map database 160 , a user interface 170 , and a wireless transceiver 172 .
  • Processing unit 110 may include one or more processing devices.
  • processing unit 110 may include an applications processor 180 , an image processor 190 , or any other suitable processing device.
  • image acquisition unit 120 may include any number of image acquisition devices and components depending on the requirements of a particular application.
  • image acquisition unit 120 may include one or more image capture devices (e.g., cameras, CCDs, or any other type of image sensor), such as image capture device 122 , image capture device 124 , and image capture device 126 .
  • System 100 may also include a data interface 128 communicatively connecting processing unit 110 to image acquisition unit 120 .
  • data interface 128 may include any wired and/or wireless link or links for transmitting image data acquired by image acquisition unit 120 to processing unit 110 .
  • Wireless transceiver 172 may include one or more devices configured to exchange transmissions over an air interface to one or more networks (e.g., cellular, the Internet, etc.) by use of a radio frequency, infrared frequency, magnetic field, or an electric field. Wireless transceiver 172 may use any known standard to transmit and/or receive data (e.g., Wi-Fi, Bluetooth®, Bluetooth Smart, 802.15.4, ZigBee, etc.). Such transmissions can include communications from the host vehicle to one or more remotely located servers.
  • networks e.g., cellular, the Internet, etc.
  • Wireless transceiver 172 may use any known standard to transmit and/or receive data (e.g., Wi-Fi, Bluetooth®, Bluetooth Smart, 802.15.4, ZigBee, etc.).
  • Such transmissions can include communications from the host vehicle to one or more remotely located servers.
  • Such transmissions may also include communications (one-way or two-way) between the host vehicle and one or more target vehicles in an environment of the host vehicle (e.g., to facilitate coordination of navigation of the host vehicle in view of or together with target vehicles in the environment of the host vehicle), or even a broadcast transmission to unspecified recipients in a vicinity of the transmitting vehicle.
  • Both applications processor 180 and image processor 190 may include various types of hardware-based processing devices.
  • applications processor 180 and image processor 190 may include a microprocessor, preprocessors (such as an image preprocessor), graphics processors, a central processing unit (CPU), support circuits, digital signal processors, integrated circuits, memory, or any other types of devices suitable for running applications and for image processing and analysis.
  • applications processor 180 and/or image processor 190 may include any type of single or multi-core processor, mobile device microcontroller, central processing unit, etc.
  • Various processing devices may be used, including, for example, processors available from manufacturers such as Intel®, AMD®, etc. and may include various architectures (e.g., x86 processor, ARM®, etc.).
  • applications processor 180 and/or image processor 190 may include any of the EyeQ series of processor chips available from Mobileye®. These processor designs each include multiple processing units with local memory and instruction sets. Such processors may include video inputs for receiving image data from multiple image sensors and may also include video out capabilities.
  • the EyeQ2® uses 90 nm-micron technology operating at 332 Mhz.
  • the EyeQ2® architecture consists of two floating point, hyper-thread 32-bit RISC CPUs (MIPS32® 34K® cores), five Vision Computing Engines (VCE), three Vector Microcode Processors (VMP®), Denali 64-bit Mobile DDR Controller, 128-bit internal Sonics Interconnect, dual 16-bit Video input and 18-bit Video output controllers, 16 channels DMA and several peripherals.
  • the MIPS34K CPU manages the five VCEs, three VMPTM and the DMA, the second MIPS34K CPU and the multi-channel DMA as well as the other peripherals.
  • the five VCEs, three VMP® and the MIPS34K CPU can perform intensive vision computations required by multi-function bundle applications.
  • the EyeQ3® which is a third generation processor and is six times more powerful that the EyeQ2®, may be used in the disclosed embodiments.
  • the EyeQ4® and/or the EyeQ5® may be used in the disclosed embodiments.
  • any newer or future EyeQ processing devices may also be used together with the disclosed embodiments.
  • Configuring a processing device such as any of the described EyeQ processors or other controller or microprocessor, to perform certain functions may include programming of computer executable instructions and making those instructions available to the processing device for execution during operation of the processing device.
  • configuring a processing device may include programming the processing device directly with architectural instructions.
  • configuring a processing device may include storing executable instructions on a memory that is accessible to the processing device during operation. For example, the processing device may access the memory to obtain and execute the stored instructions during operation.
  • the processing device configured to perform the sensing, image analysis, and/or navigational functions disclosed herein represents a specialized hardware-based system in control of multiple hardware based components of a host vehicle.
  • FIG. 1 depicts two separate processing devices included in processing unit 110 , more or fewer processing devices may be used.
  • a single processing device may be used to accomplish the tasks of applications processor 180 and image processor 190 . In other embodiments, these tasks may be performed by more than two processing devices.
  • system 100 may include one or more of processing unit 110 without including other components, such as image acquisition unit 120 .
  • Processing unit 110 may comprise various types of devices.
  • processing unit 110 may include various devices, such as a controller, an image preprocessor, a central processing unit (CPU), support circuits, digital signal processors, integrated circuits, memory, or any other types of devices for image processing and analysis.
  • the image preprocessor may include a video processor for capturing, digitizing and processing the imagery from the image sensors.
  • the CPU may comprise any number of microcontrollers or microprocessors.
  • the support circuits may be any number of circuits generally well known in the art, including cache, power supply, clock and input-output circuits.
  • the memory may store software that, when executed by the processor, controls the operation of the system.
  • the memory may include databases and image processing software.
  • the memory may comprise any number of random access memories, read only memories, flash memories, disk drives, optical storage, tape storage, removable storage and other types of storage.
  • the memory may be separate from the processing unit 110 .
  • the memory may be integrated into the processing unit 110 .
  • Each memory 140 , 150 may include software instructions that when executed by a processor (e.g., applications processor 180 and/or image processor 190 ), may control operation of various aspects of system 100 .
  • These memory units may include various databases and image processing software, as well as a trained system, such as a neural network, or a deep neural network, for example.
  • the memory units may include random access memory, read only memory, flash memory, disk drives, optical storage, tape storage, removable storage and/or any other types of storage.
  • memory units 140 , 150 may be separate from the applications processor 180 and/or image processor 190 . In other embodiments, these memory units may be integrated into applications processor 180 and/or image processor 190 .
  • Position sensor 130 may include any type of device suitable for determining a location associated with at least one component of system 100 .
  • position sensor 130 may include a GPS receiver. Such receivers can determine a user position and velocity by processing signals broadcasted by global positioning system satellites. Position information from position sensor 130 may be made available to applications processor 180 and/or image processor 190 .
  • system 100 may include components such as a speed sensor (e.g., a speedometer) for measuring a speed of vehicle 200 .
  • System 100 may also include one or more accelerometers (either single axis or multiaxis) for measuring accelerations of vehicle 200 along one or more axes.
  • the memory units 140 , 150 may include a database, or data organized in any other form, that indication a location of known landmarks.
  • Sensory information (such as images, radar signal, depth information from lidar or stereo processing of two or more images) of the environment may be processed together with position information, such as a GPS coordinate, vehicle's ego motion, etc. to determine a current location of the vehicle relative to the known landmarks, and refine the vehicle location.
  • position information such as a GPS coordinate, vehicle's ego motion, etc.
  • User interface 170 may include any device suitable for providing information to or for receiving inputs from one or more users of system 100 .
  • user interface 170 may include user input devices, including, for example, a touchscreen, microphone, keyboard, pointer devices, track wheels, cameras, knobs, buttons, etc. With such input devices, a user may be able to provide information inputs or commands to system 100 by typing instructions or information, providing voice commands, selecting menu options on a screen using buttons, pointers, or eye-tracking capabilities, or through any other suitable techniques for communicating information to system 100 .
  • User interface 170 may be equipped with one or more processing devices configured to provide and receive information to or from a user and process that information for use by, for example, applications processor 180 .
  • processing devices may execute instructions for recognizing and tracking eye movements, receiving and interpreting voice commands, recognizing and interpreting touches and/or gestures made on a touchscreen, responding to keyboard entries or menu selections, etc.
  • user interface 170 may include a display, speaker, tactile device, and/or any other devices for providing output information to a user.
  • Map database 160 may include any type of database for storing map data useful to system 100 .
  • map database 160 may include data relating to the position, in a reference coordinate system, of various items, including roads, water features, geographic features, businesses, points of interest, restaurants, gas stations, etc. Map database 160 may store not only the locations of such items, but also descriptors relating to those items, including, for example, names associated with any of the stored features.
  • map database 160 may be physically located with other components of system 100 . Alternatively or additionally, map database 160 or a portion thereof may be located remotely with respect to other components of system 100 (e.g., processing unit 110 ).
  • map database 160 may be downloaded over a wired or wireless data connection to a network (e.g., over a cellular network and/or the Internet, etc.).
  • map database 160 may store a sparse data model including polynomial representations of certain road features (e.g., lane markings) or target trajectories for the host vehicle.
  • Map database 160 may also include stored representations of various recognized landmarks that may be used to determine or update a known position of the host vehicle with respect to a target trajectory.
  • the landmark representations may include data fields such as landmark type, landmark location, among other potential identifiers.
  • Image capture devices 122 , 124 , and 126 may each include any type of device suitable for capturing at least one image from an environment. Moreover, any number of image capture devices may be used to acquire images for input to the image processor. Some embodiments may include only a single image capture device, while other embodiments may include two, three, or even four or more image capture devices. Image capture devices 122 , 124 , and 126 will be further described with reference to FIGS. 2B-2E , below.
  • One or more cameras may be part of a sensing block included on a vehicle.
  • Various other sensors may be included in the sensing block, and any or all of the sensors may be relied upon to develop a sensed navigational state of the vehicle.
  • other sensors such as RADAR, LIDAR, and acoustic sensors may be included in the sensing block.
  • the sensing block may include one or more components configured to communicate and transmit/receive information relating to the environment of the vehicle.
  • such components may include wireless transceivers (RF, etc.) that may receive from a source remotely located with respect to the host vehicle sensor based information or any other type of information relating to the environment of the host vehicle.
  • RF wireless transceivers
  • Such information may include sensor output information, or related information, received from vehicle systems other than the host vehicle.
  • such information may include information received from a remote computing device, a centralized server, etc.
  • the cameras may take on many different configurations: single camera units, multiple cameras, camera clusters, long FOV, short FOV, wide angle, fisheye, etc.
  • System 100 may be incorporated into various different platforms.
  • system 100 may be included on a vehicle 200 , as shown in FIG. 2A .
  • vehicle 200 may be equipped with a processing unit 110 and any of the other components of system 100 , as described above relative to FIG. 1 .
  • vehicle 200 may be equipped with only a single image capture device (e.g., camera), in other embodiments, such as those discussed in connection with FIGS. 2B-2E , multiple image capture devices may be used.
  • image capture devices 122 and 124 of vehicle 200 may be part of an ADAS (Advanced Driver Assistance Systems) imaging set.
  • ADAS Advanced Driver Assistance Systems
  • image capture devices included on vehicle 200 as part of the image acquisition unit 120 may be positioned at any suitable location.
  • image capture device 122 may be located in the vicinity of the rearview mirror. This position may provide a line of sight similar to that of the driver of vehicle 200 , which may aid in determining what is and is not visible to the driver.
  • Image capture device 122 may be positioned at any location near the rearview mirror, but placing image capture device 122 on the driver side of the mirror may further aid in obtaining images representative of the driver's field of view and/or line of sight.
  • image capture device 124 may be located on or in a bumper of vehicle 200 . Such a location may be especially suitable for image capture devices having a wide field of view. The line of sight of bumper-located image capture devices can be different from that of the driver and, therefore, the bumper image capture device and driver may not always see the same objects.
  • the image capture devices e.g., image capture devices 122 , 124 , and 126 ) may also be located in other locations.
  • the image capture devices may be located on or in one or both of the side mirrors of vehicle 200 , on the roof of vehicle 200 , on the hood of vehicle 200 , on the trunk of vehicle 200 , on the sides of vehicle 200 , mounted on, positioned behind, or positioned in front of any of the windows of vehicle 200 , and mounted in or near light fixtures on the front and/or back of vehicle 200 , etc.
  • vehicle 200 may include various other components of system 100 .
  • processing unit 110 may be included on vehicle 200 either integrated with or separate from an engine control unit (ECU) of the vehicle.
  • vehicle 200 may also be equipped with a position sensor 130 , such as a GPS receiver and may also include a map database 160 and memory units 140 and 150 .
  • wireless transceiver 172 may and/or receive data over one or more networks (e.g., cellular networks, the Internet, etc.). For example, wireless transceiver 172 may upload data collected by system 100 to one or more servers, and download data from the one or more servers. Via wireless transceiver 172 , system 100 may receive, for example, periodic or on demand updates to data stored in map database 160 , memory 140 , and/or memory 150 . Similarly, wireless transceiver 172 may upload any data (e.g., images captured by image acquisition unit 120 , data received by position sensor 130 or other sensors, vehicle control systems, etc.) from system 100 and/or any data processed by processing unit 110 to the one or more servers.
  • networks e.g., cellular networks, the Internet, etc.
  • wireless transceiver 172 may upload data collected by system 100 to one or more servers, and download data from the one or more servers. Via wireless transceiver 172 , system 100 may receive, for example, periodic or on demand updates to data stored
  • System 100 may upload data to a server (e.g., to the cloud) based on a privacy level setting.
  • system 100 may implement privacy level settings to regulate or limit the types of data (including metadata) sent to the server that may uniquely identify a vehicle and or driver/owner of a vehicle.
  • privacy level settings may be set by user via, for example, wireless transceiver 172 , be initialized by factory default settings, or by data received by wireless transceiver 172 .
  • system 100 may upload data according to a “high” privacy level, and under setting a setting, system 100 may transmit data (e.g., location information related to a route, captured images, etc.) without any details about the specific vehicle and/or driver/owner.
  • system 100 may not include a vehicle identification number (VIN) or a name of a driver or owner of the vehicle, and may instead transmit data, such as captured images and/or limited location information related to a route.
  • VIN vehicle identification number
  • a name of a driver or owner of the vehicle may instead transmit data, such as captured images and/or limited location information related to a route.
  • system 100 may transmit data to a server according to an “intermediate” privacy level and include additional information not included under a “high” privacy level, such as a make and/or model of a vehicle and/or a vehicle type (e.g., a passenger vehicle, sport utility vehicle, truck, etc.).
  • system 100 may upload data according to a “low” privacy level. Under a “low” privacy level setting, system 100 may upload data and include information sufficient to uniquely identify a specific vehicle, owner/driver, and/or a portion or entirely of a route traveled by the vehicle.
  • Such “low” privacy level data may include one or more of, for example, a VIN, a driver/owner name, an origination point of a vehicle prior to departure, an intended destination of the vehicle, a make and/or model of the vehicle, a type of the vehicle, etc.
  • FIG. 2A is a diagrammatic side view representation of an exemplary vehicle imaging system consistent with the disclosed embodiments.
  • FIG. 2B is a diagrammatic top view illustration of the embodiment shown in FIG. 2A .
  • the disclosed embodiments may include a vehicle 200 including in its body a system 100 with a first image capture device 122 positioned in the vicinity of the rearview mirror and/or near the driver of vehicle 200 , a second image capture device 124 positioned on or in a bumper region (e.g., one of bumper regions 210 ) of vehicle 200 , and a processing unit 110 .
  • a bumper region e.g., one of bumper regions 210
  • image capture devices 122 and 124 may both be positioned in the vicinity of the rearview mirror and/or near the driver of vehicle 200 . Additionally, while two image capture devices 122 and 124 are shown in FIGS. 2B and 2C , it should be understood that other embodiments may include more than two image capture devices. For example, in the embodiments shown in FIGS. 2D and 2E , first, second, and third image capture devices 122 , 124 , and 126 , are included in the system 100 of vehicle 200 .
  • image capture device 122 may be positioned in the vicinity of the rearview mirror and/or near the driver of vehicle 200 , and image capture devices 124 and 126 may be positioned on or in a bumper region (e.g., one of bumper regions 210 ) of vehicle 200 .
  • image capture devices 122 , 124 , and 126 may be positioned in the vicinity of the rearview mirror and/or near the driver seat of vehicle 200 .
  • the disclosed embodiments are not limited to any particular number and configuration of the image capture devices, and the image capture devices may be positioned in any appropriate location within and/or on vehicle 200 .
  • the first image capture device 122 may include any suitable type of image capture device.
  • Image capture device 122 may include an optical axis.
  • the image capture device 122 may include an Aptina M9V024 WVGA sensor with a global shutter.
  • image capture device 122 may provide a resolution of 1280 ⁇ 960 pixels and may include a rolling shutter.
  • Image capture device 122 may include various optical elements. In some embodiments one or more lenses may be included, for example, to provide a desired focal length and field of view for the image capture device. In some embodiments, image capture device 122 may be associated with a 6 mm lens or a 12 mm lens.
  • image capture device 122 may be configured to capture images having a desired field-of-view (FOV) 202 , as illustrated in FIG. 2D .
  • FOV field-of-view
  • image capture device 122 may be configured to have a regular FOV, such as within a range of 40 degrees to 56 degrees, including a 46 degree FOV, 50 degree FOV, 52 degree FOV, or greater.
  • image capture device 122 may be configured to have a narrow FOV in the range of 23 to 40 degrees, such as a 28 degree FOV or 36 degree FOV.
  • image capture device 122 may be configured to have a wide FOV in the range of 100 to 180 degrees.
  • image capture device 122 may include a wide angle bumper camera or one with up to a 180 degree FOV.
  • Such an image capture device may be used in place of a three image capture device configuration. Due to significant lens distortion, the vertical FOV of such an image capture device may be significantly less than 50 degrees in implementations in which the image capture device uses a radially symmetric lens. For example, such a lens may not be radially symmetric which would allow for a vertical FOV greater than 50 degrees with 100 degree horizontal FOV.
  • the first image capture device 122 may acquire a plurality of first images relative to a scene associated with vehicle 200 .
  • Each of the plurality of first images may be acquired as a series of image scan lines, which may be captured using a rolling shutter.
  • Each scan line may include a plurality of pixels.
  • the first image capture device 122 may have a scan rate associated with acquisition of each of the first series of image scan lines.
  • the scan rate may refer to a rate at which an image sensor can acquire image data associated with each pixel included in a particular scan line.
  • Image capture devices 122 , 124 , and 126 may contain any suitable type and number of image sensors, including CCD sensors or CMOS sensors, for example.
  • a CMOS image sensor may be employed along with a rolling shutter, such that each pixel in a row is read one at a time, and scanning of the rows proceeds on a row-by-row basis until an entire image frame has been captured.
  • the rows may be captured sequentially from top to bottom relative to the frame.
  • one or more of the image capture devices may constitute a high resolution imager and may have a resolution greater than 5M pixel, 7M pixel, 10M pixel, or greater.
  • a rolling shutter may result in pixels in different rows being exposed and captured at different times, which may cause skew and other image artifacts in the captured image frame.
  • the image capture device 122 is configured to operate with a global or synchronous shutter, all of the pixels may be exposed for the same amount of time and during a common exposure period.
  • the image data in a frame collected from a system employing a global shutter represents a snapshot of the entire FOV (such as FOV 202 ) at a particular time.
  • FOV 202 the entire FOV
  • each row in a frame is exposed and data is capture at different times.
  • moving objects may appear distorted in an image capture device having a rolling shutter. This phenomenon will be described in greater detail below.
  • the second image capture device 124 and the third image capturing device 126 may be any type of image capture device. Like the first image capture device 122 , each of image capture devices 124 and 126 may include an optical axis. In one embodiment, each of image capture devices 124 and 126 may include an Aptina M9V024 WVGA sensor with a global shutter. Alternatively, each of image capture devices 124 and 126 may include a rolling shutter. Like image capture device 122 , image capture devices 124 and 126 may be configured to include various lenses and optical elements.
  • lenses associated with image capture devices 124 and 126 may provide FOVs (such as FOVs 204 and 206 ) that are the same as, or narrower than, a FOV (such as FOV 202 ) associated with image capture device 122 .
  • FOVs such as FOVs 204 and 206
  • FOV 202 FOVs associated with image capture device 122 .
  • image capture devices 124 and 126 may have FOVs of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees, or less.
  • Image capture devices 124 and 126 may acquire a plurality of second and third images relative to a scene associated with vehicle 200 .
  • Each of the plurality of second and third images may be acquired as a second and third series of image scan lines, which may be captured using a rolling shutter.
  • Each scan line or row may have a plurality of pixels.
  • Image capture devices 124 and 126 may have second and third scan rates associated with acquisition of each of image scan lines included in the second and third series.
  • Each image capture device 122 , 124 , and 126 may be positioned at any suitable position and orientation relative to vehicle 200 .
  • the relative positioning of the image capture devices 122 , 124 , and 126 may be selected to aid in fusing together the information acquired from the image capture devices.
  • a FOV (such as FOV 204 ) associated with image capture device 124 may overlap partially or fully with a FOV (such as FOV 202 ) associated with image capture device 122 and a FOV (such as FOV 206 ) associated with image capture device 126 .
  • Image capture devices 122 , 124 , and 126 may be located on vehicle 200 at any suitable relative heights. In one instance, there may be a height difference between the image capture devices 122 , 124 , and 126 , which may provide sufficient parallax information to enable stereo analysis. For example, as shown in FIG. 2A , the two image capture devices 122 and 124 are at different heights. There may also be a lateral displacement difference between image capture devices 122 , 124 , and 126 , giving additional parallax information for stereo analysis by processing unit 110 , for example. The difference in the lateral displacement may be denoted by d x , as shown in FIGS. 2C and 2D .
  • fore or aft displacement may exist between image capture devices 122 , 124 , and 126 .
  • image capture device 122 may be located 0.5 to 2 meters or more behind image capture device 124 and/or image capture device 126 . This type of displacement may enable one of the image capture devices to cover potential blind spots of the other image capture device(s).
  • Image capture devices 122 may have any suitable resolution capability (e.g., number of pixels associated with the image sensor), and the resolution of the image sensor(s) associated with the image capture device 122 may be higher, lower, or the same as the resolution of the image sensor(s) associated with image capture devices 124 and 126 .
  • the image sensor(s) associated with image capture device 122 and/or image capture devices 124 and 126 may have a resolution of 640 ⁇ 480, 1024 ⁇ 768, 1280 ⁇ 960, or any other suitable resolution.
  • the frame rate (e.g., the rate at which an image capture device acquires a set of pixel data of one image frame before moving on to capture pixel data associated with the next image frame) may be controllable.
  • the frame rate associated with image capture device 122 may be higher, lower, or the same as the frame rate associated with image capture devices 124 and 126 .
  • the frame rate associated with image capture devices 122 , 124 , and 126 may depend on a variety of factors that may affect the timing of the frame rate.
  • one or more of image capture devices 122 , 124 , and 126 may include a selectable pixel delay period imposed before or after acquisition of image data associated with one or more pixels of an image sensor in image capture device 122 , 124 , and/or 126 .
  • image data corresponding to each pixel may be acquired according to a clock rate for the device (e.g., one pixel per clock cycle).
  • one or more of image capture devices 122 , 124 , and 126 may include a selectable horizontal blanking period imposed before or after acquisition of image data associated with a row of pixels of an image sensor in image capture device 122 , 124 , and/or 126 .
  • one or more of image capture devices 122 , 124 , and/or 126 may include a selectable vertical blanking period imposed before or after acquisition of image data associated with an image frame of image capture device 122 , 124 , and 126 .
  • timing controls may enable synchronization of frame rates associated with image capture devices 122 , 124 , and 126 , even where the line scan rates of each are different. Additionally, as will be discussed in greater detail below, these selectable timing controls, among other factors (e.g., image sensor resolution, maximum line scan rates, etc.) may enable synchronization of image capture from an area where the FOV of image capture device 122 overlaps with one or more FOVs of image capture devices 124 and 126 , even where the field of view of image capture device 122 is different from the FOVs of image capture devices 124 and 126 .
  • image sensor resolution e.g., maximum line scan rates, etc.
  • Frame rate timing in image capture device 122 , 124 , and 126 may depend on the resolution of the associated image sensors. For example, assuming similar line scan rates for both devices, if one device includes an image sensor having a resolution of 640 ⁇ 480 and another device includes an image sensor with a resolution of 1280 ⁇ 960, then more time will be required to acquire a frame of image data from the sensor having the higher resolution.
  • Another factor that may affect the timing of image data acquisition in image capture devices 122 , 124 , and 126 is the maximum line scan rate. For example, acquisition of a row of image data from an image sensor included in image capture device 122 , 124 , and 126 will require some minimum amount of time. Assuming no pixel delay periods are added, this minimum amount of time for acquisition of a row of image data will be related to the maximum line scan rate for a particular device. Devices that offer higher maximum line scan rates have the potential to provide higher frame rates than devices with lower maximum line scan rates.
  • one or more of image capture devices 124 and 126 may have a maximum line scan rate that is higher than a maximum line scan rate associated with image capture device 122 .
  • the maximum line scan rate of image capture device 124 and/or 126 may be 1.25, 1.5, 1.75, or 2 times or more than a maximum line scan rate of image capture device 122 .
  • image capture devices 122 , 124 , and 126 may have the same maximum line scan rate, but image capture device 122 may be operated at a scan rate less than or equal to its maximum scan rate.
  • the system may be configured such that one or more of image capture devices 124 and 126 operate at a line scan rate that is equal to the line scan rate of image capture device 122 .
  • the system may be configured such that the line scan rate of image capture device 124 and/or image capture device 126 may be 1.25, 1.5, 1.75, or 2 times or more than the line scan rate of image capture device 122 .
  • image capture devices 122 , 124 , and 126 may be asymmetric. That is, they may include cameras having different fields of view (FOV) and focal lengths.
  • the fields of view of image capture devices 122 , 124 , and 126 may include any desired area relative to an environment of vehicle 200 , for example.
  • one or more of image capture devices 122 , 124 , and 126 may be configured to acquire image data from an environment in front of vehicle 200 , behind vehicle 200 , to the sides of vehicle 200 , or combinations thereof.
  • each image capture device 122 , 124 , and/or 126 may be selectable (e.g., by inclusion of appropriate lenses etc.) such that each device acquires images of objects at a desired distance range relative to vehicle 200 .
  • image capture devices 122 , 124 , and 126 may acquire images of close-up objects within a few meters from the vehicle.
  • Image capture devices 122 , 124 , and 126 may also be configured to acquire images of objects at ranges more distant from the vehicle (e.g., 25 m, 50 m, 100 m, 150 m, or more).
  • the focal lengths of image capture devices 122 , 124 , and 126 may be selected such that one image capture device (e.g., image capture device 122 ) can acquire images of objects relatively close to the vehicle (e.g., within 10 m or within 20 m) while the other image capture devices (e.g., image capture devices 124 and 126 ) can acquire images of more distant objects (e.g., greater than 20 m, 50 m, 100 m, 150 m, etc.) from vehicle 200 .
  • one image capture device e.g., image capture device 122
  • the other image capture devices e.g., image capture devices 124 and 126
  • images of more distant objects e.g., greater than 20 m, 50 m, 100 m, 150 m, etc.
  • the FOV of one or more image capture devices 122 , 124 , and 126 may have a wide angle.
  • image capture device 122 may be used to capture images of the area to the right or left of vehicle 200 and, in such embodiments, it may be desirable for image capture device 122 to have a wide FOV (e.g., at least 140 degrees).
  • the field of view associated with each of image capture devices 122 , 124 , and 126 may depend on the respective focal lengths. For example, as the focal length increases, the corresponding field of view decreases.
  • Image capture devices 122 , 124 , and 126 may be configured to have any suitable fields of view.
  • image capture device 122 may have a horizontal FOV of 46 degrees
  • image capture device 124 may have a horizontal FOV of 23 degrees
  • image capture device 126 may have a horizontal FOV in between 23 and 46 degrees.
  • image capture device 122 may have a horizontal FOV of 52 degrees
  • image capture device 124 may have a horizontal FOV of 26 degrees
  • image capture device 126 may have a horizontal FOV in between 26 and 52 degrees.
  • a ratio of the FOV of image capture device 122 to the FOVs of image capture device 124 and/or image capture device 126 may vary from 1.5 to 2.0. In other embodiments, this ratio may vary between 1.25 and 2.25.
  • System 100 may be configured so that a field of view of image capture device 122 overlaps, at least partially or fully, with a field of view of image capture device 124 and/or image capture device 126 .
  • system 100 may be configured such that the fields of view of image capture devices 124 and 126 , for example, fall within (e.g., are narrower than) and share a common center with the field of view of image capture device 122 .
  • the image capture devices 122 , 124 , and 126 may capture adjacent FOVs or may have partial overlap in their FOVs.
  • the fields of view of image capture devices 122 , 124 , and 126 may be aligned such that a center of the narrower FOV image capture devices 124 and/or 126 may be located in a lower half of the field of view of the wider FOV device 122 .
  • FIG. 2F is a diagrammatic representation of exemplary vehicle control systems, consistent with the disclosed embodiments.
  • vehicle 200 may include throttling system 220 , braking system 230 , and steering system 240 .
  • System 100 may provide inputs (e.g., control signals) to one or more of throttling system 220 , braking system 230 , and steering system 240 over one or more data links (e.g., any wired and/or wireless link or links for transmitting data).
  • data links e.g., any wired and/or wireless link or links for transmitting data.
  • system 100 may provide control signals to one or more of throttling system 220 , braking system 230 , and steering system 240 to navigate vehicle 200 (e.g., by causing an acceleration, a turn, a lane shift, etc.). Further, system 100 may receive inputs from one or more of throttling system 220 , braking system 230 , and steering system 24 indicating operating conditions of vehicle 200 (e.g., speed, whether vehicle 200 is braking and/or turning, etc.). Further details are provided in connection with FIGS. 4-7 , below.
  • vehicle 200 may also include a user interface 170 for interacting with a driver or a passenger of vehicle 200 .
  • user interface 170 in a vehicle application may include a touch screen 320 , knobs 330 , buttons 340 , and a microphone 350 .
  • a driver or passenger of vehicle 200 may also use handles (e.g., located on or near the steering column of vehicle 200 including, for example, turn signal handles), buttons (e.g., located on the steering wheel of vehicle 200 ), and the like, to interact with system 100 .
  • handles e.g., located on or near the steering column of vehicle 200 including, for example, turn signal handles), buttons (e.g., located on the steering wheel of vehicle 200 ), and the like, to interact with system 100 .
  • microphone 350 may be positioned adjacent to a rearview mirror 310 .
  • image capture device 122 may be located near rearview mirror 310 .
  • user interface 170 may also include one or more speakers 360 (e.g., speakers of a vehicle audio system).
  • FIGS. 3B-3D are illustrations of an exemplary camera mount 370 configured to be positioned behind a rearview mirror (e.g., rearview mirror 310 ) and against a vehicle windshield, consistent with disclosed embodiments.
  • camera mount 370 may include image capture devices 122 , 124 , and 126
  • Image capture devices 124 and 126 may be positioned behind a glare shield 380 , which may be flush against the vehicle windshield and include a composition of film and/or anti-reflective materials.
  • glare shield 380 may be positioned such that it aligns against a vehicle windshield having a matching slope.
  • each of image capture devices 122 , 124 , and 126 may be positioned behind glare shield 380 , as depicted, for example, in FIG. 3D .
  • the disclosed embodiments are not limited to any particular configuration of image capture devices 122 , 124 , and 126 , camera mount 370 , and glare shield 380 .
  • FIG. 3C is an illustration of camera mount 370 shown in FIG. 3B from a front perspective.
  • system 100 can provide a wide range of functionality to analyze the surroundings of vehicle 200 and navigate vehicle 200 in response to the analysis.
  • system 100 may provide a variety of features related to autonomous driving and/or driver assist technology.
  • system 100 may analyze image data, position data (e.g., GPS location information), map data, speed data, and/or data from sensors included in vehicle 200 .
  • System 100 may collect the data for analysis from, for example, image acquisition unit 120 , position sensor 130 , and other sensors. Further, system 100 may analyze the collected data to determine whether or not vehicle 200 should take a certain action, and then automatically take the determined action without human intervention.
  • system 100 may automatically control the braking, acceleration, and/or steering of vehicle 200 (e.g., by sending control signals to one or more of throttling system 220 , braking system 230 , and steering system 240 ). Further, system 100 may analyze the collected data and issue warnings and/or alerts to vehicle occupants based on the analysis of the collected data. Additional details regarding the various embodiments that are provided by system 100 are provided below.
  • system 100 may provide drive assist functionality that uses a multi-camera system.
  • the multi-camera system may use one or more cameras facing in the forward direction of a vehicle.
  • the multi-camera system may include one or more cameras facing to the side of a vehicle or to the rear of the vehicle.
  • system 100 may use a two-camera imaging system, where a first camera and a second camera (e.g., image capture devices 122 and 124 ) may be positioned at the front and/or the sides of a vehicle (e.g., vehicle 200 ).
  • a first camera and a second camera e.g., image capture devices 122 and 124
  • Other camera configurations are consistent with the disclosed embodiments, and the configurations disclosed herein are examples.
  • the first camera may have a field of view that is greater than, less than, or partially overlapping with, the field of view of the second camera.
  • the first camera may be connected to a first image processor to perform monocular image analysis of images provided by the first camera
  • the second camera may be connected to a second image processor to perform monocular image analysis of images provided by the second camera.
  • the outputs (e.g., processed information) of the first and second image processors may be combined.
  • the second image processor may receive images from both the first camera and second camera to perform stereo analysis.
  • system 100 may use a three-camera imaging system where each of the cameras has a different field of view.
  • references to monocular image analysis may refer to instances where image analysis is performed based on images captured from a single point of view (e.g., from a single camera).
  • Stereo image analysis may refer to instances where image analysis is performed based on two or more images captured with one or more variations of an image capture parameter.
  • captured images suitable for performing stereo image analysis may include images captured: from two or more different positions, from different fields of view, using different focal lengths, along with parallax information, etc.
  • system 100 may implement a three camera configuration using image capture devices 122 - 126 .
  • image capture device 122 may provide a narrow field of view (e.g., 34 degrees, or other values selected from a range of about 20 to 45 degrees, etc.)
  • image capture device 124 may provide a wide field of view (e.g., 150 degrees or other values selected from a range of about 100 to about 180 degrees)
  • image capture device 126 may provide an intermediate field of view (e.g., 46 degrees or other values selected from a range of about 35 to about 60 degrees).
  • image capture device 126 may act as a main or primary camera.
  • Image capture devices 122 - 126 may be positioned behind rearview mirror 310 and positioned substantially side-by-side (e.g., 6 cm apart). Further, in some embodiments, as discussed above, one or more of image capture devices 122 - 126 may be mounted behind glare shield 380 that is flush with the windshield of vehicle 200 . Such shielding may act to minimize the impact of any reflections from inside the car on image capture devices 122 - 126 .
  • the wide field of view camera (e.g., image capture device 124 in the above example) may be mounted lower than the narrow and main field of view cameras (e.g., image devices 122 and 126 in the above example).
  • This configuration may provide a free line of sight from the wide field of view camera.
  • the cameras may be mounted close to the windshield of vehicle 200 , and may include polarizers on the cameras to damp reflected light.
  • a three camera system may provide certain performance characteristics. For example, some embodiments may include an ability to validate the detection of objects by one camera based on detection results from another camera.
  • processing unit 110 may include, for example, three processing devices (e.g., three EyeQ series of processor chips, as discussed above), with each processing device dedicated to processing images captured by one or more of image capture devices 122 - 126 .
  • a first processing device may receive images from both the main camera and the narrow field of view camera, and perform vision processing of the narrow FOV camera to, for example, detect other vehicles, pedestrians, lane marks, traffic signs, traffic lights, and other road objects. Further, the first processing device may calculate a disparity of pixels between the images from the main camera and the narrow camera and create a 3D reconstruction of the environment of vehicle 200 . The first processing device may then combine the 3D reconstruction with 3D map data or with 3D information calculated based on information from another camera.
  • the second processing device may receive images from the main camera and perform vision processing to detect other vehicles, pedestrians, lane marks, traffic signs, traffic lights, and other road objects. Additionally, the second processing device may calculate a camera displacement and, based on the displacement, calculate a disparity of pixels between successive images and create a 3D reconstruction of the scene (e.g., a structure from motion). The second processing device may send the structure from motion based 3D reconstruction to the first processing device to be combined with the stereo 3D images.
  • a 3D reconstruction of the scene e.g., a structure from motion
  • the third processing device may receive images from the wide FOV camera and process the images to detect vehicles, pedestrians, lane marks, traffic signs, traffic lights, and other road objects.
  • the third processing device may further execute additional processing instructions to analyze images to identify objects moving in the image, such as vehicles changing lanes, pedestrians, etc.
  • having streams of image-based information captured and processed independently may provide an opportunity for providing redundancy in the system.
  • redundancy may include, for example, using a first image capture device and the images processed from that device to validate and/or supplement information obtained by capturing and processing image information from at least a second image capture device.
  • system 100 may use two image capture devices (e.g., image capture devices 122 and 124 ) in providing navigation assistance for vehicle 200 and use a third image capture device (e.g., image capture device 126 ) to provide redundancy and validate the analysis of data received from the other two image capture devices.
  • image capture devices 122 and 124 may provide images for stereo analysis by system 100 for navigating vehicle 200
  • image capture device 126 may provide images for monocular analysis by system 100 to provide redundancy and validation of information obtained based on images captured from image capture device 122 and/or image capture device 124 .
  • image capture device 126 (and a corresponding processing device) may be considered to provide a redundant sub-system for providing a check on the analysis derived from image capture devices 122 and 124 (e.g., to provide an automatic emergency braking (AEB) system).
  • AEB automatic emergency braking
  • redundancy and validation of received data may be supplemented based on information received from one more sensors (e.g., radar, lidar, acoustic sensors, information received from one or more transceivers outside of a vehicle, etc.).
  • FIG. 4 is an exemplary functional block diagram of memory 140 and/or 150 , which may be stored/programmed with instructions for performing one or more operations consistent with the disclosed embodiments. Although the following refers to memory 140 , one of skill in the art will recognize that instructions may be stored in memory 140 and/or 150 .
  • memory 140 may store a monocular image analysis module 402 , a stereo image analysis module 404 , a velocity and acceleration module 406 , and a navigational response module 408 .
  • the disclosed embodiments are not limited to any particular configuration of memory 140 .
  • applications processor 180 and/or image processor 190 may execute the instructions stored in any of modules 402 - 408 included in memory 140 .
  • references in the following discussions to processing unit 110 may refer to applications processor 180 and image processor 190 individually or collectively. Accordingly, steps of any of the following processes may be performed by one or more processing devices.
  • monocular image analysis module 402 may store instructions (such as computer vision software) which, when executed by processing unit 110 , performs monocular image analysis of a set of images acquired by one of image capture devices 122 , 124 , and 126 .
  • processing unit 110 may combine information from a set of images with additional sensory information (e.g., information from radar) to perform the monocular image analysis.
  • monocular image analysis module 402 may include instructions for detecting a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, and any other feature associated with an environment of a vehicle.
  • system 100 may cause one or more navigational responses in vehicle 200 , such as a turn, a lane shift, a change in acceleration, and the like, as discussed below in connection with navigational response module 408 .
  • monocular image analysis module 402 may store instructions (such as computer vision software) which, when executed by processing unit 110 , performs monocular image analysis of a set of images acquired by one of image capture devices 122 , 124 , and 126 .
  • processing unit 110 may combine information from a set of images with additional sensory information (e.g., information from radar, lidar, etc.) to perform the monocular image analysis.
  • monocular image analysis module 402 may include instructions for detecting a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, and any other feature associated with an environment of a vehicle.
  • system 100 may cause one or more navigational responses in vehicle 200 , such as a turn, a lane shift, a change in acceleration, and the like, as discussed below in connection with determining a navigational response.
  • one or more navigational responses in vehicle 200 such as a turn, a lane shift, a change in acceleration, and the like, as discussed below in connection with determining a navigational response.
  • stereo image analysis module 404 may store instructions (such as computer vision software) which, when executed by processing unit 110 , performs stereo image analysis of first and second sets of images acquired by a combination of image capture devices selected from any of image capture devices 122 , 124 , and 126 .
  • processing unit 110 may combine information from the first and second sets of images with additional sensory information (e.g., information from radar) to perform the stereo image analysis.
  • stereo image analysis module 404 may include instructions for performing stereo image analysis based on a first set of images acquired by image capture device 124 and a second set of images acquired by image capture device 126 . As described in connection with FIG.
  • stereo image analysis module 404 may include instructions for detecting a set of features within the first and second sets of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, and the like. Based on the analysis, processing unit 110 may cause one or more navigational responses in vehicle 200 , such as a turn, a lane shift, a change in acceleration, and the like, as discussed below in connection with navigational response module 408 . Furthermore, in some embodiments, stereo image analysis module 404 may implement techniques associated with a trained system (such as a neural network or a deep neural network) or an untrained system.
  • a trained system such as a neural network or a deep neural network
  • velocity and acceleration module 406 may store software configured to analyze data received from one or more computing and electromechanical devices in vehicle 200 that are configured to cause a change in velocity and/or acceleration of vehicle 200 .
  • processing unit 110 may execute instructions associated with velocity and acceleration module 406 to calculate a target speed for vehicle 200 based on data derived from execution of monocular image analysis module 402 and/or stereo image analysis module 404 .
  • data may include, for example, a target position, velocity, and/or acceleration, the position and/or speed of vehicle 200 relative to a nearby vehicle, pedestrian, or road object, position information for vehicle 200 relative to lane markings of the road, and the like.
  • processing unit 110 may calculate a target speed for vehicle 200 based on sensory input (e.g., information from radar) and input from other systems of vehicle 200 , such as throttling system 220 , braking system 230 , and/or steering system 240 of vehicle 200 . Based on the calculated target speed, processing unit 110 may transmit electronic signals to throttling system 220 , braking system 230 , and/or steering system 240 of vehicle 200 to trigger a change in velocity and/or acceleration by, for example, physically depressing the brake or easing up off the accelerator of vehicle 200 .
  • sensory input e.g., information from radar
  • processing unit 110 may transmit electronic signals to throttling system 220 , braking system 230 , and/or steering system 240 of vehicle 200 to trigger a change in velocity and/or acceleration by, for example, physically depressing the brake or easing up off the accelerator of vehicle 200 .
  • navigational response module 408 may store software executable by processing unit 110 to determine a desired navigational response based on data derived from execution of monocular image analysis module 402 and/or stereo image analysis module 404 .
  • data may include position and speed information associated with nearby vehicles, pedestrians, and road objects, target position information for vehicle 200 , and the like.
  • the navigational response may be based (partially or fully) on map data, a predetermined position of vehicle 200 , and/or a relative velocity or a relative acceleration between vehicle 200 and one or more objects detected from execution of monocular image analysis module 402 and/or stereo image analysis module 404 .
  • Navigational response module 408 may also determine a desired navigational response based on sensory input (e.g., information from radar) and inputs from other systems of vehicle 200 , such as throttling system 220 , braking system 230 , and steering system 240 of vehicle 200 . Based on the desired navigational response, processing unit 110 may transmit electronic signals to throttling system 220 , braking system 230 , and steering system 240 of vehicle 200 to trigger a desired navigational response by, for example, turning the steering wheel of vehicle 200 to achieve a rotation of a predetermined angle. In some embodiments, processing unit 110 may use the output of navigational response module 408 (e.g., the desired navigational response) as an input to execution of velocity and acceleration module 406 for calculating a change in speed of vehicle 200 .
  • sensory input e.g., information from radar
  • processing unit 110 may transmit electronic signals to throttling system 220 , braking system 230 , and steering system 240 of vehicle 200 to trigger a desired navigational response by,
  • any of the modules may implement techniques associated with a trained system (such as a neural network or a deep neural network) or an untrained system.
  • FIG. 5A is a flowchart showing an exemplary process 500 A for causing one or more navigational responses based on monocular image analysis, consistent with disclosed embodiments.
  • processing unit 110 may receive a plurality of images via data interface 128 between processing unit 110 and image acquisition unit 120 .
  • a camera included in image acquisition unit 120 may capture a plurality of images of an area forward of vehicle 200 (or to the sides or rear of a vehicle, for example) and transmit them over a data connection (e.g., digital, wired, USB, wireless, Bluetooth, etc.) to processing unit 110 .
  • a data connection e.g., digital, wired, USB, wireless, Bluetooth, etc.
  • Processing unit 110 may execute monocular image analysis module 402 to analyze the plurality of images at step 520 , as described in further detail in connection with FIGS. 5B-5D below. By performing the analysis, processing unit 110 may detect a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and the like.
  • Processing unit 110 may also execute monocular image analysis module 402 to detect various road hazards at step 520 , such as, for example, parts of a truck tire, fallen road signs, loose cargo, small animals, and the like.
  • Road hazards may vary in structure, shape, size, and color, which may make detection of such hazards more challenging.
  • processing unit 110 may execute monocular image analysis module 402 to perform multi-frame analysis on the plurality of images to detect road hazards. For example, processing unit 110 may estimate camera motion between consecutive image frames and calculate the disparities in pixels between the frames to construct a 3D-map of the road. Processing unit 110 may then use the 3D-map to detect the road surface, as well as hazards existing above the road surface.
  • processing unit 110 may execute navigational response module 408 to cause one or more navigational responses in vehicle 200 based on the analysis performed at step 520 and the techniques as described above in connection with FIG. 4 .
  • Navigational responses may include, for example, a turn, a lane shift, a change in acceleration, and the like.
  • processing unit 110 may use data derived from execution of velocity and acceleration module 406 to cause the one or more navigational responses.
  • multiple navigational responses may occur simultaneously, in sequence, or any combination thereof. For instance, processing unit 110 may cause vehicle 200 to shift one lane over and then accelerate by, for example, sequentially transmitting control signals to steering system 240 and throttling system 220 of vehicle 200 . Alternatively, processing unit 110 may cause vehicle 200 to brake while at the same time shifting lanes by, for example, simultaneously transmitting control signals to braking system 230 and steering system 240 of vehicle 200 .
  • FIG. 5B is a flowchart showing an exemplary process 500 B for detecting one or more vehicles and/or pedestrians in a set of images, consistent with disclosed embodiments.
  • Processing unit 110 may execute monocular image analysis module 402 to implement process 500 B.
  • processing unit 110 may determine a set of candidate objects representing possible vehicles and/or pedestrians. For example, processing unit 110 may scan one or more images, compare the images to one or more predetermined patterns, and identify within each image possible locations that may contain objects of interest (e.g., vehicles, pedestrians, or portions thereof).
  • objects of interest e.g., vehicles, pedestrians, or portions thereof.
  • the predetermined patterns may be designed in such a way to achieve a high rate of “false hits” and a low rate of “misses.”
  • processing unit 110 may use a low threshold of similarity to predetermined patterns for identifying candidate objects as possible vehicles or pedestrians. Doing so may allow processing unit 110 to reduce the probability of missing (e.g., not identifying) a candidate object representing a vehicle or pedestrian.
  • processing unit 110 may filter the set of candidate objects to exclude certain candidates (e.g., irrelevant or less relevant objects) based on classification criteria.
  • criteria may be derived from various properties associated with object types stored in a database (e.g., a database stored in memory 140 ). Properties may include object shape, dimensions, texture, position (e.g., relative to vehicle 200 ), and the like.
  • processing unit 110 may use one or more sets of criteria to reject false candidates from the set of candidate objects.
  • processing unit 110 may analyze multiple frames of images to determine whether objects in the set of candidate objects represent vehicles and/or pedestrians. For example, processing unit 110 may track a detected candidate object across consecutive frames and accumulate frame-by-frame data associated with the detected object (e.g., size, position relative to vehicle 200 , etc.). Additionally, processing unit 110 may estimate parameters for the detected object and compare the object's frame-by-frame position data to a predicted position.
  • frame-by-frame data associated with the detected object (e.g., size, position relative to vehicle 200 , etc.).
  • processing unit 110 may estimate parameters for the detected object and compare the object's frame-by-frame position data to a predicted position.
  • processing unit 110 may construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values (relative to vehicle 200 ) associated with the detected objects.
  • processing unit 110 may construct the measurements based on estimation techniques using a series of time-based observations such as Kalman filters or linear quadratic estimation (LQE), and/or based on available modeling data for different object types (e.g., cars, trucks, pedestrians, bicycles, road signs, etc.).
  • the Kalman filters may be based on a measurement of an object's scale, where the scale measurement is proportional to a time to collision (e.g., the amount of time for vehicle 200 to reach the object).
  • processing unit 110 may identify vehicles and pedestrians appearing within the set of captured images and derive information (e.g., position, speed, size) associated with the vehicles and pedestrians. Based on the identification and the derived information, processing unit 110 may cause one or more navigational responses in vehicle 200 , as described in connection with FIG. 5A , above.
  • information e.g., position, speed, size
  • processing unit 110 may perform an optical flow analysis of one or more images to reduce the probabilities of detecting a “false hit” and missing a candidate object that represents a vehicle or pedestrian.
  • the optical flow analysis may refer to, for example, analyzing motion patterns relative to vehicle 200 in the one or more images associated with other vehicles and pedestrians, and that are distinct from road surface motion.
  • Processing unit 110 may calculate the motion of candidate objects by observing the different positions of the objects across multiple image frames, which are captured at different times.
  • Processing unit 110 may use the position and time values as inputs into mathematical models for calculating the motion of the candidate objects.
  • optical flow analysis may provide another method of detecting vehicles and pedestrians that are nearby vehicle 200 .
  • Processing unit 110 may perform optical flow analysis in combination with steps 540 - 546 to provide redundancy for detecting vehicles and pedestrians and increase the reliability of system 100 .
  • FIG. 5C is a flowchart showing an exemplary process 500 C for detecting road marks and/or lane geometry information in a set of images, consistent with disclosed embodiments.
  • Processing unit 110 may execute monocular image analysis module 402 to implement process 500 C.
  • processing unit 110 may detect a set of objects by scanning one or more images. To detect segments of lane markings, lane geometry information, and other pertinent road marks, processing unit 110 may filter the set of objects to exclude those determined to be irrelevant (e.g., minor potholes, small rocks, etc.).
  • processing unit 110 may group together the segments detected in step 550 belonging to the same road mark or lane mark. Based on the grouping, processing unit 110 may develop a model to represent the detected segments, such as a mathematical model.
  • processing unit 110 may construct a set of measurements associated with the detected segments.
  • processing unit 110 may create a projection of the detected segments from the image plane onto the real-world plane.
  • the projection may be characterized using a 3rd-degree polynomial having coefficients corresponding to physical properties such as the position, slope, curvature, and curvature derivative of the detected road.
  • processing unit 110 may take into account changes in the road surface, as well as pitch and roll rates associated with vehicle 200 .
  • processing unit 110 may model the road elevation by analyzing position and motion cues present on the road surface. Further, processing unit 110 may estimate the pitch and roll rates associated with vehicle 200 by tracking a set of feature points in the one or more images.
  • processing unit 110 may perform multi-frame analysis by, for example, tracking the detected segments across consecutive image frames and accumulating frame-by-frame data associated with detected segments. As processing unit 110 performs multi-frame analysis, the set of measurements constructed at step 554 may become more reliable and associated with an increasingly higher confidence level. Thus, by performing steps 550 - 556 , processing unit 110 may identify road marks appearing within the set of captured images and derive lane geometry information. Based on the identification and the derived information, processing unit 110 may cause one or more navigational responses in vehicle 200 , as described in connection with FIG. 5A , above.
  • processing unit 110 may consider additional sources of information to further develop a safety model for vehicle 200 in the context of its surroundings.
  • Processing unit 110 may use the safety model to define a context in which system 100 may execute autonomous control of vehicle 200 in a safe manner.
  • processing unit 110 may consider the position and motion of other vehicles, the detected road edges and barriers, and/or general road shape descriptions extracted from map data (such as data from map database 160 ). By considering additional sources of information, processing unit 110 may provide redundancy for detecting road marks and lane geometry and increase the reliability of system 100 .
  • FIG. 5D is a flowchart showing an exemplary process 500 D for detecting traffic lights in a set of images, consistent with disclosed embodiments.
  • Processing unit 110 may execute monocular image analysis module 402 to implement process 500 D.
  • processing unit 110 may scan the set of images and identify objects appearing at locations in the images likely to contain traffic lights. For example, processing unit 110 may filter the identified objects to construct a set of candidate objects, excluding those objects unlikely to correspond to traffic lights. The filtering may be done based on various properties associated with traffic lights, such as shape, dimensions, texture, position (e.g., relative to vehicle 200 ), and the like. Such properties may be based on multiple examples of traffic lights and traffic control signals and stored in a database.
  • processing unit 110 may perform multi-frame analysis on the set of candidate objects reflecting possible traffic lights. For example, processing unit 110 may track the candidate objects across consecutive image frames, estimate the real-world position of the candidate objects, and filter out those objects that are moving (which are unlikely to be traffic lights). In some embodiments, processing unit 110 may perform color analysis on the candidate objects and identify the relative position of the detected colors appearing inside possible traffic lights.
  • processing unit 110 may analyze the geometry of a junction. The analysis may be based on any combination of: (i) the number of lanes detected on either side of vehicle 200 , (ii) markings (such as arrow marks) detected on the road, and (iii) descriptions of the junction extracted from map data (such as data from map database 160 ). Processing unit 110 may conduct the analysis using information derived from execution of monocular analysis module 402 . In addition, processing unit 110 may determine a correspondence between the traffic lights detected at step 560 and the lanes appearing near vehicle 200 .
  • processing unit 110 may update the confidence level associated with the analyzed junction geometry and the detected traffic lights. For instance, the number of traffic lights estimated to appear at the junction as compared with the number actually appearing at the junction may impact the confidence level. Thus, based on the confidence level, processing unit 110 may delegate control to the driver of vehicle 200 in order to improve safety conditions.
  • processing unit 110 may identify traffic lights appearing within the set of captured images and analyze junction geometry information. Based on the identification and the analysis, processing unit 110 may cause one or more navigational responses in vehicle 200 , as described in connection with FIG. 5A , above.
  • FIG. 5E is a flowchart showing an exemplary process 500 E for causing one or more navigational responses in vehicle 200 based on a vehicle path, consistent with the disclosed embodiments.
  • processing unit 110 may construct an initial vehicle path associated with vehicle 200 .
  • the vehicle path may be represented using a set of points expressed in coordinates (x, z), and the distance d i between two points in the set of points may fall in the range of 1 to 5 meters.
  • processing unit 110 may construct the initial vehicle path using two polynomials, such as left and right road polynomials.
  • Processing unit 110 may calculate the geometric midpoint between the two polynomials and offset each point included in the resultant vehicle path by a predetermined offset (e.g., a smart lane offset), if any (an offset of zero may correspond to travel in the middle of a lane).
  • the offset may be in a direction perpendicular to a segment between any two points in the vehicle path.
  • processing unit 110 may use one polynomial and an estimated lane width to offset each point of the vehicle path by half the estimated lane width plus a predetermined offset (e.g., a smart lane offset).
  • processing unit 110 may update the vehicle path constructed at step 570 .
  • Processing unit 110 may reconstruct the vehicle path constructed at step 570 using a higher resolution, such that the distance d k between two points in the set of points representing the vehicle path is less than the distance d i described above. For example, the distance d k may fall in the range of 0.1 to 0.3 meters.
  • Processing unit 110 may reconstruct the vehicle path using a parabolic spline algorithm, which may yield a cumulative distance vector S corresponding to the total length of the vehicle path (i.e., based on the set of points representing the vehicle path).
  • processing unit 110 may determine a look-ahead point (expressed in coordinates as (x l , z l )) based on the updated vehicle path constructed at step 572 .
  • Processing unit 110 may extract the look-ahead point from the cumulative distance vector S, and the look-ahead point may be associated with a look-ahead distance and look-ahead time.
  • the look-ahead distance which may have a lower bound ranging from 10 to 20 meters, may be calculated as the product of the speed of vehicle 200 and the look-ahead time. For example, as the speed of vehicle 200 decreases, the look-ahead distance may also decrease (e.g., until it reaches the lower bound).
  • the look-ahead time which may range from 0.5 to 1.5 seconds, may be inversely proportional to the gain of one or more control loops associated with causing a navigational response in vehicle 200 , such as the heading error tracking control loop.
  • the gain of the heading error tracking control loop may depend on the bandwidth of a yaw rate loop, a steering actuator loop, car lateral dynamics, and the like.
  • the higher the gain of the heading error tracking control loop the lower the look-ahead time.
  • FIG. 5F is a flowchart showing an exemplary process 500 F for determining whether a leading vehicle is changing lanes, consistent with the disclosed embodiments.
  • processing unit 110 may determine navigation information associated with a leading vehicle (e.g., a vehicle traveling ahead of vehicle 200 ). For example, processing unit 110 may determine the position, velocity (e.g., direction and speed), and/or acceleration of the leading vehicle, using the techniques described in connection with FIGS. 5A and 5B , above. Processing unit 110 may also determine one or more road polynomials, a look-ahead point (associated with vehicle 200 ), and/or a snail trail (e.g., a set of points describing a path taken by the leading vehicle), using the techniques described in connection with FIG. 5E , above.
  • a leading vehicle e.g., a vehicle traveling ahead of vehicle 200
  • processing unit 110 may determine the position, velocity (e.g., direction and speed), and/or acceleration of the leading vehicle, using the techniques described in connection with FIGS. 5A and
  • processing unit 110 may analyze the navigation information determined at step 580 .
  • processing unit 110 may calculate the distance between a snail trail and a road polynomial (e.g., along the trail). If the variance of this distance along the trail exceeds a predetermined threshold (for example, 0.1 to 0.2 meters on a straight road, 0.3 to 0.4 meters on a moderately curvy road, and 0.5 to 0.6 meters on a road with sharp curves), processing unit 110 may determine that the leading vehicle is likely changing lanes. In the case where multiple vehicles are detected traveling ahead of vehicle 200 , processing unit 110 may compare the snail trails associated with each vehicle.
  • a predetermined threshold for example, 0.1 to 0.2 meters on a straight road, 0.3 to 0.4 meters on a moderately curvy road, and 0.5 to 0.6 meters on a road with sharp curves
  • processing unit 110 may determine that a vehicle whose snail trail does not match with the snail trails of the other vehicles is likely changing lanes. Processing unit 110 may additionally compare the curvature of the snail trail (associated with the leading vehicle) with the expected curvature of the road segment in which the leading vehicle is traveling.
  • the expected curvature may be extracted from map data (e.g., data from map database 160 ), from road polynomials, from other vehicles' snail trails, from prior knowledge about the road, and the like. If the difference in curvature of the snail trail and the expected curvature of the road segment exceeds a predetermined threshold, processing unit 110 may determine that the leading vehicle is likely changing lanes.
  • processing unit 110 may compare the leading vehicle's instantaneous position with the look-ahead point (associated with vehicle 200 ) over a specific period of time (e.g., 0.5 to 1.5 seconds). If the distance between the leading vehicle's instantaneous position and the look-ahead point varies during the specific period of time, and the cumulative sum of variation exceeds a predetermined threshold (for example, 0.3 to 0.4 meters on a straight road, 0.7 to 0.8 meters on a moderately curvy road, and 1.3 to 1.7 meters on a road with sharp curves), processing unit 110 may determine that the leading vehicle is likely changing lanes.
  • a predetermined threshold for example, 0.3 to 0.4 meters on a straight road, 0.7 to 0.8 meters on a moderately curvy road, and 1.3 to 1.7 meters on a road with sharp curves
  • processing unit 110 may analyze the geometry of the snail trail by comparing the lateral distance traveled along the trail with the expected curvature of the snail trail.
  • the expected radius of curvature may be determined according to the calculation: ( ⁇ z 2 + ⁇ x 2 )/2/( ⁇ x ), where ⁇ x represents the lateral distance traveled and ⁇ z represents the longitudinal distance traveled. If the difference between the lateral distance traveled and the expected curvature exceeds a predetermined threshold (e.g., 500 to 700 meters), processing unit 110 may determine that the leading vehicle is likely changing lanes. In another embodiment, processing unit 110 may analyze the position of the leading vehicle.
  • a predetermined threshold e.g. 500 to 700 meters
  • processing unit 110 may determine that the leading vehicle is likely changing lanes. In the case where the position of the leading vehicle is such that, another vehicle is detected ahead of the leading vehicle and the snail trails of the two vehicles are not parallel, processing unit 110 may determine that the (closer) leading vehicle is likely changing lanes.
  • processing unit 110 may determine whether or not leading vehicle 200 is changing lanes based on the analysis performed at step 582 . For example, processing unit 110 may make the determination based on a weighted average of the individual analyses performed at step 582 . Under such a scheme, for example, a decision by processing unit 110 that the leading vehicle is likely changing lanes based on a particular type of analysis may be assigned a value of “1” (and “0” to represent a determination that the leading vehicle is not likely changing lanes). Different analyses performed at step 582 may be assigned different weights, and the disclosed embodiments are not limited to any particular combination of analyses and weights. Furthermore, in some embodiments, the analysis may make use of trained system (e.g., a machine learning or deep learning system), which may, for example, estimate a future path ahead of a current location of a vehicle based on an image captured at the current location.
  • trained system e.g., a machine learning or deep learning system
  • FIG. 6 is a flowchart showing an exemplary process 600 for causing one or more navigational responses based on stereo image analysis, consistent with disclosed embodiments.
  • processing unit 110 may receive a first and second plurality of images via data interface 128 .
  • cameras included in image acquisition unit 120 may capture a first and second plurality of images of an area forward of vehicle 200 and transmit them over a digital connection (e.g., USB, wireless, Bluetooth, etc.) to processing unit 110 .
  • processing unit 110 may receive the first and second plurality of images via two or more data interfaces.
  • the disclosed embodiments are not limited to any particular data interface configurations or protocols.
  • processing unit 110 may execute stereo image analysis module 404 to perform stereo image analysis of the first and second plurality of images to create a 3D map of the road in front of the vehicle and detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, and the like.
  • Stereo image analysis may be performed in a manner similar to the steps described in connection with FIGS. 5A-5D , above.
  • processing unit 110 may execute stereo image analysis module 404 to detect candidate objects (e.g., vehicles, pedestrians, road marks, traffic lights, road hazards, etc.) within the first and second plurality of images, filter out a subset of the candidate objects based on various criteria, and perform multi-frame analysis, construct measurements, and determine a confidence level for the remaining candidate objects.
  • processing unit 110 may consider information from both the first and second plurality of images, rather than information from one set of images alone.
  • processing unit 110 may analyze the differences in pixel-level data (or other data subsets from among the two streams of captured images) for a candidate object appearing in both the first and second plurality of images.
  • processing unit 110 may estimate a position and/or velocity of a candidate object (e.g., relative to vehicle 200 ) by observing that the object appears in one of the plurality of images but not the other or relative to other differences that may exist relative to objects appearing in the two image streams.
  • position, velocity, and/or acceleration relative to vehicle 200 may be determined based on trajectories, positions, movement characteristics, etc. of features associated with an object appearing in one or both of the image streams.
  • processing unit 110 may execute navigational response module 408 to cause one or more navigational responses in vehicle 200 based on the analysis performed at step 620 and the techniques as described above in connection with FIG. 4 .
  • Navigational responses may include, for example, a turn, a lane shift, a change in acceleration, a change in velocity, braking, and the like.
  • processing unit 110 may use data derived from execution of velocity and acceleration module 406 to cause the one or more navigational responses. Additionally, multiple navigational responses may occur simultaneously, in sequence, or any combination thereof.
  • FIG. 7 is a flowchart showing an exemplary process 700 for causing one or more navigational responses based on an analysis of three sets of images, consistent with disclosed embodiments.
  • processing unit 110 may receive a first, second, and third plurality of images via data interface 128 .
  • cameras included in image acquisition unit 120 may capture a first, second, and third plurality of images of an area forward and/or to the side of vehicle 200 and transmit them over a digital connection (e.g., USB, wireless, Bluetooth, etc.) to processing unit 110 .
  • a digital connection e.g., USB, wireless, Bluetooth, etc.
  • processing unit 110 may receive the first, second, and third plurality of images via three or more data interfaces.
  • each of image capture devices 122 , 124 , 126 may have an associated data interface for communicating data to processing unit 110 .
  • the disclosed embodiments are not limited to any particular data interface configurations or protocols.
  • processing unit 110 may analyze the first, second, and third plurality of images to detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, and the like.
  • the analysis may be performed in a manner similar to the steps described in connection with FIGS. 5A-5D and 6 , above.
  • processing unit 110 may perform monocular image analysis (e.g., via execution of monocular image analysis module 402 and based on the steps described in connection with FIGS. 5A-5D , above) on each of the first, second, and third plurality of images.
  • processing unit 110 may perform stereo image analysis (e.g., via execution of stereo image analysis module 404 and based on the steps described in connection with FIG.
  • processing unit 110 may perform a combination of monocular and stereo image analyses. For example, processing unit 110 may perform monocular image analysis (e.g., via execution of monocular image analysis module 402 ) on the first plurality of images and stereo image analysis (e.g., via execution of stereo image analysis module 404 ) on the second and third plurality of images.
  • monocular image analysis e.g., via execution of monocular image analysis module 402
  • stereo image analysis e.g., via execution of stereo image analysis module 404
  • the configuration of image capture devices 122 , 124 , and 126 may influence the types of analyses conducted on the first, second, and third plurality of images.
  • the disclosed embodiments are not limited to a particular configuration of image capture devices 122 , 124 , and 126 , or the types of analyses conducted on the first, second, and third plurality of images.
  • processing unit 110 may perform testing on system 100 based on the images acquired and analyzed at steps 710 and 720 . Such testing may provide an indicator of the overall performance of system 100 for certain configurations of image capture devices 122 , 124 , and 126 . For example, processing unit 110 may determine the proportion of “false hits” (e.g., cases where system 100 incorrectly determined the presence of a vehicle or pedestrian) and “misses.”
  • processing unit 110 may cause one or more navigational responses in vehicle 200 based on information derived from two of the first, second, and third plurality of images. Selection of two of the first, second, and third plurality of images may depend on various factors, such as, for example, the number, types, and sizes of objects detected in each of the plurality of images. Processing unit 110 may also make the selection based on image quality and resolution, the effective field of view reflected in the images, the number of captured frames, the extent to which one or more objects of interest actually appear in the frames (e.g., the percentage of frames in which an object appears, the proportion of the object that appears in each such frame, etc.), and the like.
  • processing unit 110 may select information derived from two of the first, second, and third plurality of images by determining the extent to which information derived from one image source is consistent with information derived from other image sources. For example, processing unit 110 may combine the processed information derived from each of image capture devices 122 , 124 , and 126 (whether by monocular analysis, stereo analysis, or any combination of the two) and determine visual indicators (e.g., lane markings, a detected vehicle and its location and/or path, a detected traffic light, etc.) that are consistent across the images captured from each of image capture devices 122 , 124 , and 126 .
  • visual indicators e.g., lane markings, a detected vehicle and its location and/or path, a detected traffic light, etc.
  • Processing unit 110 may also exclude information that is inconsistent across the captured images (e.g., a vehicle changing lanes, a lane model indicating a vehicle that is too close to vehicle 200 , etc.). Thus, processing unit 110 may select information derived from two of the first, second, and third plurality of images based on the determinations of consistent and inconsistent information.
  • information that is inconsistent across the captured images e.g., a vehicle changing lanes, a lane model indicating a vehicle that is too close to vehicle 200 , etc.
  • processing unit 110 may select information derived from two of the first, second, and third plurality of images based on the determinations of consistent and inconsistent information.
  • Navigational responses may include, for example, a turn, a lane shift, a change in acceleration, and the like.
  • Processing unit 110 may cause the one or more navigational responses based on the analysis performed at step 720 and the techniques as described above in connection with FIG. 4 .
  • Processing unit 110 may also use data derived from execution of velocity and acceleration module 406 to cause the one or more navigational responses.
  • processing unit 110 may cause the one or more navigational responses based on a relative position, relative velocity, and/or relative acceleration between vehicle 200 and an object detected within any of the first, second, and third plurality of images. Multiple navigational responses may occur simultaneously, in sequence, or any combination thereof.
  • the autonomous driving task can be partitioned into, for example, three modules, including a sensing module 801 , a driving policy module 803 , and a control module 805 .
  • modules 801 , 803 , and 805 may be stored in memory unit 140 and/or memory unit 150 of system 100 , or modules 801 , 803 , and 805 (or portions thereof) may be stored remotely from system 100 (e.g., stored in a server accessible to system 100 via, for example, wireless transceiver 172 ).
  • any of the modules (e.g., modules 801 , 803 , and 805 ) disclosed herein may implement techniques associated with a trained system (such as a neural network or a deep neural network) or an untrained system.
  • Sensing module 801 may handle various tasks relating to sensing of a navigational state in an environment of a host vehicle. Such tasks may rely upon input from various sensors and sensing systems associated with the host vehicle. These inputs may include images or image streams from one or more onboard cameras, GPS position information, accelerometer outputs, user feedback, or user inputs to one or more user interface devices, radar, lidar, etc. Sensing, which may include data from cameras and/or any other available sensors, along with map information, may be collected, analyzed, and formulated into a “sensed state,” describing information extracted from a scene in the environment of the host vehicle.
  • the sensed state may include sensed information relating to target vehicles, lane markings, pedestrians, traffic lights, road geometry, lane shape, obstacles, distances to other objects/vehicles, relative velocities, relative accelerations, among any other potential sensed information.
  • Supervised machine learning may be implemented in order to produce a sensing state output based on sensed data provided to sensing module 801 .
  • the output of the sensing module may represent a sensed navigational “state” of the host vehicle, which may be passed to driving policy module 803 .
  • a sensed state may be developed based on image data received from one or more cameras or image sensors associated with a host vehicle
  • a sensed state for use in navigation may be developed using any suitable sensor or combination of sensors.
  • the sensed state may be developed without reliance upon captured image data.
  • any of the navigational principles described herein may be applicable to sensed states developed based on captured image data as well as sensed states developed using other non-image based sensors.
  • the sensed state may also be determined via sources external to the host vehicle.
  • a sensed state may be developed in full or in part based on information received from sources remote from the host vehicle (e.g., based on sensor information, processed state information, etc. shared from other vehicles, shared from a central server, or from any other source of information relevant to a navigational state of the host vehicle.)
  • Driving policy module 803 may implement a desired driving policy in order to decide on one or more navigational actions for the host vehicle to take in response to the sensed navigational state. If there are no other agents (e.g., target vehicles or pedestrians) present in the environment of the host vehicle, the sensed state input to driving policy module 803 may be handled in a relatively straightforward manner. The task becomes more complex when the sensed state requires negotiation with one or more other agents.
  • the technology used to generate the output of driving policy module 803 may include reinforcement learning (discussed in more detail below).
  • the output of driving policy module 803 may include at least one navigational action for the host vehicle and may include a desired acceleration (which may translate to an updated speed for the host vehicle), a desired yaw rate for the host vehicle, a desired trajectory, among other potential desired navigational actions.
  • control module 805 may develop control instructions for one or more actuators or controlled devices associated with the host vehicle.
  • actuators and devices may include an accelerator, one or more steering controls, a brake, a signal transmitter, a display, or any other actuator or device that may be controlled as part of a navigation operation associated with a host vehicle.
  • Aspects of control theory may be used to generate the output of control module 805 .
  • Control module 805 may be responsible for developing and outputting instructions to controllable components of the host vehicle in order to implement the desired navigational goals or requirements of driving policy module 803 .
  • driving policy module 803 in some embodiments, a trained system trained through reinforcement learning may be used to implement driving policy module 803 .
  • driving policy module 803 may be implemented without a machine learning approach, by using specified algorithms to “manually” address the various scenarios that may arise during autonomous navigation. Such an approach, however, while viable, may result in a driving policy that is too simplistic and may lack the flexibility of a trained system based on machine learning.
  • a trained system may be better equipped to handle complex navigational states and may better determine whether a taxi is parking or is stopping to pick up or drop off a passenger; determine whether a pedestrian intends to cross the street ahead of the host vehicle; balance unexpected behavior of other drivers with defensiveness; negotiate in dense traffic involving target vehicles and/or pedestrians; decide when to suspend certain navigational rules or augment other rules; anticipate unsensed, but anticipated conditions (e.g., whether a pedestrian will emerge from behind a car or obstacle); etc.
  • a trained system based on reinforcement learning may also be better equipped to address a state space that is continuous and high-dimensional along with an action space that is continuous.
  • Training of the system using reinforcement learning may involve learning a driving policy in order to map from sensed states to navigational actions.
  • a driving policy is a function ⁇ :S ⁇ A, where S is a set of states and A ⁇ 2 is the action space (e.g., desired speed, acceleration, yaw commands, etc.).
  • the system may be trained through exposure to various navigational states, having the system apply the policy, providing a reward (based on a reward function designed to reward desirable navigational behavior). Based on the reward feedback, the system may “learn” the policy and becomes trained in producing desirable navigational actions. For example, the learning system may observe the current state s t ⁇ S and decide on an action a t ⁇ A based on a policy ⁇ :S ⁇ (A). Based on the decided action (and implementation of the action), the environment moves to the next state s t+1 ⁇ S for observation by the learning system. For each action developed in response to the observed state, the feedback to the learning system is a reward signal r 1 , r 2 , . . . .
  • RL Reinforcement Learning
  • r t The goal of Reinforcement Learning (RL) is to find a policy ⁇ . It is usually assumed that at time t, there is a reward function r t which measures the instantaneous quality of being at state s t and taking action a t . However, taking the action at a t time t affects the environment and therefore affects the value of the future states. As a result, when deciding on what action to take, not only should the current reward be taken into account, but future rewards should also be considered. In some instances the system should take a certain action, even though it is associated with a reward lower than another available option, when the system determines that in the future a greater reward may be realized if the lower reward option is taken now.
  • the value of the initial states may be defined as:
  • the future rewards may be discounted to define, for some fixed ⁇ ⁇ (0, 1):
  • the optimal policy is the solution of
  • an imitation approach e.g., behavior cloning
  • the system learns from state/action pairs where the actions are those that would be chosen by a good agent (e.g., a human) in response to a particular observed state.
  • a good agent e.g., a human
  • a human driver is observed.
  • many examples of the form (s t , a t ), where s t is the state and a t is the action of the human driver could be obtained, observed, and used as a basis for training the driving policy system.
  • supervised learning can be used to learn a policy ⁇ such that ⁇ (s t ) ⁇ a t .
  • policy based learning Another technique that may be employed is policy based learning.
  • the policy may be expressed in parametric form and directly optimized using a suitable optimization technique (e.g., stochastic gradient descent).
  • a suitable optimization technique e.g., stochastic gradient descent.
  • the approach is to directly solve the problem given in
  • One advantage of this approach is that it tackles the problem directly, and therefore often leads to good practical results.
  • One potential disadvantage is that it often requires an “on-policy” training, namely, the learning of it is an iterative process, where at iteration j we have a non-perfect policy, ⁇ j , and to construct the next policy ⁇ j , we must interact with the environment while acting based on ⁇ j .
  • the system may also be trained through value based learning (learning Q or V functions). Suppose a good approximation can be learned to the optimal value function V*.
  • An optimal policy may be constructed (e.g., by relying on the Bellman equation).
  • Some versions of value based learning can be implemented offline (called “off-policy” training).
  • Some disadvantages of the value-based approach may result from its strong dependence on Markovian assumptions and required approximation of a complicated function (it may be more difficult to approximate the value function than to approximate the policy directly).
  • Another technique may include model based learning and planning (learning the probability of state transitions and solving the optimization problem of finding the optimal V). Combinations of these techniques may also be used to train the learning system.
  • the dynamics of the process may be learned, namely, the function that takes (s t , a t ) and yields a distribution over the next state s t+1 .
  • the optimization problem may be solved to find the policy ⁇ whose value is optimal. This is called “planning”.
  • One advantage of this approach may be that the learning part is supervised and can be applied offline by observing triplets (s t , a t , s t+1 ).
  • One disadvantage of this approach similar to the “imitation” approach, may be that small errors in the learning process can accumulate and to yield inadequately performing policies.
  • Another approach for training driving policy module 803 may include decomposing the driving policy function into semantically meaningful components. This allows implementation of parts of the policy manually, which may ensure the safety of the policy, and implementation of other parts of the policy using reinforcement learning techniques, which may enable adaptivity to many scenarios, a human-like balance between defensive/aggressive behavior, and a human-like negotiation with other drivers. From the technical perspective, a reinforcement learning approach may combine several methodologies and offer a tractable training procedure, where most of the training can be performed using either recorded data or a self-constructed simulator.
  • training of driving policy module 803 may rely upon an “options” mechanism.
  • an “options” mechanism For illustrate, consider a simple scenario of a driving policy for a two-lane highway.
  • a policy ⁇ that maps the state into A ⁇ 2 , where the first component of ⁇ (s) is the desired acceleration command and the second component of ⁇ (s) is the yaw rate.
  • the following policies can be constructed:
  • ACC Automatic Cruise Control
  • ACC+Left policy o L :S ⁇ A: the longitudinal command of this policy is the same as the ACC command.
  • the yaw rate is a straightforward implementation of centering the vehicle toward the middle of the left lane, while ensuring a safe lateral movement (e.g., don't move left if there's a car on the left side).
  • ACC+Right policy o R :S ⁇ A: Same as o L , but the vehicle may be centered toward the middle of the right lane.
  • the policy function may be decomposed into an options graph 901 , as shown in FIG. 9 .
  • Another example options graph 1000 is shown in FIG. 10 .
  • the options graph can represent a hierarchical set of decisions organized as a Directed Acyclic Graph (DAG).
  • DAG Directed Acyclic Graph
  • the decision process traverses through the graph, starting from the root node, until it reaches a “leaf” node, which refers to a node that has no outgoing decision lines.
  • leaf nodes may include nodes 905 , 907 , and 909 , for example.
  • driving policy module 803 may output the acceleration and steering commands associated with a desired navigational action associated with the leaf node.
  • Internal nodes such as nodes 911 , 913 , and 915 , for example, may result in implementation of a policy that chooses a child among its available options.
  • the set of available children of an internal node include all of the nodes associated with a particular internal node via decision lines.
  • internal node 913 designated as “Merge” in FIG. 9 includes three children nodes 909 , 915 , and 917 (“Stay,” “Overtake Right,” and “Overtake Left,” respectively) each joined to node 913 by a decision line.
  • any of the nodes may be allowed to declare themselves as “critical.”
  • Each node may implement a function “is critical,” that outputs “True” if the node is in a critical section of its policy implementation.
  • a node that is responsible for a take-over may declare itself as critical while in the middle of a maneuver. This may impose constraints on the set of available children of a node u, which may include all nodes v which are children of node u and for which there exists a path from v to a leaf node that goes through all nodes designated as critical.
  • Such an approach may allow, on one hand, declaration of the desired path on the graph at each time step, while on the other hand, stability of a policy may be preserved, especially while critical portions of the policy are being implemented.
  • the problem of learning the driving policy ⁇ :S ⁇ A may be decomposed into a problem of defining a policy for each node of the graph, where the policy at internal nodes should choose from among available children nodes.
  • the respective policy may be implemented manually (e.g., through if-then type algorithms specifying a set of actions in response to an observed state) while for others the policies may be implemented using a trained system built through reinforcement learning.
  • the choice between manual or trained/learned approaches may depend on safety aspects associated with the task and on its relative simplicity.
  • the option graphs may be constructed in a manner such that some of the nodes are straightforward to implement, while other nodes may rely on trained models. Such an approach can ensure safe operation of the system.
  • driving policy module 803 provides further details regarding the role of the options graph of FIG. 9 within driving policy module 803 .
  • the input to the driving policy module is a “sensed state,” which summarizes the environment map, for example, as obtained from available sensors.
  • the output of driving policy module 803 is a set of desires (optionally, together with a set of hard constraints) that define a trajectory as a solution of an optimization problem.
  • the options graph represents a hierarchical set of decisions organized as a DAG.
  • the root node is the only node that has no incoming edges (e.g., decision lines).
  • the decision process traverses the graph, starting from the root node, until it reaches a “leaf” node, namely, a node that has no outgoing edges.
  • Each internal node should implement a policy that picks a child among its available children. Every leaf node should implement a policy that, based on the entire path from the root to the leaf, defines a set of Desires (e.g., a set of navigational goals for the host vehicle).
  • the set of Desires together with a set of hard constraints that are defined directly based on the sensed state, establish an optimization problem whose solution is the trajectory for the vehicle.
  • the hard constraints may be employed to further increase the safety of the system, and the Desires can be used to provide driving comfort and human-like driving behavior of the system.
  • the trajectory provided as a solution to the optimization problem defines the commands that should be provided to the steering, braking, and/or engine actuators in order to accomplish the trajectory.
  • options graph 901 represents an options graph for a two-lane highway, including with merging lanes (meaning that at some points, a third lane is merged into either the right or the left lane of the highway).
  • the root node 903 first decides if the host vehicle is in a plain road scenario or approaching a merge scenario. This is an example of a decision that can be implemented based on the sensing state.
  • Plain road node 911 includes three child nodes: stay node 909 , overtake left node 917 , and overtake right node 915 . Stay refers to a situation in which the host vehicle would like to keep driving in the same lane.
  • the stay node is a leaf node (no outgoing edges/lines).
  • the stay node defines a set of Desires.
  • the first Desire it defines may include the desired lateral position—e.g., as close as possible to the center of the current lane of travel. There may also be a desire to navigate smoothly (e.g., within predefined or allowable acceleration maximums)
  • the stay node may also define how the host vehicle is to react to other vehicles. For example, the stay node may review sensed target vehicles and assign each a semantic meaning, which can be translated into components of the trajectory.
  • the semantic meaning may include any of the following designations: 1) not relevant: indicating that the sensed vehicle in the scene is currently not relevant; 2) next lane: indicating that the sensed vehicle is in an adjacent lane and an appropriate offset should be maintained relative to this vehicle (the exact offset may be calculated in the optimization problem that constructs the trajectory given the Desires and hard constraints, and can potentially be vehicle dependent—the stay leaf of the options graph sets the target vehicle's semantic type, which defines the Desire relative to the target vehicle); 3) give way: the host vehicle will attempt to give way to the sensed target vehicle by, for example, reducing speed (especially where the host vehicle determines that the target vehicle is likely to cut into the lane of the host vehicle); 4) take way: the host vehicle will attempt to take the right of way by, for example, increasing speed; 5) follow: the host vehicle desires to maintain smooth driving following after this target vehicle; 6) takeover left/right: this means the host vehicle would like to
  • the next node in options graph 901 is the select gap node 919 .
  • This node may be responsible for selecting a gap between two target vehicles in a particular target lane that host vehicle desires to enter.
  • the host vehicle arrives at a leaf that designates a Desire for the trajectory optimization problem—e.g., the host vehicle wishes to make a maneuver so as to arrive at the selected gap.
  • Such a maneuver may involve first accelerating/braking in the current lane and then heading to the target lane at an appropriate time to enter the selected gap.
  • the select gap node 919 cannot find an appropriate gap, it moves to the abort node 921 , which defines a desire to move back to the center of the current lane and cancel the takeover.
  • merge node 913 when the host vehicle approaches a merge, it has several options that may depend on a particular situation. For example, as shown in FIG. 11A , host vehicle 1105 is traveling along a two-lane road with no other target vehicles detected, either in the primary lanes of the two-lane road or in the merge lane 1111 . In this situation, driving policy module 803 , upon reaching merge node 913 , may select stay node 909 . That is, staying within its current lane may be desired where no target vehicles are sensed as merging onto the roadway.
  • FIG. 11B the situation is slightly different.
  • host vehicle 1105 senses one or more target vehicles 1107 entering the main roadway 1112 from merge lane 1111 .
  • driving policy module 803 encounters merge node 913 , it may choose to initiate an overtake left maneuver in order to avoid the merging situation.
  • host vehicle 1105 encounters one or more target vehicles 1107 entering main roadway 1112 from merge lane 1111 .
  • Host vehicle 1105 also detects target vehicles 1109 traveling in a lane adjacent to the lane of the host vehicle.
  • the host vehicle also detects one or more target vehicles 1110 traveling in the same lane as host vehicle 1105 .
  • driving policy module 803 may decide to adjust the speed of host vehicle 1105 to give way to target vehicle 1107 and to proceed ahead of target vehicle 1115 . This can be accomplished, for example, by progressing to select gap node 919 , which, in turn, will select a gap between ID 0 (vehicle 1107 ) and ID 1 (vehicle 1115 ) as the appropriate merging gap.
  • the appropriate gap of the merging situation defines the objective for a trajectory planner optimization problem.
  • nodes of the options graph may declare themselves as “critical,” which may ensure that the selected option passes through the critical nodes.
  • each node may implement a function IsCritical. After performing a forward pass on the options graph, from the root to a leaf, and solving the optimization problem of the trajectory planner, a backward pass may be performed from the leaf back to the root. Along this backward pass, the IsCritical function of all nodes in the pass may be called, and a list of all critical nodes may be saved. In the forward path corresponding to the next time frame, driving policy module 803 may be required to choose a path from the root node to a leaf that goes through all critical nodes.
  • FIGS. 11A-11C may be used to show a potential benefit of this approach.
  • the IDj node can designate itself as critical.
  • the success of the trajectory planner can be monitored, and function IsCritical will return a “True” value if the overtake maneuver progresses as intended. This approach may ensure that in the next time frame, the takeover maneuver will be continued (rather than jumping to another, potentially inconsistent maneuver prior to completion of the initially selected maneuver).
  • the function IsCritical can return a “False” value. This can allow the select gap node to select a different gap in the next time frame, or to abort the overtake maneuver altogether.
  • This approach may allow, on one hand, declaration of the desired path on the options graph at each time step, while on the other hand, may help to promote stability of the policy while in critical parts of the execution.
  • Hard constraints may be differentiated from navigational desires. For example, hard constraints may ensure safe driving by applying an added layer of filtering of a planned navigational action.
  • the implicated hard constraints which may be programmed and defined manually, rather than through use of a trained system built upon reinforcement learning, can be determined from the sensed state. In some embodiments, however, the trained system may learn the applicable hard constraints to be applied and followed. Such an approach may promote driving policy module 803 arriving at a selected action that is already in compliance with the applicable hard constraints, which may reduce or eliminate selected actions that may require later modification to comply with applicable hard constraints. Nevertheless, as a redundant safety measure, hard constraints may be applied to the output of driving policy module 803 even where driving policy module 803 has been trained to account for predetermined hard constraints.
  • a hard constraint may be defined in conjunction with a guardrail on an edge of a road. In no situation may the host vehicle be allowed to pass the guardrail. Such a rule induces a hard lateral constraint on the trajectory of the host vehicle.
  • a hard constraint may include a road bump (e.g., a speed control bump), which may induce a hard constraint on the speed of driving before the bump and while traversing the bump.
  • Hard constraints may be considered safety critical and, therefore, may be defined manually rather than relying solely on a trained system learning the constraints during training.
  • the goal of desires may be to enable or achieve comfortable driving.
  • an example of a desire may include a goal of positioning the host vehicle at a lateral position within a lane that corresponds to the center of the host vehicle lane.
  • Another desire may include the ID of a gap to fit into. Note that there is not a requirement for the host vehicle to be exactly in the center of the lane, but instead a desire to be as close as possible to it may ensure that the host vehicle tends to migrate to the center of the lane even in the event of deviations from the center of the lane. Desires may not be safety critical. In some embodiments, desires may require negotiation with other drivers and pedestrians.
  • One approach for constructing the desires may rely on the options graph, and the policy implemented in at least some nodes of the graph may be based on reinforcement learning.
  • the training process may include decomposing the problem into a supervised learning phase and a reinforcement learning phase.
  • a differentiable mapping from (s t , a t ) to ⁇ t+1 can be learned such that ⁇ t+1 ⁇ s t+1 .
  • This may be similar to “model-based” reinforcement learning.
  • ⁇ t+1 may be replaced by the actual value of s t+1 , therefore eliminating the problem of error accumulation.
  • the role of prediction of ⁇ t+1 is to propagate messages from the future back to past actions. In this sense, the algorithm may be a combination of “model-based” reinforcement learning with “policy-based learning.”
  • a differentiable path from future losses/rewards back to decisions on actions is usually not differentiable.
  • the choice of a child in a learned policy node may be stochastic. That is, a node may output a probability vector, p, that assigns probabilities used in choosing each of the children of the particular node.
  • p probability vector
  • an action a may be chosen to be a (i) for i ⁇ p, and the difference between a and â may be referred to as additive noise.
  • supervised learning may be used together with real data.
  • policy of nodes simulators can be used.
  • fine tuning of a policy can be accomplished using real data.
  • Two concepts may make the simulation more realistic.
  • an initial policy can be constructed using the “behavior cloning” paradigm, using large real world data sets.
  • the resulting agents may be suitable.
  • the resulting agents at least form very good initial policies for the other agents on the roads.
  • our own policy may be used to augment the training.
  • a policy may be trained based on a simulator. Some of the other agents may be replaced with the new policy, and the process may be repeated. As a result, the policy can continue to improve as it should respond to a larger variety of other agents that have differing levels of sophistication.
  • the system may implement a multi-agent approach.
  • the system may take into account data from various sources and/or images capturing from multiple angles.
  • some disclosed embodiments may provide economy of energy, as anticipation of an event which does not directly involve the host vehicle, but which may have an effect on the host vehicle can be considered, or even anticipation of an event that may lead to unpredictable circumstances involving other vehicles may be a consideration (e.g., radar may “see through” the leading vehicle and anticipation of an unavoidable, or even a high likelihood of an event that will affect the host vehicle).
  • the driving policy system may be trained using constraints, such that the actions selected by the trained system may already account for applicable safety constraints. Additionally, in some embodiments, an extra layer of safety may be provided by passing the selected actions of the trained system through one or more hard constraints implicated by a particular sensed scene in the environment of the host vehicle. Such an approach may ensure that that the actions taken by the host vehicle have been restricted to those confirmed as satisfying applicable safety constraints.
  • the navigational system may include a learning algorithm based on a policy function that maps an observed state to one or more desired actions.
  • the learning algorithm is a deep learning algorithm.
  • the desired actions may include at least one action expected to maximize an anticipated reward for a vehicle. While in some cases, the actual action taken by the vehicle may correspond to one of the desired actions, in other cases, the actual action taken may be determined based on the observed state, one or more desired actions, and non-learned, hard constraints (e.g., safety constraints) imposed on the learning navigational engine.
  • constraints may include no-drive zones surrounding various types of detected objects (e.g., target vehicles, pedestrians, stationary objects on the side of a road or in a roadway, moving objects on the side of a road or in a roadway, guard rails, etc.)
  • the size of the zone may vary based on a detected motion (e.g., speed and/or direction) of a detected object.
  • Other constraints may include a maximum speed of travel when passing within an influence zone of a pedestrian, a maximum deceleration (to account for a target vehicle spacing behind the host vehicle), a mandatory stop at a sensed crosswalk or railroad crossing, etc.
  • Hard constraints used in conjunction with a system trained through machine learning may offer a degree of safety in autonomous driving that may surpass a degree of safety available based on the output of the trained system alone.
  • the machine learning system may be trained using a desired set of constraints as training guidelines and, therefore, the trained system may select an action in response to a sensed navigational state that accounts for and adheres to the limitations of applicable navigational constraints.
  • the trained system has some flexibility in selecting navigational actions and, therefore, there may exist at least some situations in which an action selected by the trained system may not strictly adhere to relevant navigational constraints. Therefore, in order to require that a selected action strictly adheres to relevant navigational constraints, the output of the trained system may be combined with, compared to, filtered with, adjusted, modified, etc. using a non-machine learning component outside the learning/trained framework that guarantees strict application of relevant navigational constraints.
  • the reinforcement learning objective by policy may be optimized through stochastic gradient ascent.
  • the objective e.g., the expected reward
  • the objective may be defined as .
  • the gradient of [R( s )] may be estimated.
  • the following lemma shows that the variance of the random variable R( s ) grows with pr 2 , which is larger than r for r>>1/p. Therefore, estimating the objective may be difficult, and estimating its gradient may be even more difficult.
  • the policy function may be decomposed into a learnable part and a nonlearnable part.
  • the function ⁇ 8 (D) is responsible for the comfort of driving and for making strategic decisions such as which other cars should be over-taken or given way and what is the desired position of the host vehicle within its lane, etc.
  • the mapping from sensed navigational state to Desires is a policy ⁇ 6 (D) that may be learned from experience by maximizing an expected reward.
  • the desires produced by ⁇ 0 (D) may be translated into a cost function over driving trajectories.
  • the function ⁇ (T) not a learned function, may be implemented by finding a trajectory that minimizes the cost subject to hard constraints on functional safety. This decomposition may ensure functional safety while at the same time providing for comfortable driving.
  • a double merge navigational situation provides an example further illustrating these concepts.
  • vehicles approach the merge area 1130 from both left and right sides. And, from each side, a vehicle, such as vehicle 1133 or vehicle 1135 , can decide whether to merge into lanes on the other side of merge area 1130 .
  • Successfully executing a double merge in busy traffic may require significant negotiation skills and experience and may be difficult to execute in a heuristic or brute force approach by enumerating all possible trajectories that could be taken by all agents in the scene.
  • a set of Desires, appropriate for the double merge maneuver may be defined.
  • ⁇ g, t, o ⁇ are classification labels assigned to each of the n other vehicles.
  • the other vehicles may be assigned “g” if the host vehicle is to give way to the other vehicle, “t” if the host vehicle is to take way relative to the other vehicle, or “o” if the host vehicle is to maintain an offset distance relative to the other vehicle.
  • a driving trajectory may be represented by where (x 1 , y 1 ), . . . , (x k , y k ), where (x i , y i ) is the (lateral, longitudinal) location of the host vehicle (in ego-centric units) at time ⁇ i.
  • the cost assigned to a trajectory may include a weighted sum of individual costs assigned to the desired speed, lateral position, and the label assigned to each of the other n vehicles.
  • ⁇ i 2 k ( u ⁇ ( x i , y i ) ⁇ ( x i ⁇ 1 , y i ⁇ 1 ) ⁇ / r ) 2 .
  • dist(x, y, l) is the distance from the point (x, y) to the lane position l.
  • Assigning a weight to each of these costs may provide a single objective function for the trajectory planner, ⁇ (T) .
  • a cost that encourages smooth driving may be added to the objective.
  • hard constraints can be added to the objective. For example, (x i , y i ) may be prohibited from being off the roadway, and (x i , y i ) may be forbidden from being close to x′ j , y′ j ) for any trajectory point (x′ j , y′ j ) of any other vehicle if
  • the policy, ⁇ y can be decomposed into a mapping from the agnostic state to a set of Desires and a mapping from the Desires to an actual trajectory.
  • the latter mapping is not based on learning and may be implemented by solving an optimization problem whose cost depends on the Desires and whose hard constraints may guarantee functional safety of the policy.
  • mapping from the agnostic state to the set of Desires As described above, to be compliant with functional safety, a system reliant upon reinforcement learning alone may suffer a high and unwieldy variance on the reward R( s ). This result may be avoided by decomposing the problem into a mapping from (agnostic) state space to a set of Desires using policy gradient iterations followed by a mapping to an actual trajectory which does not involve a system trained based on machine learning.
  • the decision making may be further decomposed into semantically meaningful components.
  • the size of might be large and even continuous.
  • the variance may grow with the time horizon T.
  • the value of T may be roughly 250 which may be high enough to create significant variance. Supposing a sampling rate is in the range of 10 Hz and the merge area 1130 is 100 meters, preparation for the merge may begin approximately 300 meters before the merge area. If the host vehicle travels at 16 meters per second (about 60 km per hour), then the value of T for an episode may be roughly 250.
  • an options graph that may be representative of the double merge scenario depicted in FIG. 11D is shown in FIG. 11E .
  • an options graph may represent a hierarchical set of decisions organized as a Directed Acyclic Graph (DAG).
  • DAG Directed Acyclic Graph
  • the decision process may traverse the graph, starting from the root node, until it reaches a “leaf” node, namely, a node that has no outgoing edges.
  • Each internal node may implement a policy function that chooses a child from among its available children.
  • ⁇ v may specify the policy of choosing a child of v. If ⁇ is the concatenation of all the ⁇ v , then ⁇ ⁇ (D) may be defined by traversing from the root of the graph to a leaf, while at each node v using the policy defined by ⁇ v , to choose a child node.
  • root node 1140 may first decide if the host vehicle is within the merging area (e.g., area 1130 of FIG. 11D ) or if the host vehicle instead is approaching the merging area and needs to prepare for a possible merge. In both cases, the host vehicle may need to decide whether to change lanes (e.g., tothe left or to the right side) or whether to stay in the current lane. If the host vehicle has decided to change lanes, the host vehicle may need to decide whether conditions are suitable to go on and perform the lane change maneuver(e.g., at “go” node 1142 ).
  • lanes e.g., tothe left or to the right side
  • the host vehicle may need to decide whether conditions are suitable to go on and perform the lane change maneuver(e.g., at “go” node 1142 ).
  • the host vehicle may attempt to “push” toward the desired lane (e.g., at node 1144 as part of a negotiation with vehicles in the desired lane) by aiming at being on the lane mark.
  • the host vehicle may opt to “stay” in the same lane (e.g., at node 1146 ).
  • Such a process may determine the lateral position for the host vehicle in a natural way. For example,
  • a potential benefit of the options is the interpretability of the results. Another potential benefit is that the decomposable structure of the set can be relied upon and, therefore, the policy at each node may be chosen from among a small number of possibilities. Additionally, the structure may allow for a reduction in the variance of the policy gradient estimator.
  • Such a value (or any other suitable value depending on a particular navigational scenario) may provide enough time to see the consequences of the host vehicle actions (e.g., if the host vehicle decided to change lanes as a preparation for the merge, the host vehicle will see the benefit only after a successful completion of the merge).
  • the host vehicle due to the dynamic of driving, the host vehicle must make decisions at a fast enough frequency (e.g., 10 Hz in the case described above).
  • the options graph may enable a decrease in the effective value of Tin at least two ways.
  • a reward can be defined for lower level decisions while taking into account shorter episodes. For example, when the host vehicle has already chosen a “lane change” and the “go” node, a policy can be learned for assigning semantic meaning to vehicles by looking at episodes of 2-3 seconds (meaning that T becomes 20-30 instead of 250).
  • the host vehicle may not need to make decisions every 0.1 seconds. Instead, the host vehicle may be able to either make decisions at a lower frequency (e.g., every second), or implement an “option termination” function, and then the gradient may be calculated only after every termination of the option.
  • the effective value of T may be an order of magnitude smaller than its original value. All in all, the estimator at every node may depend on a value of T which is an order of magnitude smaller than the original 250 steps, which may immediately transfer to a smaller variance.
  • hard constraints may promote safer driving, and there may be several different types of constraints.
  • static hard constraints may be defined directly from the sensing state. These may include speed bumps, speed limits, road curvature, junctions, etc., within the environment of the host vehicle that may implicate one or more constraints on vehicle speed, heading, acceleration, breaking (deceleration), etc.
  • Static hard constraints may also include semantic free space where the host vehicle is prohibited from going outside of the free space and from navigating too close to physical barriers, for example.
  • Static hard constraints may also limit (e.g., prohibit) maneuvers that do not comply with various aspects of a kinematic motion of the vehicle, for example, a static hard constraint can be used to prohibit maneuvers that might lead to the host vehicle overturning, sliding, or otherwise losing control.
  • Hard constraints may also be associated with vehicles. For example, a constraint may be employed requiring that a vehicle maintain a longitudinal distance to other vehicles of at least one meter and a lateral distance from other vehicles of at least 0.5 meters. Constraints may also be applied such that the host vehicle will avoid maintaining a collision course with one or more other vehicles.
  • a time r may be a measure of time based on a particular scene. The predicted trajectories of the host vehicle and one or more other vehicles may be considered from a current time to time r. Where the two trajectories intersect, t i a , t i i ) may represent the time of arrival and the leaving time of vehicle i to the intersection point.
  • each car will arrive at point when a first part of the car passes the intersection point, and a certain amount of time will be required before the last part of the car passes through the intersection point. This amount of time separates the arrival time from the leaving time. Assuming that t 1 a ⁇ t 2 a (i.e., that the arrival time of vehicle 1 is less than the arrival time of vehicle 2 ), then we will want to ensure that vehicle 1 has left the intersection point prior to vehicle 2 arriving. Otherwise, a collision would result. Thus, a hard constraint may be implemented such that t 1 i >t 2 a .
  • an added margin of safety may be obtained by including a buffer time into the constraint (e.g., 0.5 seconds or another suitable value).
  • a buffer time e.g., 0.5 seconds or another suitable value.
  • a hard constraint relating to predicted intersection trajectories of two vehicles may be expressed as t 1 i >t 2 a +0.5.
  • the amount of time ⁇ over which the trajectories of the host vehicle and one or more other vehicles are tracked may vary. In junction scenarios, however, where speeds may be lower, ⁇ may be longer, and ⁇ may be defined such that a host vehicle will enter and leave the junction in less than ⁇ seconds.
  • trajectory prediction may be relatively straightforward, as the host vehicle generally already understands and, indeed, is planning an intended trajectory at any given time. Relative to other vehicles, predicting their trajectories can be less straightforward.
  • the baseline calculation for determining predicted trajectories may rely on the current speed and heading of the other vehicles, as determined, for example, based on analysis of an image stream captured by one or more cameras and/or other sensors (radar, lidar, acoustic, etc.) aboard the host vehicle.
  • the trajectories of other vehicles can be based, at least in part, upon the position of the other vehicles relative to the lanes and based upon applicable give-way rules.
  • the trajectories of other vehicles can be based, at least in part, upon the position of the other vehicles relative to the lanes and based upon applicable give-way rules.
  • the host vehicle may assume that a next-lane vehicle will stay in its lane unless there is observed evidence (e.g., a signal light, strong lateral movement, movement across a lane boundary) indicating that the next-lane vehicle will cut into the lane of the host vehicle.
  • evidence e.g., a signal light, strong lateral movement, movement across a lane boundary
  • Hard constraints may also be applied with respect to pedestrians in an environment of the host vehicle.
  • a buffer distance may be established with respect to pedestrians such that the host vehicle is prohibited from navigating any closer than the prescribed buffer distance relative to any observed pedestrian.
  • the pedestrian buffer distance may be any suitable distance.
  • the buffer distance may be at least one meter relative to an observed pedestrian.
  • t(p) may represent the time required for the pedestrian to reach point p.
  • t(p) must be larger than the time the host vehicle will reach point p (with sufficient difference in time such that the host vehicle passes in front of the pedestrian by a distance of at least one meter) or that t(p) must be less than the time the host vehicle will reach point p (e.g., if the host vehicle brakes to give way to the pedestrian).
  • the hard constraint may require that the host vehicle arrive at point p at a sufficient time later than the pedestrian such that the host vehicle can pass behind the pedestrian and maintain the required buffer distance of at least one meter.
  • the pedestrian hard constraint may be relaxed (e.g., to a smaller buffer of at least 0.75 meters or 0.50 meters).
  • constraints may be relaxed where it is determined that not all can be met. For example, in situations where a road is too narrow to leave desired spacing (e.g., 0.5 meters) from both curbs or from a curb and a parked vehicle, one or more the constraints may be relaxed if there are mitigating circumstances. For example, if there are no pedestrians (or other objects) on the sidewalk one can proceed slowly at 0.1 meters from a curb. In some embodiments, constraints may be relaxed if doing so will improve the user experience. For example, in order to avoid a pothole, constraints may be relaxed to allow a vehicle to navigate closer to the edges of the lane, a curb, or a pedestrian more than might ordinarily be permitted.
  • the one or more constraints chosen to relax are those deemed to have the least available negative impact to safety. For example, a constraint relating to how close the vehicle may travel to the curb or to a concrete barrier may be relaxed before relaxing one dealing with proximity to other vehicles. In some embodiments, pedestrian constraints may be the last to be relaxed, or may never be relaxed in some situations.
  • FIG. 12 shows an example of a scene that may be captured and analyzed during navigation of a host vehicle.
  • a host vehicle may include a navigation system (e.g., system 100 ), as described above, that may receive from a camera (e.g., at least one of image capture device 122 , image capture device 124 , and image capture device 126 ) associated with the host vehicle a plurality of images representative of an environment of the host vehicle.
  • the scene shown in FIG. 12 is an example of one of the images that may be captured at time t from an environment of a host vehicle traveling in lane 1210 along a predicted trajectory 1212 .
  • the navigation system may include at least one processing device (e.g., including any of the EyeQ processors or other devices described above) that are specifically programmed to receive the plurality of images and analyze the images to determine an action in response to the scene.
  • the at least one processing device may implement sensing module 801 , driving policy module 803 , and control module 805 , as shown in FIG. 8 .
  • Sensing module 801 may be responsible for collecting and outputting the image information collected from the cameras and providing that information, in the form of an identified navigational state, to driving policy module 803 , which may constitute a trained navigational system that has been trained through machine learning techniques, such as supervised learning, reinforcement learning, etc.
  • driving policy module 803 may generate a desired navigational action for execution by the host vehicle in response to the identified navigational state.
  • the at least one processing device may translate the desired navigation action directly into navigational commands using, for example, control module 805 .
  • hard constraints may be applied such that the desired navigational action provided by the driving policy module 803 is tested against various predetermined navigational constraints that may be implicated by the scene and the desired navigational action. For example, where driving policy module 803 outputs a desired navigational action that would cause the host vehicle to follow trajectory 1212 , this navigational action may be tested relative to one or more hard constraints associated with various aspects of the environment of the host vehicle.
  • a captured image 1201 may reveal a curb 1213 , a pedestrian 1215 , a target vehicle 1217 , and a stationary object (e.g., an overturned box) present in the scene.
  • curb 1213 may be associated with a static constraint that prohibits the host vehicle from navigating into the curb or past the curb and onto a sidewalk 1214 .
  • Curb 1213 may also be associated with a road barrier envelope that defines a distance (e.g., a buffer zone) extending away from (e.g., by 0.1 meters, 0.25 meters, 0.5 meters, 1 meter, etc.) and along the curb, which defines a no-navigate zone for the host vehicle.
  • static constraints may be associated with other types of roadside boundaries as well (e.g., guard rails, concrete pillars, traffic cones, pylons, or any other type of roadside barrier).
  • distances and ranging may be determined by any suitable method.
  • distance information may be provided by onboard radar and/or lidar systems.
  • distance information may be derived from analysis of one or more images captured from the environment of the host vehicle. For example, numbers of pixels of a recognized object represented in an image may be determined and compared to known field of view and focal length geometries of the image capture devices to determine scale and distances. Velocities and accelerations may be determined, for example, by observing changes in scale between objects from image to image over known time intervals. This analysis may indicate the direction of movement toward or away from the host vehicle along with how fast the object is pulling away from or coming toward the host vehicle. Crossing velocity may be determined through analysis of the change in an object's X coordinate position from one image to another over known time periods.
  • Pedestrian 1215 may be associated with a pedestrian envelope that defines a buffer zone 1216 .
  • an imposed hard constraint may prohibit the host vehicle from navigating within a distance of 1 meter from pedestrian 1215 (in any direction relative to the pedestrian).
  • Pedestrian 1215 may also define the location of a pedestrian influence zone 1220 .
  • Such an influence zone may be associated with a constraint that limits the speed of the host vehicle within the influence zone.
  • the influence zone may extend 5 meters, 10 meters, 20 meters, etc., from pedestrian 1215 .
  • Each graduation of the influence zone may be associated with a different speed limit
  • host vehicle may be limited to a first speed (e.g., 10 mph, 20 mph, etc.) that may be less than a speed limit in a pedestrian influence zone extending from 5 meters to 10 meters. Any graduation for the various stages of the influence zone may be used.
  • the first stage may be narrower than from 1 meter to five meters and may extend only from one meter to two meters.
  • the first stage of the influence zone may extend from 1 meter (the boundary of the no-navigate zone around a pedestrian) to a distance of at least 10 meters.
  • a second stage in turn, may extend from 10 meters to at least about 20 meters.
  • the second stage may be associated with a maximum rate of travel for the host vehicle that is greater than the maximum rate of travel associated with the first stage of the pedestrian influence zone.
  • One or more stationary object constraints may also be implicated by the detected scene in the environment of the host vehicle.
  • the at least one processing device may detect a stationary object, such as box 1219 present in the roadway.
  • Detected stationary objects may include various objects, such as at least one of a tree, a pole, a road sign, or an object in a roadway.
  • One or more predefined navigational constraints may be associated with the detected stationary object.
  • such constraints may include a stationary object envelope, wherein the stationary object envelope defines a buffer zone about the object within which navigation of the host vehicle may be prohibited. At least a portion of the buffer zone may extend a predetermined distance from an edge of the detected stationary object.
  • a buffer zone of at least 0.1 meters, 0.25 meters, 0.5 meters or more may be associated with box 1219 such that the host vehicle will pass to the right or to the left of the box by at least some distance (e.g., the buffer zone distance) in order to avoid a collision with the detected stationary object.
  • the predefined hard constraints may also include one or more target vehicle constraints.
  • a target vehicle 1217 may be detected in image 1201 .
  • one or more hard constraints may be employed.
  • a target vehicle envelope may be associated with a single buffer zone distance.
  • the buffer zone may be defined by a 1 meter distance surrounding the target vehicle in all directions.
  • the buffer zone may define a region extending from the target vehicle by at least one meter into which the host vehicle is prohibited from navigating.
  • the envelope surrounding target vehicle 1217 need not be defined by a fixed buffer distance, however.
  • the predefined hard constraints associate with target vehicles (or any other movable objects detected in the environment of the host vehicle) may depend on the orientation of the host vehicle relative to the detected target vehicle.
  • a longitudinal buffer zone distance e.g., one extending from the target vehicle toward the front or rear of the host vehicle—such as in the case that the host vehicle is driving toward the target vehicle
  • a lateral buffer zone distance (e.g., one extending from the target vehicle toward either side of the host vehicle—such as when the host vehicle is traveling in a same or opposite direction as the target vehicle such that a side of the host vehicle will pass adjacent to a side of the target vehicle) may be at least 0.5 meters.
  • constraints may also be implicated by detection of a target vehicle or a pedestrian in the environment of the host vehicle.
  • the predicted trajectories of the host vehicle and target vehicle 1217 may be considered and where the two trajectories intersect (e.g., at intersection point 1230 ), a hard constraint may require t 1 l >t 2 a or t 1 i >t 2 a +0.5 where the host vehicle is vehicle 1 , and target vehicle 1217 is vehicle 2
  • the trajectory of pedestrian 1215 (based on a heading direction and speed) may be monitored relative to the projected trajectory of the host vehicle.
  • t(p) Given a particular pedestrian trajectory, with every point p on the trajectory, t(p) will represent the time required for the pedestrian to reach point p (i.e., point 1231 in FIG. 12 ). To maintain the required buffer distance of at least 1 meter from the pedestrian, either t(p) must be larger than the time the host vehicle will reach point p (with sufficient difference in time such that the host vehicle passes in front of the pedestrian by a distance of at least one meter) or that t(p) must be less than the time the host vehicle will reach point p (e.g., if the host vehicle brakes to give way to the pedestrian). Still, in the latter example, the hard constraint will require that the host vehicle arrive at point p at a sufficient time later than the pedestrian such that the host vehicle can pass behind the pedestrian and maintain the required buffer distance of at least one meter.
  • a maximum deceleration rate of the host vehicle may be employed in at least some cases. Such a maximum deceleration rate may be determined based on a detected distance to a target vehicle following the host vehicle (e.g., using images collected from a rearward facing camera).
  • the hard constraints may include a mandatory stop at a sensed crosswalk or a railroad crossing or other applicable constraints.
  • those constraints may be imposed relative to one or more planned navigational actions for the host vehicle. For example, where analysis of a scene results in driving policy module 803 returning a desired navigational action, that desired navigational action may be tested against one or more implicated constraints. If the desired navigational action is determined to violate any aspect of the implicated constraints (e.g., if the desired navigational action would carry the host vehicle within a distance of 0.7 meters of pedestrian 1215 where a predefined hard constraint requires that the host vehicle remain at least 1.0 meters from pedestrian 1215 ), then at least one modification to the desired navigational action may be made based on the one or more predefined navigational constraints. Adjusting the desired navigational action in this way may provide an actual navigational action for the host vehicle in compliance with the constraints implicated by a particular scene detected in the environment of the host vehicle.
  • That navigational action may be implemented by causing at least one adjustment of a navigational actuator of the host vehicle in response to the determined actual navigational action for the host vehicle.
  • a navigational actuator may include at least one of a steering mechanism, a brake, or an accelerator of the host vehicle.
  • constraints may be employed with a navigational system to ensure safe operation of a host vehicle.
  • the constraints may include a minimum safe driving distance with respect to a pedestrian, a target vehicle, a road barrier, or a detected object, a maximum speed of travel when passing within an influence zone of a detected pedestrian, or a maximum deceleration rate for the host vehicle, among others.
  • These constraints may be imposed with a trained system trained based on machine learning (supervised, reinforcement, or a combination), but they also may be useful with non-trained systems (e.g., those employing algorithms to directly address anticipated situations arising in scenes from a host vehicle environment).
  • the navigation system may determine the available navigational action that achieves the highest priority constraints first. For example, the system may cause the vehicle to avoid a pedestrian first even if navigation to avoid the pedestrian would result in a collision with another vehicle or an object detected in a road. In another example, the system may cause the vehicle to ride up on a curb to avoid a pedestrian.
  • FIG. 13 provides a flowchart illustrating an algorithm for implementing a hierarchy of implicated constraints determined based on analysis of a scene in an environment of a host vehicle.
  • at least one processing device associated with the navigational system e.g., an EyeQ processor, etc.
  • a navigational state associated with the host vehicle may be identified.
  • a navigational state may indicate that the host vehicle is traveling along a two-lane road 1210 , as in FIG.
  • a target vehicle 1217 is moving through an intersection ahead of the host vehicle, that a pedestrian 1215 is waiting to cross the road on which the host vehicle travels, that an object 1219 is present ahead in the host vehicle lane, among various other attributes of the scene.
  • one or more navigational constraints implicated by the navigational state of the host vehicle may be determined.
  • the at least one processing device after analyzing a scene in the environment of the host vehicle represented by one or more captured images may determine one or more navigational constraints implicated by objects, vehicles, pedestrians, etc., recognized through image analysis of the captured images.
  • the at least one processing device may determine at least a first predefined navigational constraint and a second predefined navigational constraint implicated by the navigational state, and the first predefined navigational constraint may differ from the second predefined navigational constraint.
  • the first navigational constraint may relate to one or more target vehicles detected in the environment of the host vehicle
  • the second navigational constraint may relate to a pedestrian detected in the environment of the host vehicle.
  • the at least one processing device may determine a priority associated with constraints identified in step 1305 .
  • the second predefined navigational constraint relating to pedestrians, may have a priority higher than the first predefined navigational constraint, which relates to target vehicles.
  • priorities associated with navigational constraints may be determined or assigned based on various factors, in some embodiments, the priority of a navigational constraint may be related to its relative importance from a safety perspective. For example, while it may be important that all implemented navigational constraints be followed or satisfied in as many situations as possible, some constraints may be associated with greater safety risks than others and, therefore, may be assigned higher priorities.
  • a navigational constraint requiring that the host vehicle maintain at least a 1 meter spacing from a pedestrian may have a higher priority than a constraint requiring that the host vehicle maintain at least one meter spacing from a target vehicle. This may be because a collision with a pedestrian may have more severe consequences than a collision with another vehicle.
  • maintaining a space between the host vehicle and a target vehicle may have a higher priority than a constraint requiring the host vehicle to avoid a box in the road, to drive less than a certain speed over a speed bump, or to expose the host vehicle occupants to no more than a maximum acceleration level.
  • While driving policy module 803 is designed to maximize safety by satisfying navigational constraints implicated by a particular scene or navigational state, in some situations it may be physically impossible to satisfy every implicated constraint. In such situations, the priority of each implicated constraint may be used to determine which of the implicated constraints should be satisfied first, as shown at step 1309 . Continuing with the example above, in a situation where it is not possible satisfy both the pedestrian gap constraint and the target vehicle gap constraint, but rather only one of the constraints can be satisfied, then the higher priority of the pedestrian gap constraint may result in that constraint being satisfied before attempting to maintain a gap to the target vehicle.
  • the at least one processing device may determine, based on the identified navigational state of the host vehicle, a first navigational action for the host vehicle satisfying both the first predefined navigational constraint and the second predefined navigational constraint where both the first predefined navigational constraint and the second predefined navigational constraint can be satisfied, as shown at step 1311 .
  • the at least one processing device may determine, based on the identified navigational state, a second navigational action for the host vehicle satisfying the second predefined navigational constraint (i.e., the higher priority constraint), but not satisfying the first predefined navigational constraint (having a priority lower than the second navigational constraint), where the first predefined navigational constraint and the second predefined navigational constraint cannot both be satisfied, as shown at step 1313 .
  • the second predefined navigational constraint i.e., the higher priority constraint
  • the first predefined navigational constraint having a priority lower than the second navigational constraint
  • the at least one processing device can cause at least one adjustment of a navigational actuator of the host vehicle in response to the determined first navigational action or the determined second navigational action for the host vehicle.
  • the navigational actuator may include at least one of a steering mechanism, a brake, or an accelerator.
  • navigational constraints may be imposed for safety purposes.
  • the constraints may include a minimum safe driving distance with respect to a pedestrian, a target vehicle, a road barrier, or a detected object, a maximum speed of travel when passing within an influence zone of a detected pedestrian, or a maximum deceleration rate for the host vehicle, among others.
  • These constraints may be imposed in a learning or non-learning navigational system. In certain situations, these constraints may be relaxed. For example, where the host vehicle slows or stops near a pedestrian, then progresses slowly to convey an intention to pass by the pedestrian, a response of the pedestrian can be detected from acquired images.
  • the system may relax one or more predefined constraints and implement a less stringent constraint (e.g., allow the vehicle to navigate within 0.5 meters of a pedestrian rather than within a more stringent 1 meter boundary).
  • FIG. 14 provides a flowchart for implementing control of the host vehicle based on relaxation of one or more navigational constraints.
  • the at least one processing device may receive, from a camera associated with the host vehicle, a plurality of images representative of an environment of the host vehicle. Analysis of the images at step 1403 may enable identification of a navigational state associated with the host vehicle.
  • the at least one processor may determine navigational constraints associated with the navigational state of the host vehicle. The navigational constraints may include a first predefined navigational constraint implicated by at least one aspect of the navigational state.
  • analysis of the plurality of images may reveal the presence of at least one navigational constraint relaxation factor.
  • a navigational constraint relaxation factor may include any suitable indicator that one or more navigational constraints may be suspended, altered, or otherwise relaxed in at least one aspect.
  • the at least one navigational constraint relaxation factor may include a determination (based on image analysis) that the eyes of a pedestrian are looking in a direction of the host vehicle. In such cases, it may more safely be assumed that the pedestrian is aware of the host vehicle. As a result, a confidence level may be higher that the pedestrian will not engage in unexpected actions that cause the pedestrian to move into a path of the host vehicle. Other constraint relaxation factors may also be used.
  • the at least one navigational constraint relaxation factor may include: a pedestrian determined to be not moving (e.g., one presumed to be less likely of entering a path of the host vehicle); or a pedestrian whose motion is determined to be slowing.
  • the navigational constraint relaxation factor may also include more complicated actions, such as a pedestrian determined to be not moving after the host vehicle has come to a stop and then resumed movement. In such a situation, the pedestrian may be assumed to understand that the host vehicle has a right of way, and the pedestrian coming to a stop may suggest an intent of the pedestrian to give way to the host vehicle.
  • curb stone e.g., a low curb stone or one with a gradual slope might allow a relaxed distance constraint
  • lack of pedestrians or other objects on sidewalk a vehicle with its engine not running may have a relaxed distance, or a situation in which a pedestrian is facing away and/or is moving away from the area towards which the host vehicle is heading.
  • a second navigational constraint may be determined or developed in response to detection of the constraint relaxation factor.
  • This second navigational constraint may be different from the first navigational constraint and may include at least one characteristic relaxed with respect to the first navigational constraint.
  • the second navigational constraint may include a newly generated constraint based on the first constraint, where the newly generated constraint includes at least one modification that relaxes the first constraint in at least one respect.
  • the second constraint may constitute a predetermined constraint that is less stringent than the first navigational constraint in at least one respect.
  • such second constraints may be reserved for usage only for situations where a constraint relaxation factor is identified in an environment of the host vehicle. Whether the second constraint is newly generated or selected from a set of fully or partially available predetermined constraints, application of a second navigational constraint in place of a more stringent first navigational constraint (that may be applied in the absence of detection of relevant navigational constraint relaxation factors) may be referred to as constraint relaxation and may be accomplished in step 1409 .
  • a navigational action for the host vehicle may be determined at step 1411 .
  • the navigational action for the host vehicle may be based on the identified navigational state and may satisfy the second navigational constraint.
  • the navigational action may be implemented at step 1413 by causing at least one adjustment of a navigational actuator of the host vehicle in response to the determined navigational action.
  • navigational constraints and relaxed navigational constraints may be employed with navigational systems that are trained (e.g., through machine learning) or untrained (e.g., systems programmed to respond with predetermined actions in response to specific navigational states).
  • trained navigational systems e.g., through machine learning
  • untrained e.g., systems programmed to respond with predetermined actions in response to specific navigational states
  • the availability of relaxed navigational constraints for certain navigational situations may represent a mode switching from a trained system response to an untrained system response.
  • a trained navigational network may determine an original navigational action for the host vehicle, based on the first navigational constraint. The action taken by the vehicle, however, may be one that is different from the navigational action satisfying the first navigational constraint.
  • the action taken may satisfy the more relaxed second navigational constraint and may be an action developed by a non-trained system (e.g., as a response to detection of a particular condition in the environment of the host vehicle, such as the presence of a navigational constraint relaxation factor).
  • a non-trained system e.g., as a response to detection of a particular condition in the environment of the host vehicle, such as the presence of a navigational constraint relaxation factor.
  • a relaxed navigational constraint may include a different or modified buffer zone.
  • the different or modified buffer zone may have a distance relative to the pedestrian that is less than the original or unmodified buffer zone relative to the detected pedestrian.
  • a relaxed characteristic of a navigational constraint may include a reduced width in a buffer zone associated with at least one pedestrian, as noted above.
  • the relaxed characteristic may also include a reduced width in a buffer zone associated with a target vehicle, a detected object, a roadside barrier, or any other object detected in the environment of the host vehicle.
  • the at least one relaxed characteristic may also include other types of modifications in navigational constraint characteristics.
  • the relaxed characteristic may include an increase in speed associated with at least one predefined navigational constraint.
  • the relaxed characteristic may also include an increase in a maximum allowable deceleration/acceleration associated with at least one predefined navigational constraint.
  • a navigational system may determine that conditions warrant augmentation of a normal set of navigational constraints.
  • Such augmentation may include adding new constraints to a predefined set of constraints or adjusting one or more aspects of a predefined constraint. The addition or adjustment may result in more conservative navigation relative the predefined set of constraints applicable under normal driving conditions.
  • Conditions that may warrant constraint augmentation may include sensor failure, adverse environmental conditions (rain, snow, fog, or other conditions associated with reduced visibility or reduced vehicle traction), etc.
  • FIG. 15 provides a flowchart for implementing control of the host vehicle based on augmentation of one or more navigational constraints.
  • the at least one processing device may receive, from a camera associated with the host vehicle, a plurality of images representative of an environment of the host vehicle. Analysis of the images at step 1503 may enable identification of a navigational state associated with the host vehicle.
  • the at least one processor may determine navigational constraints associated with the navigational state of the host vehicle.
  • the navigational constraints may include a first predefined navigational constraint implicated by at least one aspect of the navigational state.
  • analysis of the plurality of images may reveal the presence of at least one navigational constraint augmentation factor.
  • An implicated navigational constraint may include any of the navigational constraints discussed above (e.g., with respect to FIG. 12 ) or any other suitable navigational constraints.
  • a navigational constraint augmentation factor may include any indicator that one or more navigational constraints may be supplemented/augmented in at least one aspect. Supplementation or augmentation of navigational constraints may be performed on a per set basis (e.g., by adding new navigational constraints to a predetermined set of constraints) or may be performed on a per constraint basis (e.g., modifying a particular constraint such that the modified constraint is more restrictive than the original, or adding a new constraint that corresponds to a predetermined constraint, wherein the new constraint is more restrictive than the corresponding constraint in at least one aspect).
  • supplementation or augmentation of navigational constraints may refer selection from among a set of predetermined constraints based on a hierarchy.
  • a set of augmented constraints may be available for selection based on whether a navigational augmentation factor is detected in the environment of or relative to the host vehicle. Under normal conditions where no augmentation factor is detected, then the implicated navigational constraints may be drawn from constraints applicable to normal conditions.
  • the implicated constraints may be drawn from augmented constraints either generated or predefined relative to the one or more augmentation factors.
  • the augmented constraints may be more restrictive in at least one aspect than corresponding constraints applicable under normal conditions.
  • the at least one navigational constraint augmentation factor may include a detection (e.g., based on image analysis) of the presence of ice, snow, or water on a surface of a road in the environment of the host vehicle. Such a determination may be based, for example, upon detection of: areas of reflectance higher than expected for dry roadways (e.g., indicative of ice or water on the roadway); white regions on the road indicating the presence of snow; shadows on the roadway consistent with the presence of longitudinal trenches (e.g., tire tracks in snow) on the roadway; water droplets or ice/snow particles on a windshield of the host vehicle; or any other suitable indicator of the presence of water or ice/snow on a surface of a road.
  • a detection e.g., based on image analysis
  • the at least one navigational constraint augmentation factor may also include detection of particulates on an outer surface of a windshield of the host vehicle. Such particulates may impair image quality of one or more image capture devices associated with the host vehicle. While described with respect to a windshield of the host vehicle, which is relevant for cameras mounted behind the windshield of the host vehicle, detection of particulates on other surfaces (e.g., a lens or lens cover of a camera, headlight lens, rear windshield, a tail light lens, or any other surface of the host vehicle visible to an image capture device (or detected by a sensor) associated with the host vehicle may also indicate the presence of a navigational constraint augmentation factor.
  • a navigational constraint augmentation factor may also include detection of particulates on an outer surface of a windshield of the host vehicle. Such particulates may impair image quality of one or more image capture devices associated with the host vehicle. While described with respect to a windshield of the host vehicle, which is relevant for cameras mounted behind the windshield of the host vehicle, detection of particulates on other surfaces (e.
  • the navigational constraint augmentation factor may also be detected as an attribute of one or more image acquisition devices.
  • a detected decrease in image quality of one or more images captured by an image capture device (e.g., a camera) associated with the host vehicle may also constitute a navigational constraint augmentation factor.
  • a decline in image quality may be associated with a hardware failure or partial hardware failure associated with the image capture device or an assembly associated with the image capture device.
  • Such a decline in image quality may also be caused by environmental conditions. For example, the presence of smoke, fog, rain, snow, etc., in the air surrounding the host vehicle may also contribute to reduced image quality relative to the road, pedestrians, target vehicles, etc., that may be present in an environment of the host vehicle.
  • the navigational constraint augmentation factor may also relate to other aspects of the host vehicle.
  • the navigational constraint augmentation factor may include a detected failure or partial failure of a system or sensor associate with the host vehicle.
  • Such an augmentation factor may include, for example, detection of failure or partial failure of a speed sensor, GPS receiver, accelerometer, camera, radar, lidar, brakes, tires, or any other system associated with the host vehicle that may impact the ability of the host vehicle to navigate relative to navigational constraints associated with a navigational state of the host vehicle.
  • a second navigational constraint may be determined or developed in response to detection of the constraint augmentation factor.
  • This second navigational constraint may be different from the first navigational constraint and may include at least one characteristic augmented with respect to the first navigational constraint.
  • the second navigational constraint may be more restrictive than the first navigational constraint, because detection of a constraint augmentation factor in the environment of the host vehicle or associated with the host vehicle may suggest that the host vehicle may have at least one navigational capability reduced with respect to normal operating conditions.
  • Such reduced capabilities may include lowered road traction (e.g., ice, snow, or water on a roadway; reduced tire pressure; etc.); impaired vision (e.g., rain, snow, dust, smoke, fog etc. that reduces captured image quality); impaired detection capability (e.g., sensor failure or partial failure, reduced sensor performance, etc.), or any other reduction in capability of the host vehicle to navigate in response to a detected navigational state.
  • lowered road traction e.g., ice, snow, or water on a roadway; reduced tire pressure; etc.
  • impaired vision e.g., rain, snow, dust, smoke, fog etc. that reduces captured image quality
  • impaired detection capability e.g., sensor failure or partial failure, reduced sensor performance, etc.
  • a navigational action for the host vehicle may be determined at step 1511 .
  • the navigational action for the host vehicle may be based on the identified navigational state and may satisfy the second navigational (i.e., augmented) constraint.
  • the navigational action may be implemented at step 1513 by causing at least one adjustment of a navigational actuator of the host vehicle in response to the determined navigational action.
  • navigational constraints and augmented navigational constraints may be employed with navigational systems that are trained (e.g., through machine learning) or untrained (e.g., systems programmed to respond with predetermined actions in response to specific navigational states).
  • trained navigational systems e.g., through machine learning
  • untrained navigational constraints e.g., systems programmed to respond with predetermined actions in response to specific navigational states.
  • the availability of augmented navigational constraints for certain navigational situations may represent a mode switching from a trained system response to an untrained system response.
  • a trained navigational network may determine an original navigational action for the host vehicle, based on the first navigational constraint. The action taken by the vehicle, however, may be one that is different from the navigational action satisfying the first navigational constraint.
  • the action taken may satisfy the augmented second navigational constraint and may be an action developed by a non-trained system (e.g., as a response to detection of a particular condition in the environment of the host vehicle, such as the presence of a navigational constraint augmented factor).
  • a non-trained system e.g., as a response to detection of a particular condition in the environment of the host vehicle, such as the presence of a navigational constraint augmented factor.
  • navigational constraints that may be generated, supplemented, or augmented in response to detection in the environment of the host vehicle of a constraint augmentation factor.
  • a predefined navigational constraint includes a buffer zone associated with a detected pedestrian, object, vehicle, etc., and at least a portion of the buffer zone extends a distance from the detected pedestrian/object/vehicle
  • an augmented navigational constraint (either newly developed, called up from memory from a predetermined set, or generated as an augmented version of a preexisting constraint) may include a different or modified buffer zone.
  • the different or modified buffer zone may have a distance relative to the pedestrian/object/vehicle that is greater than the original or unmodified buffer zone relative to the detected pedestrian/object/vehicle.
  • the host vehicle may be forced to navigate further from the detected pedestrian/object/vehicle, where an appropriate constraint augmentation factor is detected in the environment of the host vehicle or relative to the host vehicle.
  • the at least one augmented characteristic may also include other types of modifications in navigational constraint characteristics.
  • the augmented characteristic may include a decrease in speed associated with at least one predefined navigational constraint.
  • the augmented characteristic may also include a decrease in a maximum allowable deceleration/acceleration associated with at least one predefined navigational constraint.
  • the disclosed navigational system can respond not only to a detected navigational state in an environment of the host vehicle, but may also determine one or more navigational actions based on long range planning. For example, the system may consider the potential impact on future navigational states of one or more navigational actions available as options for navigating with respect to a detected navigational state. Considering the effects of available actions on future states may enable the navigational system to determine navigational actions based not just upon a currently detected navigational state, but also based upon long range planning. Navigation using long range planning techniques may be especially applicable where one or more reward functions are employed by the navigation system as a technique for selecting navigational actions from among available options.
  • Potential rewards may be analyzed with respect to the available navigational actions that may be taken in response to a detected, current navigational state of the host vehicle. Further, however, the potential rewards may also be analyzed relative to actions that may be taken in response to future navigational states projected to result from the available actions to a current navigational state. As a result, the disclosed navigational system may, in some cases, select a navigational action in response to a detected navigational state even where the selected navigational action may not yield the highest reward from among the available actions that may be taken in response to the current navigational state.
  • the disclosed navigational system capable of long range planning may choose a suboptimal short term action where long term prediction indicates that a short term loss in reward may result in long term reward gains.
  • autonomous driving applications may involve a series of planning problems, where the navigational system may decide on immediate actions in order to optimize a longer term objective. For example, when a vehicle is confronted with a merge situation at a roundabout, the navigational system may decide on an immediate acceleration or braking command in order to initiate navigation into the roundabout. While the immediate action to the detected navigational state at the roundabout may involve an acceleration or braking command responsive to the detected state, the long term objective is a successful merge, and the long term effect of the selected command is the success/failure of the merge.
  • the planning problem may be addressed by decomposing the problem into two phases.
  • supervised learning may be applied for predicting the near future based on the present (assuming the predictor will be differentiable with respect to the representation of the present).
  • a full trajectory of the agent may be modeled using a recurrent neural network, where unexplained factors are modeled as (additive) input nodes. This may allow solutions to the long-term planning problem to be determined using supervised learning techniques and direct optimization over the recurrent neural network. Such an approach may also enable the learning of robust policies by incorporating adversarial elements to the environment.
  • Sensing deals with finding a compact representation of the present state of the environment, while planning deals with deciding on what actions to take so as to optimize future objectives.
  • Supervised machine learning techniques are useful for solving sensing problems.
  • Machine learning algorithmic frameworks may also be used for the planning part, especially reinforcement learning (RL) frameworks, such as those described above.
  • RL may be performed in a sequence of consecutive rounds.
  • the planner a.k.a. the agent or driving policy module 803
  • the planner may observe a state, s t ⁇ S, which represents the agent as well as the environment. It then should decide on an action a t ⁇ A.
  • the agent receives an immediate reward, r t ⁇ R, and is moved to a new state, s t+1 .
  • the host vehicle may include an adaptive cruise control (ACC) system, in which the vehicle should autonomously implement acceleration/braking so as to keep an adequate distance to a preceding vehicle while maintaining smooth driving.
  • ACC adaptive cruise control
  • the action a t ⁇ will be the acceleration command (where the host vehicle slows down if a t ⁇ 0).
  • the reward can be a function that depends on
  • the goal of the planner is to maximize the cumulative reward (maybe up to a time horizon or a discounted sum of future rewards). To do so, the planner may rely on a policy, ⁇ :S ⁇ A, which maps a state into an action.
  • RL Supervised Learning
  • the actions (or predictions) taken by the learner may have no effect on the environment.
  • s t+1 and a t are independent. This can have two important implications.
  • a sample s 1 , y 1 ), . . . , (s m , y m ) can be collected in advance, and only then can the search begin for a policy (or predictor) that will have good accuracy relative to the sample.
  • the state s t+1 usually depends on the action taken (and also on the previous state), which in turn depends on the policy used to generate the action. This ties the data generation process to the policy learning process.
  • a “one-shot” value of the reward may be all that can be observed for a specific choice of action taken. This may be referred to as a “bandit” feedback.
  • RL algorithms rely, at least in part, on the mathematically elegant model of a Markov Decision Process (MDP).
  • MDP Markov Decision Process
  • the Markovian assumption is that the distribution of s t+1 is fully determined given s t and a t .
  • the stationary distribution of a policy can be expressed as a solution to a linear programming problem. This yields two families of algorithms: 1) optimization with respect to the primal problem, which may be referred to as policy search, and 2) optimization with respect to a dual problem, whose variables are called the value function, V ⁇ .
  • the value function determines the expected cumulative reward if the MDP begins from the initial state, s, and from there actions are chosen according to ⁇ .
  • a related quantity is the state-action value function, Q ⁇ (s, a), which determines the cumulative reward assuming a start from state, s, an immediately chosen action a, and from there on actions chosen according to ⁇ .
  • the Q function may give rise to a characterization of the optimal policy (using the Bellman's equation). In particular, the Q function may show that the optimal policy is a deterministic function from S to A (in fact, it may be characterized as a “greedy” policy with respect to the optimal Q function).
  • the MDP model allows coupling of the future into the present using the Q function. For example, given that a host vehicle is now in state, s, the value of Q ⁇ (s, a) may indicate the effect of performing action a on the future. Therefore, the Q function may provide a local measure of the quality of an action a, thus making the RL problem more similar to a SL scenario.
  • RL algorithms approximate the V function or the Q function in one way or another.
  • Value iteration algorithms e.g., the Q learning algorithm, may rely on the fact that the V and Q functions of the optimal policy may be fixed points of some operators derived from Bellman's equation.
  • Actor-critic policy iteration algorithms aim to learn a policy in an iterative way, where at iteration t, the “critic” estimates Q ⁇ t and based on this estimate, the “actor” improves the policy.
  • an approximate notion of a Markovian behaving state may be all that can be found in some cases.
  • the transition of states may depend not only on the agent's action, but also on actions of other players in the environment.
  • the dynamic of the autonomous vehicle may be Markovian
  • the next state may depend on the behavior of the driver of the other car, which is not necessarily Markovian.
  • One possible solution to this problem is to use partially observed MDPs, in which it is assumed that there is a Markovian state, but an observation that is distributed according to the hidden state is what can be seen.
  • MDPs game theoretical generalizations of MDPs (e.g., the Stochastic Games framework). Indeed, algorithms for MDPs may be generalized to multi-agents games (e.g., minimax-Q learning or Nash-Q learning). Other approaches may include explicit modeling of the other players and vanishing regret learning algorithms. Learning in a multi-agent setting may be more complex than in a single agent setting.
  • a second limitation of the Q function representation may arise by departing from a tabular setting.
  • the tabular setting is when the number of states and actions is small, and therefore, Q can be expressed as a table with
  • the Q function may be approximated by some function from a parametric hypothesis class (e.g., neural networks of a certain architecture). For example, a deep-Q-network (DQN) learning algorithm may be used.
  • a parametric hypothesis class e.g., neural networks of a certain architecture.
  • DQN deep-Q-network
  • the state space can be continuous, but the action space may remain a small discrete set.
  • approaches for dealing with continuous action spaces may rely on approximating the Q function.
  • the Q function may be complicated and sensitive to noise, and, therefore, may be challenging to learn.
  • RNN recurrent neural network
  • the first step of the approach may be to either define the reward as a function, ⁇ circumflex over (r) ⁇ (s, a), which is differentiable with respect to s and a, or to use a regression learning algorithm in order to learn a differentiable function, ⁇ circumflex over (r) ⁇ , that minimizes at least some regression loss over a sample with instance vector being (s t , a t ) ⁇ d ⁇ k and target scalar being r t .
  • elements of exploration may be used.
  • ⁇ circumflex over (N) ⁇ (s, a) can be learned such that ⁇ circumflex over (N) ⁇ (s t , a t ) ⁇ s t+1 Learning such a function may be characterized as an SL problem.
  • ⁇ circumflex over (N) ⁇ may be viewed as a predictor for the near future.
  • a policy that maps from S to A may be described using a parametric function ⁇ ⁇ :S ⁇ A.
  • RNN recurrent neural network
  • s t+1 ⁇ circumflex over (N) ⁇ (s t , a t )+v t .
  • v t ⁇ d may be defined by the environment and may express unpredictable aspects of the near future. The fact that s t+1 depends on s t and a t in a differentiable manner may enable a connection between future reward values and past actions.
  • a parameter vector of the policy function, ⁇ ⁇ may be learned by back-propagation over the resulting RNN. Note that explicit probabilistic assumptions need not be imposed on v t .
  • ⁇ circumflex over (N) ⁇ (s t , a t ) may describe the predictable part of the near future, while v t may express the unpredictable aspects, which may arise due to the behavior of other players in the environment.
  • the learning system should learn a policy that will be robust to the behavior of other players. If ⁇ v t ⁇ is large, the connection between past actions and future reward values may be too noisy for learning a meaningful policy.
  • Explicitly expressing the dynamic of the system in a transparent way may enable incorporation of prior knowledge more easily. For example, prior knowledge may simplify the problem of defining ⁇ circumflex over (N) ⁇ .
  • the learning system may benefit from robustness relative to an adversarial environment, such as the environment of a host vehicle, which may include multiple other drivers that may act in unexpected way.
  • an adversarial environment such as the environment of a host vehicle
  • environments may be considered in which v t is chosen in an adversarial manner.
  • restrictions may be placed on ⁇ t , otherwise the adversary can make the planning problem difficult or even impossible.
  • One natural restriction may be to require that ⁇ t ⁇ is bounded by a constant.
  • the state is s t ⁇
  • the action is a t ⁇
  • the immediate loss function is 0.1
  • + max ⁇ x, 0 ⁇ is the ReLU (rectified linear unit) function.
  • the derivative of the loss with respect to a t is 0.1 sign (a t ), and the derivative with respect to s t is 1[
  • the adversarial choice of v t may help the navigational system obtain a non-zero back-propagation message in cases for which the choice of a t is sub-optimal.
  • Such a relationship may aid the navigational system in selecting present actions based on an expectation that such a present action (even if that action would result in a suboptimal reward or even a loss) will provide opportunities in the future for more optimal actions that result in higher rewards.
  • ACC adaptive cruise control
  • the host vehicle may attempt to maintain an adequate distance to a target vehicle ahead (e.g., 1.5 seconds to the target car).
  • Another goal may be to drive as smooth as possible while maintaining the desired gap.
  • a model representing this situation may be defined as follows.
  • the state space is , and the action space is .
  • the first coordinate of the state is the speed of the target car
  • the second coordinate is the speed of the host vehicle
  • the last coordinate is the distance between the host vehicle and target vehicle (e.g., location of the host vehicle minus the location of the target along the road curve).
  • the action to be taken by the host vehicle is the acceleration, and may be denoted by a t .
  • the quantity may denote the difference in time between consecutive rounds. While may be set to any suitable quantity, in one example, may be 0.1 seconds.
  • v t target [ v t ⁇ 1 target + ⁇ a t ⁇ 1 target ] +
  • v t host [ v t ⁇ 1 host + ⁇ a t ⁇ 1 ] +
  • x t [ x t ⁇ 1 + ⁇ ( v t ⁇ 1 target ⁇ v t ⁇ 1 host )] +
  • the first vector is the predictable part, and the second vector is the unpredictable part.
  • the reward on round t is defined as follows:
  • the first term may result in a penalty for non-zero accelerations, thus encouraging smooth driving.
  • the second term depends on the ratio between the distance to the target car, x t , and the desired distance, x* t , which is defined as the maximum between a distance of 1 meter and break distance of 1.5 seconds. In some cases, this ratio may be exactly 1, but as long as this ratio is within [0.7, 1.3], the policy may forego any penalties, which may allow the host vehicle some slack in navigation—a characteristic that may be important in achieving a smooth drive.
  • the navigation system of the host vehicle may select an action in response to an observed state.
  • the selected action may be based on analysis not only of rewards associated with the responsive actions available relative to a sensed navigational state, but may also be based on consideration and analysis of future states, potential actions in response to the futures states, and rewards associated with the potential actions.
  • FIG. 16 illustrates an algorithmic approach to navigation based on detection and long range planning.
  • the at least one processing device 110 of the navigation system for the host vehicle may receive a plurality of images. These images may capture scenes representative of an environment of the host vehicle and may be supplied by any of the image capture devices (e.g., cameras, sensors, etc.) described above. Analysis of one or more of these images at step 1603 may enable the at least one processing device 110 to identify a present navigational state associated with the host vehicle (as described above).
  • various potential navigational actions responsive to the sensed navigational state may be determined. These potential navigational actions (e.g., a first navigational action through an N th available navigational action) may be determined based on the sensed state and the long range goals of the navigational system (e.g., to complete a merge, follow a lead vehicle smoothly, pass a target vehicle, avoid an object in the roadway, slow for a detected stop sign, avoid a target vehicle cutting in, or any other navigational action that may advance the navigational goals of the system).
  • these potential navigational actions e.g., a first navigational action through an N th available navigational action
  • the long range goals of the navigational system e.g., to complete a merge, follow a lead vehicle smoothly, pass a target vehicle, avoid an object in the roadway, slow for a detected stop sign, avoid a target vehicle cutting in, or any other navigational action that may advance the navigational goals of the system.
  • the system may determine an expected reward.
  • the expected reward may be determined according to any of the techniques described above and may include analysis of a particular potential action relative to one or more reward functions.
  • Expected rewards 1606 , 1608 , and 1610 may be determined for each of the potential navigational actions (e.g., the first, second, and N th ) determined in steps 1605 , 1607 , and 1609 , respectively.
  • the navigational system of the host vehicle may select from among the available potential actions based on values associated with expected rewards 1606 , 1608 , and 1610 (or any other type of indicator of an expected reward). For example, in some situations, the action that yields the highest expected reward may be selected.
  • the system may not choose the potential action that yields the highest expected reward. Rather, the system may look to the future to analyze whether there may be opportunities for realizing higher rewards later if lower reward actions are selected in response to a current navigational state. For example, for any or all of the potential actions determined at steps 1605 , 1607 , and 1609 , a future state may be determined. Each future state, determined at steps 1613 , 1615 , and 1617 , may represent a future navigational state expected to result based on the current navigational state as modified by a respective potential action (e.g., the potential actions determined at steps 1605 , 1607 , and 1609 ).
  • one or more future actions may be determined and evaluated.
  • values or any other type of indicator of expected rewards associated with one or more of the future actions may be developed (e.g., based on one or more reward functions).
  • the expected rewards associated with the one or more future actions may be evaluated by comparing values of reward functions associated with each future action or by comparing any other indicators associated with the expected rewards.
  • the navigational system for the host vehicle may select a navigational action for the host vehicle based on a comparison of expected rewards, not just based on the potential actions identified relative to a current navigational state (e.g., at steps 1605 , 1607 , and 1609 ), but also based on expected rewards determined as a result of potential future actions available in response to predicted future states (e.g., determined at steps 1613 , 1615 , and 1617 ).
  • the selection at step 1625 may be based on the options and rewards analysis performed at steps 1619 , 1621 , and 1623 .
  • the selection of a navigational action at step 1625 may be based on a comparison of expected rewards associated with future action options only.
  • the navigational system may select an action to the current state based solely on a comparison of expected rewards resulting from actions to potential future navigational states.
  • the system may select the potential action identified at step 1605 , 1607 , or 1609 that is associated with a highest future reward value as determined through analysis at steps 1619 , 1621 , and 1623 .
  • the selection of a navigational action at step 1625 may also be based on comparison of current action options only (as noted above). In this situation, the navigational system may select the potential action identified at step 1605 , 1607 , or 1609 that is associated with a highest expected reward, 1606 , 1608 , or 1610 . Such a selection may be performed with little or no consideration of future navigational states or future expected rewards to navigational actions available in response to expected future navigational states.
  • the selection of a navigational action at step 1625 may be based on a comparison of expected rewards associated with both future action options and with current action options. This, in fact, may be one of the principles of navigation based on long range planning. For example, expected rewards to future actions may be analyzed to determine if any may warrant a selection of a lower reward action in response to the current navigational state in order to achieve a potential higher reward in response to a subsequent navigational action expected to be available in response to future navigational states. As an example, a value or other indicator of an expected reward 1606 may indicate a highest expected reward from among rewards 1606 , 1608 , and 1610 .
  • expected reward 1608 may indicate a lowest expected reward from among rewards 1606 , 1608 , and 1610 .
  • analysis of future states, potential future actions, and future rewards may be used in making a navigational action selection at step 1625 .
  • it may be determined that a reward identified at step 1621 (in response to at least one future action to a future state determined at step 1615 based on the second potential action determined at step 1607 ) may be higher than expected reward 1606 .
  • the second potential action determined at step 1607 may be selected rather than the first potential action determined at step 1605 despite expected reward 1606 being higher than expected reward 1608 .
  • the potential navigational action determined at step 1605 may include a merge in front of a detected target vehicle
  • the potential navigational action determined at step 1607 may include a merge behind the target vehicle. While the expected reward 1606 of merging in front of the target vehicle may be higher than the expected reward 1608 associated with merging behind the target vehicle, it may be determined that merging behind the target vehicle may result in a future state for which there may be action options yielding even higher potential rewards than expected reward 1606 , 1608 , or other rewards based on available actions in response to a current, sensed navigational state.
  • Selection from among potential actions at step 1625 may be based on any suitable comparison of expected rewards (or any other metric or indicator of benefits associated with one potential action over another).
  • a second potential action may be selected over a first potential action if the second potential action is projected to provide at least one future action associated with an expected reward higher than a reward associated with the first potential action.
  • more complex comparisons may be employed. For example, rewards associated with action options in response to projected future states may be compared to more than one expected reward associated with a determined potential action.
  • actions and expected rewards based on projected future states may affect selection of a potential action to a current state if at least one of the future actions is expected to yield a reward higher than any of the rewards expected as a result of the potential actions to a current state (e.g., expected rewards 1606 , 1608 , 1610 , etc.).
  • the future action option that yields the highest expected reward e.g., from among the expected rewards associated with potential actions to a sensed current state as well as from among expected rewards associated with potential future action options relative to potential future navigational states
  • the potential action that would lead to the future state associated with the identified future action yielding the highest expected reward may be selected at step 1625 .
  • FIG. 16 represents two layers in the long range planning analysis (e.g., a first layer considering the rewards resulting from potential actions to a current state, and a second layer considering the rewards resulting from future action options in response to projected future states), analysis based on more layers may be possible. For example, rather than basing the long range planning analysis upon one or two layers, three, four or more layers of analysis could be used in selecting from among available potential actions in response to a current navigational state.
  • Target vehicles may be monitored through analysis of an acquired image stream to determine indicators of driving aggression. Aggression is described herein as a qualitative or quantitative parameter, but other characteristics may be used: perceived level of attention (potential impairment of driver, distracted—cell phone, asleep, etc.). In some cases, a target vehicle may be deemed to have a defensive posture, and in some cases, the target vehicle may be determined to have a more aggressive posture. Navigational actions may be selected or developed based on indicators of aggression. For example, in some cases, the relative velocity, relative acceleration, increases in relative acceleration, following distance, etc., relative to a host vehicle may be tracked to determine if the target vehicle is aggressive or defensive.
  • a target vehicle may be modeled by an “aggressive” driving policy, such that the aggressive target vehicle accelerates when the host vehicle attempts to merge in front of the target vehicle.
  • the target vehicle may be modeled by a “defensive” driving policy, such that the target vehicle decelerates and lets the host vehicle merge in.
  • the navigational state may be represented as the velocity and location of the host vehicle (the agent), and the locations, velocities, and accelerations of the target vehicles. Maintaining target acceleration observations may be important in order to differentiate between aggressive and defensive drivers based on the current state. All target vehicles may move on a one-dimensional curve that outlines the roundabout path. The host vehicle may move on its own one-dimensional curve, which intersects the target vehicles' curve at the merging point, and this point is the origin of both curves. To model reasonable driving, the absolute value of all vehicles' accelerations may be upper bounded by a constant. Velocities may also be passed through a ReLU because driving backward is not allowed. Note that by not allowing driving backwards, long-term planning may become a necessity, as the agent cannot regret on its past actions.
  • next state may be decomposed into a sum of a predictable part, ⁇ circumflex over (N) ⁇ (s t , a t ), and a non-predictable part, v t .
  • the expression, ⁇ circumflex over (N) ⁇ (s t , a t ), may represent the dynamics of vehicle locations and velocities (which may be well-defined in a differentiable manner), while v t may represent the target vehicles' acceleration.
  • ⁇ circumflex over (N) ⁇ (s t , a t ) can be expressed as a combination of ReLU functions over an affine transformation, hence it is differentiable with respect to s t and a t .
  • the vector v t may be defined by a simulator in a non-differentiable manner, and may implement aggressive behavior for some targets and defensive behavior for other targets. Two frames from such a simulator are shown in FIGS. 17A and 17B . In this example experiment, a host vehicle 1701 learned to slowdown as it approached the entrance of the roundabout.
  • target vehicle 1701 recognized that the target vehicle 1710 traveling behind vehicle 1703 exhibited defensive tendencies (again, based on observed position, velocity, and/or relative acceleration of vehicle 1710 ) and, therefore, completed a successful merge in front of target vehicle 1710 and behind target vehicle 1703 .
  • FIG. 18 provides a flowchart representing an example algorithm for navigating a host vehicle based on predicted aggression of other vehicles.
  • a level of aggression associated with at least one target vehicle may be inferred based on observed behavior of the target vehicle relative to an object in the environment of the target vehicle.
  • at least one processing device e.g., processing device 110
  • the host vehicle navigation system may receive, from a camera associated with the host vehicle, a plurality of images representative of an environment of the host vehicle.
  • analysis of one or more of the received images may enable the at least one processor to identify a target vehicle (e.g., vehicle 1703 ) in the environment of the host vehicle 1701 .
  • analysis of one or more of the received images may enable the at least one processing device to identify in the environment of the host vehicle at least one obstacle to the target vehicle.
  • the object may include debris in a roadway, a stoplight/traffic light, a pedestrian, another vehicle (e.g., a vehicle traveling ahead of the target vehicle, a parked vehicle, etc.), a box in the roadway, a road barrier, a curb, or any other type of object that may be encountered in an environment of the host vehicle.
  • analysis of one or more of the received images may enable the at least one processing device to determine at least one navigational characteristic of the target vehicle relative to the at least one identified obstacle to the target vehicle.
  • navigational characteristics may be used to infer a level of aggression of a detected target vehicle in order to develop an appropriate navigational response to the target vehicle.
  • navigational characteristics may include a relative acceleration between the target vehicle and the at least one identified obstacle, a distance of the target vehicle from the obstacle (e.g., a following distance of the target vehicle behind another vehicle), and/or a relative velocity between the target vehicle and the obstacle, etc.
  • the navigational characteristics of the target vehicles may be determined based on outputs from sensors associated with the host vehicle (e.g., radar, speed sensors, GPS, etc.). In some cases, however, the navigational characteristics of the target vehicles may be determined partially or fully based on analysis of images of an environment of the host vehicle. For example, image analysis techniques described above and in, for example, U.S. Pat. No. 9,168,868, which is incorporated herein by reference, may be used to recognize target vehicles within an environment of the host vehicle.
  • monitoring a location of a target vehicle in the captured images over time and/or monitoring locations in the captured images of one or more features associated with the target vehicle may enable a determination of relative distances, velocities, and/or accelerations between the target vehicles and the host vehicle or between the target vehicles and one or more other objects in an environment of the host vehicle.
  • An aggression level of an identified target vehicle may be inferred from any suitable observed navigational characteristic of the target vehicle or any combination of observed navigational characteristics. For example, a determination of aggressiveness may be made based on any observed characteristic and one or more predetermined threshold levels or any other suitable qualitative or quantitative analysis.
  • a target vehicle may be deemed as aggressive if the target vehicle is observed to be following the host vehicle or another vehicle at a distance less than a predetermined aggressive distance threshold.
  • a target vehicle observed to be following the host vehicle or another vehicle at a distance greater than a predetermined defensive distance threshold may be deemed defensive.
  • the predetermined aggressive distance threshold need not be the same as the predetermined defensive distance threshold.
  • either or both of the predetermined aggressive distance threshold and the predetermined defensive distance threshold may include a range of values, rather than a bright line value.
  • neither of the predetermined aggressive distance threshold nor the predetermined defensive distance threshold must be fixed. Rather these values, or ranges of values, may shift over time, and different thresholds/ranges of threshold values may be applied based on observed characteristics of a target vehicle. For example, the thresholds applied may depend on one or more other characteristics of the target vehicle. Higher observed relative velocities and/or accelerations may warrant application of larger threshold values/ranges. Conversely, lower relative velocities and/or accelerations, including zero relative velocities and/or accelerations, may warrant application of smaller distance threshold values/ranges in making the aggressive/defensive inference.
  • the aggressive/defensive inference may also be based on relative velocity and/or relative acceleration thresholds.
  • a target vehicle may be deemed aggressive if its observed relative velocity and/or its relative acceleration with respect to another vehicle exceeds a predetermined level or range.
  • a target vehicle may be deemed defensive if its observed relative velocity and/or its relative acceleration with respect to another vehicle falls below a predetermined level or range.
  • a target vehicle may be deemed aggressive based solely on an observation that it is following another vehicle at a distance below a certain threshold or range. In other cases, however, the target vehicle may be deemed aggressive if it both follows another vehicle at less than a predetermined amount (which may be the same as or different than the threshold applied where the determination is based on distance alone) and has a relative velocity and/or a relative acceleration of greater than a predetermined amount or range. Similarly, a target vehicle may be deemed defensive based solely on an observation that it is following another vehicle at a distance greater than a certain threshold or range.
  • the target vehicle may be deemed defensive if it both follows another vehicle at greater than a predetermined amount (which may be the same as or different than the threshold applied where the determination is based on distance alone) and has a relative velocity and/or a relative acceleration of less than a predetermined amount or range.
  • a predetermined amount which may be the same as or different than the threshold applied where the determination is based on distance alone
  • System 100 may make an aggressive/defensive if, for example, a vehicle exceeds 0.5 G acceleration or deceleration (e.g., jerk 5 m/s3), a vehicle has a lateral acceleration of 0.5 G in a lane change or on a curve, a vehicle causes another vehicle to do any of the above, a vehicle changes lanes and causes another vehicle to give way by more than 0.3 G deceleration or jerk of 3 m/s3, and/or a vehicle changes two lanes without stopping.
  • 0.5 G acceleration or deceleration e.g., jerk 5 m/s3
  • a vehicle has a lateral acceleration of 0.5 G in a lane change or on a curve
  • a vehicle causes another vehicle to do any of the above
  • a vehicle changes lanes and causes another vehicle to give way by more than 0.3 G deceleration or jerk of 3 m/s3, and/or a vehicle changes two lanes without stopping.
  • the aggressive/defensive inference may be made by observing the navigational characteristics of a target vehicle relative to any other type of obstacle (e.g., a pedestrian, road barrier, traffic light, debris, etc.).
  • a target vehicle relative to any other type of obstacle (e.g., a pedestrian, road barrier, traffic light, debris, etc.).
  • the navigation system may receive a stream of images from a camera associated with the host vehicle. Based on analysis of one or more of the received images, any of target vehicles 1703 , 1705 , 1706 , 1708 , and 1710 may be identified. Further, the navigation system may analyze the navigational characteristics of one or more of the identified target vehicles. The navigation system may recognize that the gap between target vehicles 1703 and 1705 represents the first opportunity for a potential merge into the roundabout. The navigation system may analyze target vehicle 1703 to determine indicators of aggression associated with target vehicle 1703 .
  • target vehicle 1703 is deemed aggressive, then the host vehicle navigation system may choose to give way to vehicle 1703 rather than merging in front of vehicle 1703 . On the other hand, if target vehicle 1703 is deemed defensive, then the host vehicle navigation system may attempt to complete a merge action ahead of vehicle 1703 .
  • the at least one processing device of the navigation system may analyze the captured images to determine navigational characteristics associated with target vehicle 1703 . For example, based on the images, it may be determined that vehicle 1703 is following vehicle 1705 at a distance that provides a sufficient gap for the host vehicle 1701 to safely enter. Indeed, it may be determined that vehicle 1703 is following vehicle 1705 by a distance that exceeds an aggressive distance threshold, and therefore, based on this information, the host vehicle navigation system may be inclined to identify target vehicle 1703 as defensive. In some situations, however, more than one navigational characteristic of a target vehicle may be analyzed in making the aggressive/defensive determination, as discussed above.
  • the host vehicle navigation system may determine that, while target vehicle 1703 is following at a non-aggressive distance behind target vehicle 1705 , vehicle 1703 has a relative velocity and/or a relative acceleration with respect to vehicle 1705 that exceeds one or more thresholds associated with aggressive behavior. Indeed, host vehicle 1701 may determine that target vehicle 1703 is accelerating relative to vehicle 1705 and closing the gap that exists between vehicles 1703 and 1705 . Based on further analysis of the relative velocity, acceleration, and distance (and even a rate that the gap between vehicles 1703 and 1705 is closing), host vehicle 1701 may determine that target vehicle 1703 is behaving aggressively.
  • host vehicle 1701 may expect that a merge in front of target vehicle 1703 would result in an aggressively navigating vehicle directly behind the host vehicle. Further, target vehicle 1703 may be expected, based on the observed behavior through image analysis or other sensor output, that target vehicle 1703 would continue accelerating toward host vehicle 1701 or continuing toward host vehicle 1701 at a non-zero relative velocity if host vehicle 1701 was to merge in front of vehicle 1703 . Such a situation may be undesirable from a safety perspective and may also result in discomfort to passengers of the host vehicle. For such reasons, host vehicle 1701 may choose to give way to vehicle 1703 , as shown in FIG. 17B , and merge into the roundabout behind vehicle 1703 and in front of vehicle 1710 , deemed defensive based on analysis of one or more of its navigational characteristics.
  • the at least one processing device of the navigation system of the host vehicle may determine, based on the identified at least one navigational characteristic of the target vehicle relative to the identified obstacle, a navigational action for the host vehicle (e.g., merge in front of vehicle 1710 and behind vehicle 1703 ).
  • the at least one processing device may cause at least one adjustment of a navigational actuator of the host vehicle in response to the determined navigational action. For example, a brake may be applied in order to give way to vehicle 1703 in FIG. 17A , and an accelerator may be applied along with steering of the wheels of the host vehicle in order to cause the host vehicle to enter the roundabout behind vehicle 1703 , as shown if FIG. 17B .
  • navigation of the host vehicle may be based on the navigational characteristics of a target vehicle relative to another vehicle or object. Additionally, navigation of the host vehicle may be based on navigational characteristics of the target vehicle alone without a particular reference to another vehicle or object.
  • analysis of a plurality of images captured from an environment of a host vehicle may enable determination of at least one navigational characteristic of an identified target vehicle indicative of a level of aggression associated with the target vehicle.
  • the navigational characteristic may include a velocity, acceleration, etc. that need not be referenced with respect to another object or target vehicle in order to make an aggressive/defensive determination.
  • observed accelerations and/or velocities associated with a target vehicle that exceed a predetermined threshold or fall within or exceed a range of values may indicate aggressive behavior.
  • observed accelerations and/or velocities associated with a target vehicle that fall below a predetermined threshold or fall within or exceed a range of values may indicate defensive behavior.
  • an observed navigational characteristic of the target vehicle indicative of a level of aggression associated with the target vehicle may include an increase in relative acceleration between the target vehicle and the host vehicle, a following distance of the target vehicle behind the host vehicle, a relative velocity between the target vehicle and the host vehicle, etc.
  • a host vehicle navigation system may select between navigational rules based on applicability of rules to the vehicle. For example, the host vehicle navigation system may monitor a location of the host vehicle (e.g., based on GPS, a location broadcasting beacon, a recognized traffic sign, etc., or any combination of the foregoing) and select between navigational rules (e.g., left turn on green with yield or left turn on green arrow only) based on location.
  • navigational rules e.g., left turn on green with yield or left turn on green arrow only
  • modules 1902 and 1904 may be stored in memory unit 140 and/or memory unit 150 of system 100 , or modules 1902 and 1904 (or portions thereof) may be stored remotely from system 100 (e.g., stored in a server accessible to system 100 via, for example, wireless transceiver 172 ).
  • Jurisdiction determination module 1902 which may store instructions executable by processing unit 110 , may handle various tasks relating to identifying one or more jurisdictions with which the target vehicle is associated. Such tasks may rely upon input from various sensors and sensing systems associated with the host vehicle, such as images or image streams from one or more onboard cameras, GPS position information, user feedback, or user inputs to one or more user interface devices, radar, lidar, etc.
  • jurisdiction determination module 1902 may identify a jurisdiction in which the host vehicle is traveling based on at least one indicator of a location of the host vehicle.
  • the at least one indicator may include one or more of a GPS signal or other digital or analog wireless signal including information relating to the location of the host vehicle.
  • the at least one indicator of the location of the host vehicle may be based at least in part on an analysis of the plurality of images.
  • the images may include a road sign with text, which may be analyzed via optical character recognition to determine the location of the vehicle.
  • Determination of jurisdiction may be based on physical presence within a particular area, as determined by any one or more of the sensors and sensing systems described above. Such areas may include, for example, the geographical limits of a state, county, city, etc. In some embodiments, a plurality of jurisdictions may be applicable at once, for example, if the host vehicle is simultaneously within the limits of a city and a county. In some embodiments, the jurisdiction may include a particular type of area (e.g., urban, suburban, recreational, shopping, entertainment, dining, etc.).
  • jurisdiction may be determined based on an attribute associated with the host vehicle's location or environment.
  • jurisdiction determination module 1902 may determine that the host vehicle is traveling along a particular type of road, such as a limited access highway, which represents a particular jurisdiction subject to particular rules and/or traffic laws.
  • Jurisdiction determination module 1902 may determine other attributes, such as jurisdiction based on time and/or date (e.g., weekend, holiday, rush hour, etc.), status of location as private or public property, vehicle status (e.g., number of vehicle occupants), etc.
  • time and/or date e.g., weekend, holiday, rush hour, etc.
  • vehicle status e.g., number of vehicle occupants
  • Such attributes may be determined by sensors and sensing systems associated with the host vehicle, as described above, via map database 160 , or a combination of factors.
  • the output of jurisdiction determination module 1902 may be passed to navigational rule determination module 1904 .
  • Navigational rule determination module 1904 may store instructions executable by processing unit 110 and may implement a desired driving policy in order to decide on one or more navigational actions for the host vehicle to take in response to the determined jurisdiction.
  • navigational rule determination module 1904 may cause a navigational change for the host vehicle based on the identified navigational state of the host vehicle and based on the determined at least one navigational rule specific to the identified jurisdiction.
  • navigational rule determination module 1904 may determine that a jurisdiction determined by jurisdiction determination module 1902 prohibits a left turn at an intersection with a traffic light in an absence of a green arrow shown by the traffic light. Alternatively, navigational rule determination module 1904 may determine that the jurisdiction allows a left turn at the intersection, with a yield, in the presence of a green light shown by the traffic light. Other rules determined by navigational rule determination module 1904 may include rules prohibiting or allowing turns when a red light is shown, prohibiting turns when pedestrians are present, etc. In some embodiments, multiple rules may apply to a particular scenario. In such cases, navigational rule determination module 1904 may determine whether the rules agree or contradict.
  • navigational rule determination module 1904 may cause the host vehicle to proceed in accordance with the rules. If the multiple rules contradict, navigational rule determination module 1904 may rank the rules, applying the rule with the highest ranking and while maintaining safety standards. For example, rules based on city jurisdiction may supersede rules based on county jurisdiction.
  • Navigational rule determination module 1904 may determine navigational rules applicable to a variety of scenarios. In some embodiments, navigational rule determination module may determine rules related to particular lanes of a multi-lane road relevant to a particular jurisdiction. For example, a determined jurisdiction may restrict access to a particular lane or lanes to vehicles based on weight or number of axles, or may restrict a high occupancy vehicle lane based on a number of passengers present in a vehicle. Navigational rule determination module 1904 may determine that a jurisdiction prohibits navigation in lane (e.g., a left lane) of a multi-lane road, except to pass another vehicle, or prohibits access to a particular lane or shoulder outside of designated dates and/or times.
  • lane e.g., a left lane
  • Navigational rule determination module 1904 may further determine navigational rules based on characteristics known to be present in the determined jurisdiction. Such characteristics may include speed limits, road characteristics (e.g., lane width), traffic light timing, toll schedules, etc. Known characteristics may also include “unwritten rules” of a particular location. Adherence to such unwritten rules may avoid unwanted behavior by the host vehicle. For example, rule determination module 1904 may determine a rule to provide additional distance between a host vehicle and a target vehicle in an area known to be particularly hilly, prone to traffic, or prone to collisions. Such a rule may prevent unnecessary braking, improve fuel economy, or prevent collisions. Further, such unwritten rules may be developed via reinforcement learning, as described above with respect to driving policy module 803 .
  • driving policies may be developed and employed based on the jurisdiction in which the policy was trained.
  • control module 805 may develop control instructions for one or more actuators or controlled devices associated with the host vehicle based on output from navigational rule determination module 1904 .
  • FIG. 20 shows an example of a scene that may be captured and analyzed during navigation of a host vehicle, as described in relation to FIG. 12 .
  • the scene shown in FIG. 20 includes a number of features that may be affected by jurisdictional rules.
  • traffic light 2002 includes a plurality of columns of lights, which may include a green arrow and yellow arrow in the leftmost column.
  • a proper interpretation of various lights of traffic light 2002 may be affected by the jurisdiction(s) in which traffic light 2002 is located.
  • Sign 2004 indicates that vehicles turning left must yield to oncoming traffic.
  • sign 2006 indicates that left turns are prohibited during the hours of 7:00 am through 7:00 pm, but that holidays are excluded.
  • Navigational rule determination module 1904 may determine a rule or rules based on information defining the requirements indicated by signs 2004 and/or 2006 .
  • navigational rule determination module 1904 may determine a time zone associated with the jurisdiction, and determine whether the host vehicle is operating within the hours specified by sign 2006 . Navigational rule determination module 1904 may also determine holidays observed in the jurisdiction, and determine whether the host vehicle is operating during a holiday observed by the jurisdiction.
  • Navigational rule determination module 1904 may determine whether Hartom Street extends through multiple jurisdictions, and whether the street comprises different attributes or is subject to different laws as a result. For example, navigational rule determination module 1904 may determine that Hartom Street is a one way street within the limits of a particular city, county, or other jurisdiction.
  • Navigational rule determination module 1904 may determine whether rules related to the presence of pedestrians may be affected by relevant jurisdictions. For example, navigational rule determination module 1904 may determine that a particular jurisdiction defines the presence of a pedestrian based on a particular distance from the road, distance within the road from a boundary of the road, etc.
  • FIG. 21 is an example of a flowchart 2100 representing an example process for navigational rule selection for a host vehicle navigation system based on location.
  • navigational rules may be established or modified based on a jurisdiction relevant to a location of the host vehicle.
  • At step 2102 at least one processing device (e.g., processing device 110 ) of the host vehicle navigation system may receive, from a camera associated with the host vehicle, a plurality of images representative of an environment of the host vehicle, for example as described above in relation to FIGS. 2 and 5 .
  • analysis of one or more of the received images may enable the at least one processor to identify a navigational state of the host vehicle, for example as described above in relation to sensing module 801 .
  • the at least one processing device may identify a jurisdiction associated with the host vehicle. Identification may be performed by jurisdiction determination module 1902 , as described above. For example, jurisdiction determination module 1902 may identify relevant jurisdictions based on a combination of one or more of GPS, image analysis of the images received at step 2102 , and user input, that the host vehicle is associated with a plurality of jurisdictions including a city and state. More specifically, jurisdiction determination module 1902 may determine association with a particular city and state based on a combination of requested route information input by a user, location information received from a GPS receiver, and analysis of images comprising a sign, such a sign 2008 , shown in FIG. 20 .
  • a universe of jurisdiction information may be narrowed to the jurisdictions present in a route requested for navigation.
  • a specific jurisdiction may be identified by comparing locations found via a GPS signal with a database of jurisdiction locations. The location may be verified via an analysis of the plurality of images by confirming that an intersection identified via optical character recognition of a road name reflected on a street sign is in fact located within the identified jurisdiction.
  • the at least one processing device may determine at least one navigational rule specific to the jurisdiction identified in step 2106 .
  • the navigational rule may be determined via any rule determination module 1904 , as described above. As outlined above, to the extent multiple rules apply based on jurisdiction, rule determination module 1904 may determine whether the rules are in agreement, and if not determine which rule controls at the particular location.
  • the at least one processing device may cause a navigational change for the host vehicle based on the identified navigational state of the host vehicle and based on the determined at least one navigational rule specific to the identified jurisdiction.
  • the at least one processing device of the navigation system of the host vehicle may determine, based on the determined navigational rule a navigational action for the host vehicle (e.g., turn left, stop, yield to oncoming traffic, do not pass, do not change lanes, change lanes only to pass, etc.) necessitated by the navigational change.
  • the processing device may determine based on the navigational state that a left turn is desired.
  • the processing device may have identified a jurisdiction based on location of the vehicle determined via a GPS signal and an analysis of the images received by the processor to extract Hartom St. (e.g., via OCR techniques) from sign 2008 .
  • the processing device may have determined that the location is governed by a single jurisdiction which allows left turns on a green light with no arrow, but with a yield to oncoming traffic. Based on this determination, the processing device may initiate a turn, yielding to oncoming traffic.
  • the at least one processing device may cause at least one adjustment of a navigational actuator of the host vehicle in response to the determined navigational action.
  • a navigational actuator of the host vehicle For example, a brake may be applied in order to yield to oncoming traffic, and an accelerator may be applied along with steering of the wheels of the host vehicle in order to cause the host vehicle to turn left when oncoming traffic has passed.
  • a host vehicle navigation system may select between navigational rules based on a desire to pass a target vehicle.
  • a pass may be desired for any of a number of reasons which would make following the target vehicle undesirable, such as the target vehicle's size, type, effect on visibility, effect to comfort of passengers of the host vehicle, expected effect to safety of passengers of the host vehicle, etc.
  • the following describes systems and methods for applying such navigational rules to autonomous control of a vehicle.
  • a navigation system for a host vehicle may include at least one processing device (e.g., processing unit 110 ) programmed to receive, from at least one camera (e.g., at least one of image capture units 122 , 124 , and 126 ), a plurality of images representative of an environment of the host vehicle.
  • the at least one processing device may further programmed to analyze the plurality of images to identify at least one target vehicle in the environment of the host vehicle, and to analyze the plurality of images to identify at least one characteristic of the target vehicle.
  • the at least one characteristic of the host vehicle may related to any one or more aspects of the target vehicle (e.g., a size, shape, type of vehicle, etc.).
  • the at least one processing device may further programmed to cause at least one navigational change of the host vehicle to initiate a pass of the target vehicle.
  • modules 2202 and 2204 may be stored in memory unit 140 and/or memory unit 150 of system 100 , or modules 2202 and 2204 (or portions thereof) may be stored remotely from system 100 (e.g., stored in a server accessible to system 100 via, for example, wireless transceiver 172 ).
  • Target vehicle characteristic determination module 2202 which may store instructions executable by processing unit 110 , may handle various tasks relating to identifying one or more characteristics of a target vehicle sensed by sensing module 801 . Such tasks may rely upon input from sensors and sensing systems associated with the host vehicle, such as images or image streams from one or more onboard cameras, user feedback, or user inputs to one or more user interface devices, radar, lidar, etc.
  • target vehicle characteristic determination module may determine a size and/or shape of a target vehicle. Such a determination may be made in absolute terms, such as a measurement in linear units (e.g., feet, meters, etc.) or may be relative to characteristics relevant to a driving context, such as percent of lane width, percent of a maximum height, portion of field of view obscured by the target vehicle, etc.
  • Vehicle dimensions and/or shape(s) may be determined via analysis of the received images. For example, known distances in the images may be determined and/or identified, and the known distances compared to vehicle dimensions to determine the actual size of the vehicle. Relevance of shape may be determined by comparing shapes found in the received images to known shapes found in vehicles and other objects.
  • Target vehicle characteristic determination module 2202 may also determine a vehicle type.
  • a vehicle category e.g., sedan, truck, van, motorcycle, commercial, etc.
  • Target vehicle characteristic determination module 2202 may determine vehicle type by determining a shape of the target vehicle and comparing it to a database of vehicle shapes. Alternatively, target vehicle characteristic determination module may determine using particular features of the target vehicle, such as the size of its tires. A trained system may be used rained to identify shapes or other characteristics in one or more images, which gains confidence as additional determinations are completed. Furthermore, target vehicle characteristic determination module may identify text found on the vehicle via an optical character recognition of an image, such as text on tires, the vehicle, etc. Target vehicle characteristic determination module 2202 may also determine whether the target vehicle fits into a category such as construction vehicle, agricultural equipment, off-road vehicle, taxi, police, emergency vehicle, etc.
  • Target vehicle characteristic determination module 2202 may determine other characteristics of the target vehicle, in particular characteristics that may be relevant to a decision to pass the target vehicle. For example, target vehicle characteristic determination module may detect conditions that may suggest a safety hazard to a nearby host vehicle, such as unsecured material (e.g., flapping fabric, loose tie down, loose panels, open door, unlocked door, or other unsecured objects).
  • unsecured material e.g., flapping fabric, loose tie down, loose panels, open door, unlocked door, or other unsecured objects.
  • target vehicle characteristic determination module 2202 may determine other conditions or events associated with a target vehicle, such as release of matter from the target vehicle (e.g., liquids, solids such as gravel or ice, particulate matter such as smoke or soot, etc.). Similar to identification of vehicle characteristics described above, such a determination may be made via analysis of received images via comparison to shapes and/or sizes of objects in a database, learning algorithms, or a combination.
  • a target vehicle e.g., liquids, solids such as gravel or ice, particulate matter such as smoke or soot, etc.
  • target vehicle characteristic determination module 2202 may receive from particle detector hardware mounted to the host vehicle an indication of particulate matter. Target vehicle characteristic determination module 2202 may determine based on this indication that the particulate matter is, for example, smoke or soot emitted by the target vehicle.
  • Target vehicle characteristic determination module 2202 may output information indicating the determined characteristics of the target vehicle.
  • the output may be categorical in nature, indicating merely that a characteristic is present, or may indicate a degree of the characteristic, for example, such as a magnitude of an oversized vehicle's size or degree of smoke emittance.
  • the output of characteristic determination module 2202 may be passed to navigational change initiation module 2204 .
  • Navigational change initiation module 2204 may store instructions executable by processing unit 110 and may implement a desired driving policy, as described above in relation to driving policy module 803 , in order to decide on one or more navigational actions for the host vehicle to take in response to the determined target vehicle characteristic.
  • Navigational change initiation module 2204 may cause at least one navigational change of the host vehicle to initiate a pass of the target vehicle.
  • Navigational change initiation module 2204 may determine a navigational change based on an adverse condition of the target vehicle, such as an effect on visibility, effect to comfort of passengers of the host vehicle, expected effect to safety of passengers of the host vehicle, etc.
  • a driving policy may be employed to avoid the target vehicle or the adverse condition observed, such as slowing down the host vehicle, moving the host vehicle to another lane, or causing the host vehicle to pass the target vehicle.
  • navigational change initiation module 2204 may initiate a change based on size of a target vehicle. Navigational changes based on size may be initiated by taking into account a number of factors and/or metrics, such as height, width, area, shape, etc. Navigational change initiation module 2204 may also initiate a change based on the speed that the target vehicle is traveling. For example, a navigational change initiation module may initiate a pass if the target vehicle is traveling below the speed limit
  • navigational change initiation module 2204 may initiate a change based on safety considerations. For example driving behaviors such as weaving, frequent or sudden braking, failure to remain within a lane, etc. may be used as factors by navigational change initiation module 2204 .
  • navigational change initiation module 2204 may initiate a change based on vehicle type. For example, navigational change initiation module 2204 may cause the host vehicle to pass certain types of vehicles, such as construction vehicles or agricultural vehicles, or to stay back a greater distance from certain types of vehicles than from others.
  • Navigational change initiation module 2204 may also base navigational action may on other factors, such as user input.
  • navigational change initiation module 2204 may receive input from a user interface operated by a passenger of the host vehicle.
  • the input from an occupant or passenger of the host vehicle may include an input such as a non-mechanical input.
  • Such input may be used to initiate a navigational change, confirm a navigational change, override a navigational change, reinforce the appropriateness of a navigational change, request that a navigational change not be made in the future, or be used in any other combination with information received from characteristic determination module 2202 .
  • Navigational change initiation module 2204 may initiate a navigational change by determining one or more spatial targets for navigation.
  • a spatial target may be a physical location to which the host vehicle is intended to navigate in order to carry out a navigational change.
  • the physical location may be defined in absolute terms (e.g., latitude and longitude), relative to a fixed object or objects, relative to a target vehicle, or any other means of defining a spatial location.
  • the spatial target may be associated with a temporal specification, which may set an expected or intended time or time window for arriving at the spatial target.
  • the processing device may be configured to provide a set of control commands for navigating the vehicle to a selected spatial target within a selected timeframe.
  • Determination of spatial target(s) and/or temporal specification(s) may be carried out automatically, or in response to user input. Furthermore, navigational change initiation module 2204 may determine whether a safe pass maneuver is available, for example by determining whether there is available a pass maneuver that will not cause an accident of the vehicle fault.
  • Navigational change initiation module 2204 may be configured to invoke a machine learning policy module, such as described above in relation to driving policy module 803 .
  • the machine learning policy module may determine a set of actions for the vehicle to initiate and complete a pass of another vehicle.
  • FIG. 23 shows an example of a scene 2300 that may be captured by a camera of a host vehicle and analyzed during navigation of the host vehicle, as described in relation to FIG. 12 .
  • the scene shown in FIG. 23 includes a target vehicle 2302 which may be identified by the host vehicle.
  • Target vehicle 2302 includes a number of example characteristics that may be apparent in the received images, identified by target vehicle characteristic determination module 2202 , and may prompt navigational change initiation module 2204 to make a navigational change.
  • a target vehicle may include an explicit indication to avoid target vehicle 2302 , such as illuminated tail lights 2316 or a “STAY BACK” sign 2318 .
  • a target vehicle may include other unsecured material such as a flapping flat tire, a loose fabric tie-down, etc.
  • FIG. 24 is an example of a flowchart 2400 of a process for selecting between navigational rules based on a desire to pass a target vehicle.
  • at least one processing device e.g., processing device 110
  • a host vehicle navigation system may receive, from a camera associated with the host vehicle, a plurality of images representative of an environment of the host vehicle, for example as described above in relation to FIGS. 2 and 5 .
  • analysis of one or more of the received images may enable the at least one processor to identify a target vehicle, for example as described above in relation to sensing module 801 .
  • the at least one processing device may identify one or more characteristics associated with the target vehicle. Identification may be performed by characteristic determination module 2202 , as described above. For example, the at least one processing device may determine a height 2304 and/or width 2306 . The determination may be output as an absolute measurement (e.g., meters, square meters) or as a qualitative assessment (e.g., oversized). As another example, the at least one processing device may identify smoke 2310 and output an appropriate indication of smoke concentration, or merely an indication that smoke is present.
  • the at least one processing device may cause a navigational change based on the one or more characteristics identified in step 2406 .
  • the navigational change may be caused by navigational change initiation module 2204 , as described above.
  • the at least one processing device of the navigation system of the host vehicle may determine, based on the identified one or more characteristics associated with the target vehicle a navigational action for the host vehicle (e.g., slow down, pass, change lanes, etc.). To implement the navigational action the at least one processing device may cause at least one adjustment of a navigational actuator of the host vehicle in response to the determined navigational action. For example, a brake may be applied in order to slow down, and an accelerator may be applied along with steering of the wheels of the host vehicle in order to complete a pass.
  • the navigational action may be carried out automatically, without user intervention. For example, after determining the presence of a particular characteristic of the target vehicle, the at least one processing device may initiate the navigational action via adjustment of a navigational actuator.
  • One or more thresholds may also be used.
  • characteristics may be given a score, such a score between 0 and 1. The score may be based on the relevance or severity of the characteristic itself, or may vary based on a degree of the characteristic (e.g., size of oversized vehicle, degree of flapping motion of loose object, quantity of smoke, etc.).
  • the navigational action may be carried out based on the characteristic scores. For example, a navigational action may be initiated upon the score of a characteristic exceeding a preset value, or when a combination of characteristics together exceed a value, or another indicator based on the score.
  • the navigational action may also be carried out in response to a user input.
  • a passenger in the host vehicle may manipulate a user interface to initiate a navigational action associated with the characteristics identified by characteristic determination module 2202 .
  • Such manipulation may be achieved via a voice command; press of a button, a touchscreen, or a gesture recognition system, or any other means known in the art for operation of an interface.
  • the user interface may propose, based on one or more identified characteristics, to initiate a navigational action, and wait for confirmation from a user. Alternatively or additionally, the interface may accept a command from a user.
  • the navigation system may save the characteristics of the target vehicle present at the time of the command. For example, these characteristics may be saved to a database such that the host vehicle may initiate or suggest a similar navigational change at a later time, in response to an identification of the same or similar target vehicle characteristics. This may allow the system to respond in a way preferred by the user in a future drive. For example, if the user is particularly averse to repetitive braking, the host vehicle may recognize that the user has repeatedly manually initiated navigational changes to reduce such braking. The host vehicle may associate the presence of repetitive illuminated tail lights with such repetitive braking and therefore suggest or initiate a pass when behind a target vehicle that repeatedly exhibits the characteristic of illuminated tail lights.
  • a host vehicle navigation system may recognize a navigational system in which at least one target vehicle has the same or similar navigational priority as the host vehicle.
  • the navigational system may take at least one action to break the tie and provide a navigational advantage to either the target vehicle or to the host vehicle.
  • Such actions may be based on a dynamic altruistic or dominance setting.
  • the actions may include the transmission of an information signal to the target vehicle (“you go” or “I'm going”), a light flash, a nudge forward, etc.
  • the following describes systems and methods for applying such navigational tiebreakers to autonomous control of a vehicle.
  • a navigational system for a host vehicle may include at least one processing device (e.g., processing unit 110 ) programmed to receive, from at least one camera (e.g., one of image capture units 122 , 124 , and 126 ), a plurality of images representative of an environment of the host vehicle.
  • the at least one processing device may be further programmed to analyze the plurality of images to identify at least one target vehicle in the environment of the host vehicle, and determine based, at least in part, on analysis of the plurality of images that the target vehicle and the host vehicle have a similar navigational priority resulting in a navigational tie situation (i.e., non-conclusive navigational priority).
  • the at least one processing device may be further programmed to cause at least one action by the host vehicle to establish navigational priority with the host vehicle or the target vehicle, and cause control of at least one navigational actuator of the host vehicle in accordance with the established navigational priority.
  • modules 2502 , 2504 , and 2506 may be stored in memory unit 140 and/or memory unit 150 of system 100 , or modules 2502 , 2504 , and 2506 (or portions thereof) may be stored remotely from system 100 (e.g., stored in a server accessible to system 100 via, for example, wireless transceiver 172 ).
  • Navigational priority determination module 2502 which may store instructions executable by processing unit 110 , may handle various tasks relating to identifying one or more characteristics of a target vehicle sensed by sensing module 801 . Such tasks may rely upon input from various sensors and sensing systems associated with the host vehicle, such as images or image streams from one or more onboard cameras, user feedback, or user inputs to one or more user interface devices, radar, lidar, etc. Navigational priority determination module may determine whether the host vehicle or the target vehicle has the priority (i.e., “right of way”) in a particular interaction between the two vehicles. Navigational states of the host and target vehicles and the navigational rules applicable to each may be determined via any of the systems and methods described above, for example analysis of images received by the processing device.
  • navigational priority determination module 2502 may determine a navigational priority tie between the host vehicle and target vehicle.
  • Navigational priority determination module 2502 may assign navigational priority score or scores determined with respect to the target vehicle. Navigational priority determination module 2502 may determine that navigational priority is established or non-conclusive based on whether a priority score is within or outside a predetermined threshold of an assigned score. In some embodiments, a priority value may be computed for each of the host and the target vehicle. Navigational priority determination module 2502 may determine whether navigational priority is established or non-conclusive based on whether the difference between the priority values is within a predetermined confidence threshold.
  • Navigational priority establishment module 2504 may store instructions executable by processing unit 110 and may implement a desired driving policy in order to decide on one or more actions for the host vehicle to take to establish navigational priority.
  • navigational priority establishment module 2504 may be configured to establish priority based on a presumption of deference (i.e. altruism) or dominance.
  • a deference presumption may result in priority establishment module 2504 establishing priority by giving way to the target vehicle (e.g., ceding priority (“you go”)), whereas a dominance presumption may result in priority establishment module 2504 establishing priority by initiating a navigational maneuver ahead of the target vehicle (e.g., asserting priority (“I'm going”)).
  • Navigational priority establishment module 2504 may be configured such that the deference vs. dominance setting is fixed, may be set by a passenger of the host vehicle, or may be dynamic based on any number of factors. For example, deference vs. dominance may be set based on whether navigation to a desired location is running ahead of or behind schedule. That is, priority establishment module 2504 may be configured to establish priority through deference unless the host vehicle is behind schedule to arrive at its destination.
  • navigational priority establishment module 2504 may transmit an informational signal to the target vehicle.
  • the informational signal may indicate that the host vehicle intends to give way to the target vehicle or may indicate that the host vehicle intends to initiate a navigational maneuver ahead of the target vehicle.
  • the signal may be transmitted via any known means, such as via a visual cue, and audible cue, motion, wireless communication (e.g., digital or analog wireless networking).
  • navigational priority establishment module 2504 may be configured to nudge the host vehicle to indicate priority. Nudging may indicate that the host vehicle moves out a certain distance at a time (e.g., a small distance, such as centimeters, a meter, a few meters, as appropriate for the situation).
  • navigational priority establishment module 2504 may nudge the host vehicle forward to assert priority and may nudge the host vehicle backward to cede priority. Those of skill in the art will recognize that other motion-based cues may be used in place of nudging backward or forward.
  • the system may continue to evaluate the navigational priority as the nudge takes place, i.e., to continue to determine whether the other vehicle has ceded in response to the nudging.
  • navigational priority establishment module 2504 may be configured to cause the host vehicle to emit a flash of a light to indicate priority. For example, navigational priority establishment module 2504 may cause the host vehicle to flash its headlights to indicate an intention to cede priority to the target vehicle. Similar to the case of nudging the system to continue to determine whether the other vehicle has ceded in response to the flash.
  • navigational priority establishment module 2504 may be configured to detect a response by the target vehicle to the established priority.
  • the response may be via any known means, such as via a visual cue, and audible cue, motion, wireless communication (e.g. digital or analog wireless networking).
  • the detected response may be detecting a navigational change by the target vehicle, acting upon the established priority.
  • Navigational change initiation module 2206 may store instructions executable by processing unit 110 and may implement a desired driving policy in order to decide on one or more navigational actions for the host vehicle to take in response to the established navigational priority.
  • FIG. 26A shows an example of a scene 2600 that may be captured by a camera of a host vehicle and analyzed during navigation of the host vehicle, as described in relation to FIG. 12 .
  • the scene shown in FIG. 26A includes a target vehicle 2602 arriving at one side of a four-way stop ahead of intersection 2604 . If the host vehicle arrives at stop sign 2606 at the same or nearly the same time as the target vehicle arrives at stop sign 2608 , a navigational tie may result.
  • the navigational tie may be resolved in a number of ways, for example by flashing headlights of the host vehicle, or moving the host vehicle slightly in a way that will be recognized by the target vehicle.
  • FIG. 26B shows an example of a scene 2650 that may be captured by a camera of a host vehicle and analyzed during navigation of the host vehicle, as described in relation to FIG. 12 .
  • the scene shown in FIG. 26B includes a target vehicle 2652 above to merge into the same line of a highway as the host vehicle. If the target vehicle is about to arrive at the same place in the highway as the target vehicle is about to merge, a navigational tie may result.
  • the navigational tie may be resolved in a number of ways, for example by flashing headlights of the host vehicle.
  • FIG. 27 is an example of a flowchart 2700 representing an example process for addressing ties in navigational priority.
  • navigational rules may be established or modified based on a jurisdiction relevant to a location of the host vehicle.
  • at least one processing device e.g., processing device 110
  • a host vehicle navigation system may receive, from a camera associated with the host vehicle, a plurality of images representative of an environment of the host vehicle, for example as described above in relation to FIGS. 2 and 5 .
  • analysis of one or more of the received images may enable the at least one processor to identify a target vehicle, for example as described above in relation to sensing module 801 .
  • the at least one processing device may determine that the target vehicle and the host vehicle have a similar navigational priority resulting in a navigational tie situation. The determination may be performed by navigational priority determination module 2502 , as described above.
  • the host vehicle and target vehicle 2602 may arrive at a four-way stop intersection 2604 nearly simultaneously, as depicted in FIG. 26A .
  • the at least one processing device may determine that both the host vehicle and target vehicle 2602 are required to stop, for example by analyzing received images to recognize the “4-WAY” instruction included in stop sign 2606 or by analyzing received images to recognize that both 2062 the host vehicle and target vehicle 2602 are approaching stop signs 2606 and 2608 respectively.
  • the at least one processing device may attempt to determine which of the host vehicle and target vehicle 2602 arrived at the four way stop first, to determine which has priority. If the host vehicle and target vehicle arrived simultaneously or within a threshold amount of time from each other, navigational priority determination module 2502 may determine that the navigational priority is a tie.
  • the host vehicle and a target vehicle 2652 may approach each other to merge into the same lane of a road at the same time or nearly the same time.
  • the at least one processing device may determine whether the host vehicle and target vehicle can both safely attempt to merge or if one will need to give way. If one of the host vehicle and target vehicle will need to give way, the navigational priority determination module 2502 may determine that the navigational priority is a tie.
  • the at least one processing device may cause action by the host vehicle to establish navigational priority with the host vehicle or the target vehicle.
  • the establishment of navigational priority may be performed by navigational priority establishment module 2504 , as described above. That is, the host vehicle may transmit an informational signal to the target vehicle to establish navigational priority.
  • navigational priority establishment module 2504 may cause the host vehicle to nudge forward to assert priority or flash its headlights to cede priority.
  • navigational priority establishment module 2504 may also detect a response by the target vehicle to the established priority, as described above.
  • the detected response may be a received information signal confirming establishment of priority, or may be determined by detecting a navigational change by the target vehicle, acting upon the established priority.
  • the response may be that the target vehicle stops, slows, or otherwise cedes priority.
  • the at least one processing device may cause control of a navigational actuator of the host vehicle in accordance with the established navigational priority.
  • Control of the navigational actuator may be based on a navigational priority established at step 2710 , described above. For example, a brake may be applied, an accelerator may be applied, and/or steering of the wheels of the host vehicle may be carried out accordance with the established navigational priority.
  • a host vehicle navigation system may suspend or relax normal navigational rules in some situations. For example, in a traffic jam, certain right of way rules (e.g., in a traffic circle) may be suspended. As another example, in response to a detected hazard (e.g., a weaving vehicle in a lane adjacent to the host vehicle, or an obstacle in a lane of the host vehicle, etc.), rules regarding not driving on a shoulder or in a high occupancy vehicle (“HOV”) lane may be temporarily suspended.
  • HOV high occupancy vehicle
  • a navigational system for a host vehicle may include at least one processing device (e.g., processing unit 110 ) programmed to receive, from at least one camera (e.g., one of image capture units 122 , 124 , and 126 ), a plurality of images representative of an environment of the host vehicle.
  • the at least one processing device may be further programmed to analyze the plurality of images to identify a presence in the environment of the host vehicle a navigation rule suspension condition.
  • the at least one processing device may further programmed to temporarily suspend at least one navigational rule in response to identification of the navigation rule suspension condition, and cause at least one navigational change of the host vehicle unconstrained by the temporarily suspended at least one navigational rule.
  • modules 2802 and 2804 may be stored in memory unit 140 and/or memory unit 150 of system 100 , or modules 2802 and 2804 (or portions thereof) may be stored remotely from system 100 (e.g., stored in a server accessible to system 100 via, for example, wireless transceiver 172 ).
  • Rule suspension condition determination module 2802 may handle various tasks relating to identifying one or more conditions which may justify and/or require suspension of one or more navigational rules.
  • Such rules may include traffic rules (e.g., speed, right of way, stop signs, traffic lights, not driving on a shoulder, etc.), route rules (e.g., avoid traffic, avoid tolls, etc.), or other rules.
  • Such tasks may rely upon input from various sensors and sensing systems associated with the host vehicle, such as images or image streams from one or more onboard cameras, user feedback, or user inputs to one or more user interface devices, radar, lidar, etc.
  • rule suspension condition determination module may identify conditions that may justify and/or require a suspension of one or more navigational rules, such as traffic or a traffic jam, obstacles or other obstructions, safety hazards, irregular behavior by one or more target vehicles, emergency vehicles, etc.
  • the output of rule suspension condition determination module 2802 may be passed to navigational rule suspension module 2804 .
  • Navigational rule suspension module may store instructions executable by processing unit 110 to identify and suspend navigational rules based on one or more conditions identified by rule suspension condition determination module 2802 .
  • the temporarily suspended rule(s) may prohibit navigation in selected areas under normal operating conditions.
  • after rule suspension condition determination module 2802 indicates an obstacle is in the road ahead of the host vehicle navigational rule suspension module 2804 may suspend a rule interfering with bypassing the obstacle. For example, navigational rule suspension module 2804 may suspend a navigational rule preventing the host vehicle from entering a high occupancy vehicle lane or a shoulder of a road, allowing the host vehicle to avoid the obstacle.
  • navigational rule suspension module 2804 may suspend a rule in response to a target vehicle encroaching into a lane of the host vehicle.
  • traffic conditions such as a traffic jam may render certain actions permissible that would be impermissible if traffic were flowing normally. Therefore, for example in the case of traffic, navigational rule suspension module 2804 may suspend a rule establishing navigational rights-of-way, speed limits, restrictions on passing, etc. under normal operating conditions.
  • Navigational rule suspension module 2804 may suspend a rule based on a degree of a rule suspension condition. For example, rule suspension module 2804 may determine that a rule suspension condition includes a height of an obstacle, and suspending the navigational rule may be based on whether the height exceeds a threshold.
  • Navigational rule suspension module 2804 may determine whether a condition may merit a rule suspension based on one or more factors which may be considered to take priority over the basis for the rule. Factors such as safety of an occupant of the host vehicle, safety of persons proximate to the host vehicle, imminence of a collision with a target vehicle or anther object, potential for loss of the host vehicle, etc.
  • factors associated with rule suspension conditions may be assigned a weight or a level of importance, for example on a scale from 0 to 1, where the level of importance may need to exceed a threshold before the rule may be suspended.
  • the threshold for suspension of a rule may vary depending on the rule. For example, a threshold to suspend a rule preventing entering an HOV lane may be lower than a threshold to suspend a rule preventing driving on the shoulder of a highway.
  • whether a condition may merit a rule suspension may consider a plurality of factors.
  • Each of the plurality of factors may be assigned a weight or a level of importance.
  • the weighted values of the plurality of factors or a cumulative score related to the level of importance may be considered in determining whether to suspend a rule.
  • rule suspension module 2804 may replace a temporarily suspended rule with a temporary rule.
  • the temporary rule may for example be more relaxed than the suspended rule, or may be specific to the condition associated with the rules suspension condition.
  • FIG. 29 shows an example of a scene 2900 that may be captured by at least one camera of a host vehicle and analyzed during navigation of the host vehicle, as described in relation to FIG. 12 .
  • Scene 2900 includes a highway 2902 including three lanes, 2904 , 2916 , and 2918 , and a shoulder 2910 .
  • Lane 2904 is restricted to HOV use, as indicated by sign 2906 and road marking 2908
  • sign 2912 indicates that shoulder 2910 is restricted from use by vehicular traffic.
  • Lanes 2916 and 2918 are open to general traffic.
  • Scene 2900 also includes an object 2914 , in this example a large box, obstructing lanes 2916 and 2918 .
  • the host vehicle may change lanes to lane 2904 . To do so, a navigational rule prohibiting non HOV vehicles in lane 2904 may be temporarily suspended by the host vehicle's navigation system.
  • FIG. 30 shows an example of another scene 3000 that may be captured by at least one camera of a host vehicle and analyzed during navigation of the host vehicle, as described in relation to FIG. 12 .
  • scene 3000 includes a vehicle 3002 weaving from lane 2918 into lane 2916 .
  • the host vehicle may change lanes to lane 2904 or 2910 .
  • navigational rules prohibiting non HOV vehicles in lane 2904 and prohibiting vehicles in lane 2910 may be temporarily suspended by the host vehicle's navigation system.
  • the navigational change may result in the host vehicle entering a traffic circle without right of way.
  • FIG. 31 is an example of a flowchart 3100 representing an example process for suspending navigational rules.
  • navigational rules may be suspended based on circumstances detected by a host vehicle.
  • At step 3102 at least one processing device (e.g., processing device 110 ) of the host vehicle navigation system may receive, from a camera associated with the host vehicle, a plurality of images representative of an environment of the host vehicle, for example as described above in relation to FIGS. 2 and 5 .
  • the at least one processing device may analyze one or more of the received images to identify in the environment of the host vehicle a rule suspension condition.
  • the analysis may be performed, for example, as described above in relation to sensing module 801 .
  • the analysis at step 3104 may be performed by rule suspension condition determination module 2802 , as described above.
  • the at least one processing device may identify object 2916 or vehicle 3002 shown in scenes 2900 and 3000 , respectively. Accordingly, the at least one processing device may determine whether a rule suspension condition is present in the received images.
  • the at least one processing device may temporarily suspend at least one navigational rule in response to identification of the navigation rule suspension condition.
  • step 3106 may be performed by navigational rule suspension module 2804 , as described above.
  • the at least one processing device may suspend a rule prohibiting, under normal conditions, driving on a road shoulder 2910 , suspend a rule prohibiting, under normal conditions, driving in a high occupancy vehicle (HOV) lane with fewer than a required number of occupants, or suspend a rule establishing, under normal conditions, that vehicles in a traffic circle have right-of-way over vehicles entering the traffic circle.
  • the rule may be suspended based on a degree of a rule suspension condition, as described above. For example, a rule may be suspended based on a determination that object 2914 exceeds a predetermined height. Alternatively, if object 2914 does not exceed the predetermined height, the rule may be left in place such that the host vehicle travels over object 2914 .
  • the suspended rule may be replaced with a temporary rule.
  • a rule establishing a speed limit of 70 miles per hour may be replaced with a more relaxed rule setting a speed limit of 90 miles per hour, for example to give the host vehicle an opportunity to avoid vehicle 3002 .
  • a temporary rule may be associated with an expiration based on, for example, a predetermined amount of time and/or a predetermined distance.
  • the at least one processing device may cause at least one navigational change of the host vehicle unconstrained by the temporarily suspended at least one navigational rule.
  • the at least one processing device of the navigation system of the host vehicle may determine, based on the analyzed scene, the identified rule suspension condition, and the suspended navigational rules a navigational action for the host vehicle (e.g., turn left, stop, yield, pass, change lanes, etc.) due to the rule suspension condition.
  • the at least one processing device may cause at least one adjustment of a navigational actuator of the host vehicle in response to the determined navigational action.
  • a brake may be applied or an accelerator may be applied along with steering of the wheels of the host vehicle.
  • the at least one navigational change may result in the host vehicle entering a road shoulder or the host vehicle entering a high occupancy vehicle lane.
  • Programs based on the written description and disclosed methods are within the skill of an experienced developer.
  • the various programs or program modules can be created using any of the techniques known to one skilled in the art or can be designed in connection with existing software.
  • program sections or program modules can be designed in or by means of .Net Framework, .Net Compact Framework (and related languages, such as Visual Basic, C, etc.), Java, C++, Objective-C, HTML, HTML/AJAX combinations, XML, or HTML with included Java applets.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Electromagnetism (AREA)
  • Artificial Intelligence (AREA)
  • Chemical & Material Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Evolutionary Computation (AREA)
  • Game Theory and Decision Science (AREA)
  • Medical Informatics (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
  • Navigation (AREA)
  • Steering Control In Accordance With Driving Conditions (AREA)
US16/507,971 2017-01-12 2019-07-10 Pass on command feature for a navigation system Abandoned US20190329782A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US16/507,971 US20190329782A1 (en) 2017-01-12 2019-07-10 Pass on command feature for a navigation system
US17/861,533 US20220363248A1 (en) 2017-01-12 2022-07-11 Temporary rule suspension for autonomous navigation

Applications Claiming Priority (6)

Application Number Priority Date Filing Date Title
US201762445500P 2017-01-12 2017-01-12
US201762546343P 2017-08-16 2017-08-16
US201762565244P 2017-09-29 2017-09-29
US201762582687P 2017-11-07 2017-11-07
PCT/US2018/013391 WO2018132614A2 (en) 2017-01-12 2018-01-11 Rules-based navigation
US16/507,971 US20190329782A1 (en) 2017-01-12 2019-07-10 Pass on command feature for a navigation system

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2018/013391 Continuation WO2018132614A2 (en) 2017-01-12 2018-01-11 Rules-based navigation

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/861,533 Continuation US20220363248A1 (en) 2017-01-12 2022-07-11 Temporary rule suspension for autonomous navigation

Publications (1)

Publication Number Publication Date
US20190329782A1 true US20190329782A1 (en) 2019-10-31

Family

ID=61054599

Family Applications (9)

Application Number Title Priority Date Filing Date
US16/507,773 Active 2039-04-19 US11738741B2 (en) 2017-01-12 2019-07-10 Navigation based on detected occlusion overlapping a road entrance
US16/507,971 Abandoned US20190329782A1 (en) 2017-01-12 2019-07-10 Pass on command feature for a navigation system
US16/508,142 Active US10875528B2 (en) 2017-01-12 2019-07-10 Navigation through automated negotiation with other vehicles
US16/509,325 Active 2038-08-01 US11173900B2 (en) 2017-01-12 2019-07-11 Navigating based on sensed brake light patterns
US16/509,135 Active US12090994B2 (en) 2017-01-12 2019-07-11 Navigation based on bahaviors of following vehicles
US16/508,872 Active US11034346B2 (en) 2017-01-12 2019-07-11 Navigation at alternating merge zones
US17/325,301 Active US11608057B2 (en) 2017-01-12 2021-05-20 Navigation at alternating merge zones
US17/861,533 Pending US20220363248A1 (en) 2017-01-12 2022-07-11 Temporary rule suspension for autonomous navigation
US18/219,240 Pending US20230347877A1 (en) 2017-01-12 2023-07-07 Navigation Based on Detected Size of Occlusion Zones

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US16/507,773 Active 2039-04-19 US11738741B2 (en) 2017-01-12 2019-07-10 Navigation based on detected occlusion overlapping a road entrance

Family Applications After (7)

Application Number Title Priority Date Filing Date
US16/508,142 Active US10875528B2 (en) 2017-01-12 2019-07-10 Navigation through automated negotiation with other vehicles
US16/509,325 Active 2038-08-01 US11173900B2 (en) 2017-01-12 2019-07-11 Navigating based on sensed brake light patterns
US16/509,135 Active US12090994B2 (en) 2017-01-12 2019-07-11 Navigation based on bahaviors of following vehicles
US16/508,872 Active US11034346B2 (en) 2017-01-12 2019-07-11 Navigation at alternating merge zones
US17/325,301 Active US11608057B2 (en) 2017-01-12 2021-05-20 Navigation at alternating merge zones
US17/861,533 Pending US20220363248A1 (en) 2017-01-12 2022-07-11 Temporary rule suspension for autonomous navigation
US18/219,240 Pending US20230347877A1 (en) 2017-01-12 2023-07-07 Navigation Based on Detected Size of Occlusion Zones

Country Status (8)

Country Link
US (9) US11738741B2 (ko)
EP (4) EP3548845B1 (ko)
JP (4) JP7160251B2 (ko)
KR (3) KR102535540B1 (ko)
CN (3) CN110657820A (ko)
CA (1) CA3049770A1 (ko)
IL (3) IL293713B2 (ko)
WO (3) WO2018132607A2 (ko)

Cited By (38)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111301410A (zh) * 2020-02-24 2020-06-19 新石器慧通（北京）科技有限公司 自动驾驶车辆及其车速调节方法
US10752258B2 (en) * 2018-09-17 2020-08-25 GM Global Technology Operations LLC Apparatus and method for audible driver confirmation for maneuvers in an autonomous vehicle
US10816968B2 (en) * 2018-05-08 2020-10-27 GM Global Technology Operations LLC System and method for access to restricted areas by an autonomous vehicle
US10836405B2 (en) 2017-10-30 2020-11-17 Nissan North America, Inc. Continual planning and metareasoning for controlling an autonomous vehicle
US20200386031A1 (en) * 2018-03-29 2020-12-10 Toyoda Gosei Co., Ltd. Vehicle door opening/closing device
US20210101625A1 (en) * 2019-10-08 2021-04-08 Motional Ad Llc Navigating multi-way stop intersections with an autonomous vehicle
US11027751B2 (en) 2017-10-31 2021-06-08 Nissan North America, Inc. Reinforcement and model learning for vehicle operation
US20210240274A1 (en) * 2020-01-30 2021-08-05 Toyota Motor Engineering & Manufacturing North America, Inc. System and method for interpreting gestures
US11084504B2 (en) * 2017-11-30 2021-08-10 Nissan North America, Inc. Autonomous vehicle operational management scenarios
CN113276864A (zh) * 2020-02-20 2021-08-20 操纵技术Ip控股公司 用于障碍物接近检测的系统和方法
US11110941B2 (en) 2018-02-26 2021-09-07 Renault S.A.S. Centralized shared autonomous vehicle operational management
US11113973B2 (en) * 2017-02-10 2021-09-07 Nissan North America, Inc. Autonomous vehicle operational management blocking monitoring
US11120688B2 (en) 2018-06-29 2021-09-14 Nissan North America, Inc. Orientation-adjust actions for autonomous vehicle operational management
US20210284191A1 (en) * 2020-03-11 2021-09-16 Cartica Ai Ltd Autonomous driving using local driving patterns
US11135719B2 (en) * 2015-09-21 2021-10-05 Rainbow Robotics Real-time control system, real-time control device and system control method
US11209822B2 (en) * 2019-06-28 2021-12-28 Zoox, Inc. Techniques for contacting a teleoperator
US11275370B2 (en) 2019-06-28 2022-03-15 Zoox, Inc. Techniques for navigating vehicles using teleoperator instructions
US11295609B1 (en) 2018-12-06 2022-04-05 Nissan Motor Co., Ltd. Travel assistance method and travel assistance device
US11300957B2 (en) 2019-12-26 2022-04-12 Nissan North America, Inc. Multiple objective explanation and control interface design
US11400935B2 (en) * 2018-04-23 2022-08-02 Renault S.A.S. Method for a motor vehicle to select a preferred traffic lane to cross a toll area
US11443524B2 (en) * 2018-12-10 2022-09-13 Motional Ad Llc Systems and methods for validating sensor calibration
US11500380B2 (en) 2017-02-10 2022-11-15 Nissan North America, Inc. Autonomous vehicle operational management including operating a partially observable Markov decision process model instance
US11510404B2 (en) * 2018-05-24 2022-11-29 Blue River Technology Inc. Boom sprayer including machine feedback control
US11577746B2 (en) 2020-01-31 2023-02-14 Nissan North America, Inc. Explainability of autonomous vehicle decision making
US11613269B2 (en) 2019-12-23 2023-03-28 Nissan North America, Inc. Learning safety and human-centered constraints in autonomous vehicles
US11635758B2 (en) 2019-11-26 2023-04-25 Nissan North America, Inc. Risk aware executor with action set recommendations
US11647685B2 (en) * 2018-07-12 2023-05-16 Raven Industries, Inc. Implement position control system and method for same
US11702070B2 (en) 2017-10-31 2023-07-18 Nissan North America, Inc. Autonomous vehicle operation with explicit occlusion reasoning
US11714971B2 (en) 2020-01-31 2023-08-01 Nissan North America, Inc. Explainability of autonomous vehicle decision making
US20230249778A1 (en) * 2020-06-26 2023-08-10 Robert Bosch Gmbh Controller for straddle-type vehicle, rider-assistance system, and control method for straddle-type vehicle
US11782438B2 (en) 2020-03-17 2023-10-10 Nissan North America, Inc. Apparatus and method for post-processing a decision-making model of an autonomous vehicle using multivariate data
US20230356741A1 (en) * 2020-11-19 2023-11-09 Nissan Motor Co., Ltd. Travel Control Method and Travel Control Apparatus for Vehicle
US11874120B2 (en) 2017-12-22 2024-01-16 Nissan North America, Inc. Shared autonomous vehicle operational management
US11899454B2 (en) 2019-11-26 2024-02-13 Nissan North America, Inc. Objective-based reasoning in autonomous vehicle decision-making
US11940539B2 (en) 2019-12-18 2024-03-26 Motional Ad Llc Camera-to-LiDAR calibration and validation
US11952014B2 (en) 2021-10-29 2024-04-09 Waymo Llc Behavior predictions for active emergency vehicles
US12037015B2 (en) 2020-07-28 2024-07-16 Denso Corporation Vehicle control device and vehicle control method
US12110012B2 (en) 2019-07-26 2024-10-08 Denso Corporation Vehicle control apparatus and vehicle control method

Families Citing this family (188)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9499139B2 (en) * 2013-12-05 2016-11-22 Magna Electronics Inc. Vehicle monitoring system
DE102015218809A1 (de) * 2015-09-29 2017-03-30 Continental Teves Ag & Co. Ohg Verfahren zum Aktualisieren einer elektronischen Karte eines Fahrzeugs
WO2018024320A1 (en) * 2016-08-02 2018-02-08 Bayerische Motoren Werke Aktiengesellschaft A method for learning an illumination-pattern of a monitored automobile and a respective automobile
KR102535540B1 (ko) * 2017-01-12 2023-05-23 모빌아이 비젼 테크놀로지스 엘티디. 차량 움직임에 기반한 항법
US20180208203A1 (en) * 2017-01-26 2018-07-26 International Business Machines Corporation System, method and computer program product for braking control when approaching a traffic signal
FR3062944B1 (fr) * 2017-02-10 2021-05-14 Continental Automotive France Procede de detection de faux-positifs relatifs a un feu de signalisation
US10671076B1 (en) 2017-03-01 2020-06-02 Zoox, Inc. Trajectory prediction of third-party objects using temporal logic and tree search
US10133275B1 (en) 2017-03-01 2018-11-20 Zoox, Inc. Trajectory generation using temporal logic and tree search
CN108305477B (zh) * 2017-04-20 2019-08-13 腾讯科技（深圳）有限公司 一种车道选择方法及终端
US11208103B2 (en) * 2017-05-24 2021-12-28 Honda Motor Co., Ltd. Vehicle control device
US10296004B2 (en) * 2017-06-21 2019-05-21 Toyota Motor Engineering & Manufacturing North America, Inc. Autonomous operation for an autonomous vehicle objective in a multi-vehicle environment
US10816354B2 (en) 2017-08-22 2020-10-27 Tusimple, Inc. Verification module system and method for motion-based lane detection with multiple sensors
US10850732B2 (en) * 2017-09-05 2020-12-01 Aptiv Technologies Limited Automated speed control system
US10860019B2 (en) 2017-09-08 2020-12-08 Motional Ad Llc Planning autonomous motion
US10733465B2 (en) 2017-09-20 2020-08-04 Tusimple, Inc. System and method for vehicle taillight state recognition
JP2019075008A (ja) * 2017-10-18 2019-05-16 トヨタ自動車株式会社 車両制御装置
US20180079423A1 (en) * 2017-11-27 2018-03-22 GM Global Technology Operations LLC Active traffic participant
JP7200946B2 (ja) * 2017-12-12 2023-01-10 ソニーグループ株式会社 情報処理装置、制御システム、情報処理方法及びプログラム
WO2019117774A1 (en) * 2017-12-14 2019-06-20 Saab Ab Flight vision system and method for presenting images from the surrounding of an airborne vehicle in a flight vision system
US11273836B2 (en) 2017-12-18 2022-03-15 Plusai, Inc. Method and system for human-like driving lane planning in autonomous driving vehicles
US20190185012A1 (en) 2017-12-18 2019-06-20 PlusAI Corp Method and system for personalized motion planning in autonomous driving vehicles
US11130497B2 (en) 2017-12-18 2021-09-28 Plusai Limited Method and system for ensemble vehicle control prediction in autonomous driving vehicles
US20190187719A1 (en) * 2017-12-19 2019-06-20 Trw Automotive U.S. Llc Emergency lane change assistance system
US11422561B2 (en) * 2018-01-11 2022-08-23 Toyota Jidosha Kabushiki Kaisha Sensor system for multiple perspective sensor data sets
US10955851B2 (en) 2018-02-14 2021-03-23 Zoox, Inc. Detecting blocking objects
US11009365B2 (en) 2018-02-14 2021-05-18 Tusimple, Inc. Lane marking localization
US11009356B2 (en) 2018-02-14 2021-05-18 Tusimple, Inc. Lane marking localization and fusion
JP7000202B2 (ja) * 2018-02-27 2022-01-19 本田技研工業株式会社 車両制御システム、車両制御方法、およびプログラム
JP2019156180A (ja) * 2018-03-13 2019-09-19 本田技研工業株式会社 車両制御装置、車両制御方法、およびプログラム
US11671329B2 (en) * 2018-04-04 2023-06-06 Arista Networks, Inc. Computation of network flooding topologies
US10414395B1 (en) 2018-04-06 2019-09-17 Zoox, Inc. Feature-based prediction
US10895468B2 (en) * 2018-04-10 2021-01-19 Toyota Jidosha Kabushiki Kaisha Dynamic lane-level vehicle navigation with lane group identification
US11126873B2 (en) * 2018-05-17 2021-09-21 Zoox, Inc. Vehicle lighting state determination
US11218399B2 (en) 2018-06-20 2022-01-04 Arista Networks, Inc. Embedded area abstraction
WO2020014683A1 (en) 2018-07-13 2020-01-16 Kache.AI Systems and methods for autonomous object detection and vehicle following
US11287814B2 (en) * 2018-08-07 2022-03-29 GM Global Technology Operations LLC Lane change detection system and method for an autonomous vehicle
JP7091956B2 (ja) * 2018-09-07 2022-06-28 トヨタ自動車株式会社 車両の車線変更支援装置
JP7040621B2 (ja) * 2018-09-07 2022-03-23 日産自動車株式会社 車両の走行制御方法及び走行制御装置
US10884424B2 (en) 2018-09-07 2021-01-05 GM Global Technology Operations LLC Traffic light occlusion detection for autonomous vehicle
KR102637599B1 (ko) * 2018-10-08 2024-02-19 주식회사 에이치엘클레무브 차량간 통신 정보를 이용한 차선변경 제어장치 및 방법과, 그를 위한 성향 정보 산출 장치
KR20200040374A (ko) * 2018-10-10 2020-04-20 삼성전자주식회사 거리 추정 방법 및 장치
US10627819B1 (en) 2018-10-11 2020-04-21 Pony Ai Inc. On-site notification from autonomous vehicle for traffic safety
US10816987B2 (en) * 2018-10-15 2020-10-27 Zoox, Inc. Responsive vehicle control
US10940863B2 (en) * 2018-11-01 2021-03-09 GM Global Technology Operations LLC Spatial and temporal attention-based deep reinforcement learning of hierarchical lane-change policies for controlling an autonomous vehicle
WO2020100023A1 (en) * 2018-11-12 2020-05-22 Srg Global, Inc. Detection of modified vehicle body components for aeb response
JP7183729B2 (ja) * 2018-11-26 2022-12-06 トヨタ自動車株式会社 撮影異常診断装置
US11537811B2 (en) * 2018-12-04 2022-12-27 Tesla, Inc. Enhanced object detection for autonomous vehicles based on field view
JP7085973B2 (ja) * 2018-12-12 2022-06-17 本田技研工業株式会社 運転支援装置、車両、運転支援装置の制御方法および運転支援プログラム
US11403955B2 (en) 2018-12-14 2022-08-02 Brunswick Corporation Marine propulsion control system and method with proximity-based velocity limiting
US11373537B2 (en) 2018-12-21 2022-06-28 Brunswick Corporation Marine propulsion control system and method with collision avoidance override
CN110614995B (zh) * 2018-12-29 2021-01-22 长城汽车股份有限公司 车辆自动驾驶时的行车道选择方法、选择系统及车辆
US10780861B2 (en) * 2019-01-08 2020-09-22 Ford Global Technologies, Llc Liquid droplet path prediction
EP3683782B1 (en) * 2019-01-18 2023-06-28 Honda Research Institute Europe GmbH Method for assisting a driver, driver assistance system, and vehicle including such driver assistance system
US11338807B2 (en) 2019-01-30 2022-05-24 Allstate Insurance Company Dynamic distance estimation output generation based on monocular video
US10796571B2 (en) * 2019-01-31 2020-10-06 StradVision, Inc. Method and device for detecting emergency vehicles in real time and planning driving routes to cope with situations to be expected to be occurred by the emergency vehicles
US11074480B2 (en) * 2019-01-31 2021-07-27 StradVision, Inc. Learning method and learning device for supporting reinforcement learning by using human driving data as training data to thereby perform personalized path planning
US11702178B2 (en) 2019-01-31 2023-07-18 Brunswick Corporation Marine propulsion control system, method, and user interface for marine vessel docking and launch
US11257378B2 (en) 2019-01-31 2022-02-22 Brunswick Corporation Marine propulsion control system and method
CN111325318B (zh) * 2019-02-01 2023-11-24 北京地平线机器人技术研发有限公司 神经网络的训练方法、神经网络的训练装置和电子设备
KR102671622B1 (ko) * 2019-02-01 2024-06-03 주식회사 에이치엘클레무브 주차 공간 검출 장치 및 방법
JP7275623B2 (ja) * 2019-02-12 2023-05-18 株式会社デンソー 運転支援装置
DE102019202107B3 (de) * 2019-02-18 2020-04-23 Zf Friedrichshafen Ag Kollisionsvermeidung einer autonomen Landmaschine
FR3093057B1 (fr) * 2019-02-21 2021-02-19 Renault Sas Procédé de sécurisation d’un véhicule.
JP7199269B2 (ja) * 2019-03-20 2023-01-05 日立Astemo株式会社 外界センシング情報処理装置
CN113614777A (zh) * 2019-03-28 2021-11-05 索尼集团公司 信息处理装置、信息处理方法和程序
JP2020164045A (ja) * 2019-03-29 2020-10-08 マツダ株式会社 車両走行制御装置
JP2020179729A (ja) * 2019-04-24 2020-11-05 マツダ株式会社 車両制御装置
JP7197832B2 (ja) * 2019-04-24 2022-12-28 マツダ株式会社 車両制御装置
US11267393B2 (en) * 2019-05-16 2022-03-08 Magna Electronics Inc. Vehicular alert system for alerting drivers of other vehicles responsive to a change in driving conditions
CN110532846B (zh) * 2019-05-21 2022-09-16 华为技术有限公司 自动换道方法、装置及存储介质
JP7303667B2 (ja) * 2019-05-31 2023-07-05 株式会社Subaru 自動運転支援装置
US20200406894A1 (en) * 2019-06-28 2020-12-31 Zoox, Inc. System and method for determining a target vehicle speed
KR20210002959A (ko) * 2019-07-01 2021-01-11 현대자동차주식회사 자율주행차량의 차선변경 제어 장치 및 그 방법
JP6898388B2 (ja) * 2019-07-05 2021-07-07 本田技研工業株式会社 車両の制御システム、車両の制御方法、およびプログラム
US20210025738A1 (en) * 2019-07-24 2021-01-28 EMC IP Holding Company LLC System and method for device operation monitoring
KR20190098735A (ko) * 2019-08-01 2019-08-22 엘지전자 주식회사 차량 단말 및 그의 동작 방법
US11403853B2 (en) * 2019-08-30 2022-08-02 Waymo Llc Occupancy prediction neural networks
JP7161458B2 (ja) * 2019-09-09 2022-10-26 本田技研工業株式会社 車両制御装置、車両制御方法、およびプログラム
US11614739B2 (en) 2019-09-24 2023-03-28 Apple Inc. Systems and methods for hedging for different gaps in an interaction zone
WO2021062596A1 (en) * 2019-09-30 2021-04-08 Beijing Voyager Technology Co., Ltd. Systems and methods for predicting a vehicle trajectory
CN112572462B (zh) 2019-09-30 2022-09-20 阿波罗智能技术(北京)有限公司 自动驾驶的控制方法、装置、电子设备及存储介质
US11420630B2 (en) 2019-10-24 2022-08-23 Zoox, Inc. Trajectory modifications based on a collision zone
US11643073B2 (en) * 2019-10-24 2023-05-09 Zoox, Inc. Trajectory modifications based on a collision zone
US11577757B2 (en) * 2019-11-01 2023-02-14 Honda Motor Co., Ltd. System and method for future forecasting using action priors
CN110728878A (zh) * 2019-11-06 2020-01-24 北京千种幻影科技有限公司 一种体感交互vr模拟驾驶装置
US11640155B2 (en) * 2019-11-07 2023-05-02 Baker Hughes Oilfield Operations Llc Customizable workflows for machinery management
CN110989568B (zh) * 2019-11-15 2021-03-30 吉林大学 一种基于模糊控制器的自动驾驶车辆安全通行方法及系统
CN112859830B (zh) * 2019-11-28 2022-08-26 华为技术有限公司 一种设计运行区域odd判断方法、装置及相关设备
CN112925301B (zh) * 2019-12-05 2024-05-17 杭州海康机器人股份有限公司 用于agv避险的控制方法和agv
US11609576B2 (en) * 2019-12-05 2023-03-21 Baidu Usa Llc Emergency vehicle audio detection
US11592575B2 (en) * 2019-12-20 2023-02-28 Waymo Llc Sensor steering for multi-directional long-range perception
CN114902655A (zh) * 2019-12-23 2022-08-12 Jvc建伍株式会社 记录装置、记录方法以及程序
US11415992B2 (en) * 2019-12-27 2022-08-16 Woven Planet North America, Inc. Resource prioritization based on travel path relevance
WO2021134172A1 (zh) * 2019-12-30 2021-07-08 华为技术有限公司 一种轨迹预测方法及相关设备
US11296948B2 (en) 2020-01-09 2022-04-05 Arista Networks, Inc. Topology partition detection
CN113128315A (zh) * 2020-01-15 2021-07-16 宝马股份公司 一种传感器模型性能评估方法、装置、设备及存储介质
CN113677583B (zh) * 2020-01-21 2023-08-15 深圳元戎启行科技有限公司 基于图计算的车辆驾驶数据处理方法、装置和计算机设备
CN111258300B (zh) * 2020-01-22 2023-05-30 长安大学 一种无人车无信号灯环岛通行能力测试系统及测试方法
CN111289003A (zh) * 2020-02-06 2020-06-16 广州小马智行科技有限公司 路径规划方法、装置、系统、存储介质和处理器
JP7371520B2 (ja) * 2020-02-14 2023-10-31 トヨタ自動車株式会社 情報処理装置、情報処理方法、及び、プログラム
US11639173B2 (en) * 2020-02-26 2023-05-02 Ford Global Technologies, Llc Vehicle planned path signal
US11195033B2 (en) * 2020-02-27 2021-12-07 Gm Cruise Holdings Llc Multi-modal, multi-technique vehicle signal detection
JP7383532B2 (ja) * 2020-03-12 2023-11-20 本田技研工業株式会社 制御装置及び車両
CN111352426B (zh) * 2020-03-17 2021-03-02 广西柳工机械股份有限公司 一种车辆避障方法、车辆避障装置、车辆避障系统和车辆
US11097735B1 (en) 2020-03-19 2021-08-24 Toyota Motor North America, Inc. Transport lane usage
US11488424B2 (en) 2020-03-19 2022-11-01 Toyota Motor North America, Inc. Motion-based transport assessment
US11720114B2 (en) 2020-03-19 2023-08-08 Toyota Motor North America, Inc. Safety of transport maneuvering
JP7115502B2 (ja) 2020-03-23 2022-08-09 トヨタ自動車株式会社 物体状態識別装置、物体状態識別方法及び物体状態識別用コンピュータプログラムならびに制御装置
DE102020107880A1 (de) * 2020-03-23 2021-09-23 Ford Global Technologies, Llc Verfahren zum Steuern eines Geschwindigkeitsregelsystems in einem Kurvenverlauf
WO2021192521A1 (ja) * 2020-03-27 2021-09-30 パイオニア株式会社 情報提供装置、情報提供方法及び情報提供用プログラム
JP7359735B2 (ja) * 2020-04-06 2023-10-11 トヨタ自動車株式会社 物体状態識別装置、物体状態識別方法及び物体状態識別用コンピュータプログラムならびに制御装置
JP7388971B2 (ja) 2020-04-06 2023-11-29 トヨタ自動車株式会社 車両制御装置、車両制御方法及び車両制御用コンピュータプログラム
EP3893150A1 (en) 2020-04-09 2021-10-13 Tusimple, Inc. Camera pose estimation techniques
CN111497842B (zh) * 2020-04-30 2023-03-24 重庆大学 一种人机双闭环分层协同纵向跟车控制方法
US11145202B1 (en) 2020-05-01 2021-10-12 United Services Automobile Association (Usaa) Systems and methods for providing warnings of imminent hazards
CN111597986B (zh) * 2020-05-15 2023-09-29 北京百度网讯科技有限公司 用于生成信息的方法、装置、设备和存储介质
CN111580522A (zh) * 2020-05-15 2020-08-25 东风柳州汽车有限公司 无人驾驶汽车的控制方法、汽车和存储介质
US11551429B2 (en) 2020-06-05 2023-01-10 Uatc, Llc Photorealistic image simulation with geometry-aware composition
GB2595856A (en) * 2020-06-08 2021-12-15 Daimler Ag A method for determining a trajectory of an autonomous motor vehicle, as well as an assistance system
US20210389138A1 (en) * 2020-06-15 2021-12-16 Google Llc Vehicle Communication System for Optimizing Traffic Flow
CN111785045B (zh) * 2020-06-17 2022-07-05 南京理工大学 基于演员-评论家算法的分布式交通信号灯联合控制方法
US20210394756A1 (en) * 2020-06-18 2021-12-23 GM Global Technology Operations LLC System and method for predictive vehicle launch
CN111832179B (zh) * 2020-07-17 2023-08-15 北京赛目科技有限公司 无人车的测试场景创建方法及装置
US11644835B2 (en) 2020-07-29 2023-05-09 Toyota Research Institute, Inc. Game-theoretic planning for risk-aware interactive agents
US11396305B2 (en) 2020-07-30 2022-07-26 Toyota Research Institute, Inc. Systems and methods for improving driver warnings during automated driving
KR20220017228A (ko) * 2020-08-04 2022-02-11 현대자동차주식회사 차량 주행 제어 장치 및 방법
US11608067B2 (en) * 2020-08-12 2023-03-21 Honda Motor Co., Ltd. Probabilistic-based lane-change decision making and motion planning system and method thereof
US11501538B2 (en) * 2020-08-24 2022-11-15 Verizon Connect Development Limited Systems and methods for detecting vehicle tailgating
US11726471B2 (en) 2020-08-27 2023-08-15 Waymo Llc Methods and systems for gradually adjusting vehicle sensor perspective using remote assistance
CN112232111B (zh) * 2020-09-01 2024-04-26 杭州鸿泉物联网技术股份有限公司 商砼车搅拌筒转向监测方法、系统、电子设备与存储介质
KR102551283B1 (ko) * 2020-09-08 2023-07-06 한국전자통신연구원 메타인지 기반 자율주행 보정 장치 및 방법
KR20220036423A (ko) * 2020-09-15 2022-03-23 현대자동차주식회사 차량 및 그를 위한 자율주행 제어방법
US11597388B2 (en) * 2020-09-24 2023-03-07 Toyota Motor Engineering & Manufacturing North America, Inc. System and method for connected vehicle lane merge
DE102020212565A1 (de) * 2020-10-06 2022-04-07 Volkswagen Aktiengesellschaft Fahrzeug, Vorrichtung, Computerprogramm und Verfahren zur Durchführung in einem Fahrzeug
US11725950B2 (en) * 2020-10-24 2023-08-15 International Business Machines Corporation Substitute autonomous vehicle data
KR20220056922A (ko) * 2020-10-28 2022-05-09 현대자동차주식회사 자율주행 제어 장치 및 방법
WO2022089817A1 (de) * 2020-11-02 2022-05-05 Mercedes-Benz Group AG Verfahren zur steuerung eines automatisiert fahrenden fahrzeuges
CN114527737B (zh) * 2020-11-06 2024-08-02 陕西世纪华耀科技有限公司 用于自动驾驶的速度规划方法、装置、设备、介质和车辆
CN112614382B (zh) * 2020-11-11 2022-03-04 山东卓智软件股份有限公司 相对距离智能化调节系统
US11461992B2 (en) * 2020-11-12 2022-10-04 Samsung Electronics Co., Ltd. Region of interest selection for object detection
CN112498351B (zh) * 2020-11-20 2021-11-23 东风汽车集团有限公司 一种基于v2v的自动驾驶优化系统及方法
KR102509622B1 (ko) * 2020-11-23 2023-03-13 한양대학교 산학협력단 자동주차 시스템 안정성을 보장하는 근사 클로소이드 기반 로컬 경로 생성 방법 및 장치
CN112560609B (zh) * 2020-12-03 2022-11-15 北京百度网讯科技有限公司 路况预估方法、建立路况预估模型的方法及对应装置
CN112590791B (zh) * 2020-12-16 2022-03-11 东南大学 一种基于博弈论的智能车换道间隙选择方法及装置
US11776281B2 (en) 2020-12-22 2023-10-03 Toyota Research Institute, Inc. Systems and methods for traffic light detection and classification
CN114633749B (zh) * 2021-01-11 2024-10-15 广东科学技术职业学院 一种无人驾驶车辆
CN112706783B (zh) * 2021-01-12 2022-06-28 重庆大学 一种基于状态流的自动驾驶汽车纵向速度控制方法
US11834042B2 (en) * 2021-01-14 2023-12-05 GM Global Technology Operations LLC Methods, systems, and apparatuses for behavioral based adaptive cruise control (ACC) to driver's vehicle operation style
CN116783106A (zh) * 2021-01-22 2023-09-19 株式会社电装 处理方法、处理系统、处理程序、处理装置
JP2022125580A (ja) * 2021-02-17 2022-08-29 トヨタ自動車株式会社 衝突回避支援装置
CN113022555B (zh) * 2021-03-01 2023-01-20 重庆兰德适普信息科技有限公司 一种速差滑移转向车辆的目标跟随控制方法和装置
US12014549B2 (en) 2021-03-04 2024-06-18 Toyota Research Institute, Inc. Systems and methods for vehicle light signal classification
CN112918481A (zh) * 2021-03-25 2021-06-08 蔚来汽车科技(安徽)有限公司 确定驾驶参数的方法及车辆控制装置
JP2022154193A (ja) * 2021-03-30 2022-10-13 本田技研工業株式会社 学習装置、学習方法、プログラム、および物体検知装置
US11810289B2 (en) 2021-03-31 2023-11-07 Caterpillar Inc. Estimating the moving state of rotating machines systems and methods
CN112937588B (zh) * 2021-04-01 2022-03-25 吉林大学 一种冰雪车辙路况的车辆稳定性分析方法
JP7505442B2 (ja) * 2021-04-27 2024-06-25 トヨタ自動車株式会社 車両
US20230020503A1 (en) * 2021-07-08 2023-01-19 Ford Global Technologies, Llc Machine control
CN113415274B (zh) * 2021-07-14 2022-07-05 重庆长安汽车股份有限公司 自动驾驶的跟车轨迹规划系统、方法、车辆及存储介质
US11724739B2 (en) * 2021-07-22 2023-08-15 GM Global Technology Operations LLC Vehicle actuation commands to affect transient handling
EP4381490A1 (en) * 2021-08-02 2024-06-12 Mobileye Vision Technologies Ltd. Vulnerable road user (vru) collision avoidance system
CN113625718B (zh) * 2021-08-12 2023-07-21 上汽大众汽车有限公司 车辆的行驶路径规划方法
KR102624143B1 (ko) * 2021-09-24 2024-01-12 (주) 오토노머스에이투지 교차로에 설치된 라이다를 이용하여 신호등을 제어하기 위한 방법 및 이를 이용한 서버
DE102021125525A1 (de) * 2021-10-01 2023-04-06 Deere & Company Verfahren zur Ausgabe von Kollisionswarnungen für ein land-wirtschaftliches Fahrzeuggespann
US11760368B2 (en) * 2021-10-19 2023-09-19 Cyngn, Inc. System and method of same-loop adaptive simulation for autonomous driving
US20230127465A1 (en) * 2021-10-26 2023-04-27 Ford Global Technologies, Llc System and method for approaching vehicle detection
US11938968B2 (en) 2021-11-10 2024-03-26 Robert Bosch Gmbh Trajectory design for image data acquisition for object detection/recognition
WO2023090166A1 (ja) * 2021-11-22 2023-05-25 株式会社デンソー 車両用制御装置及び車両用制御方法
CN114489038B (zh) * 2021-12-08 2024-02-27 农芯(南京)智慧农业研究院有限公司 一种基于强化学习的农林用车辆的导航控制方法
CN114291114B (zh) * 2022-01-05 2024-06-18 天地科技股份有限公司 车辆控制系统及方法
US12112551B2 (en) 2022-02-09 2024-10-08 Toyota Research Institute, Inc. Vehicles, systems and methods for automatically detecting a state of signal lights of a vehicle
CN114550297B (zh) * 2022-02-25 2022-09-27 北京拙河科技有限公司 一种行人的意图分析方法及系统
JP7519397B2 (ja) 2022-03-30 2024-07-19 本田技研工業株式会社 制御装置、制御装置の動作方法、プログラム及び記憶媒体
CN114596470B (zh) * 2022-03-31 2024-06-25 广州文远知行科技有限公司 一种并道危险场景分类系统、方法、设备和介质
US20230322208A1 (en) * 2022-04-06 2023-10-12 Mobileye Vision Technologies Ltd. Steering limiters for vehicle navigation
US12008681B2 (en) * 2022-04-07 2024-06-11 Gm Technology Operations Llc Systems and methods for testing vehicle systems
US20230341234A1 (en) * 2022-04-20 2023-10-26 Nvidia Corporation Lane planning architecture for autonomous machine systems and applications
US12080161B2 (en) * 2022-04-28 2024-09-03 Toyota Research Institute, Inc. Traffic signal understandings and representation for prediction, planning, and control
WO2023212338A1 (en) * 2022-04-29 2023-11-02 Apple Inc. Systems and methods for movement control in multi-device environments
CN115100540B (zh) * 2022-06-30 2024-05-07 电子科技大学 一种高分辨率遥感影像道路自动提取的方法
US20240010203A1 (en) * 2022-07-08 2024-01-11 Toyota Motor Engineering & Manufacturing North America, Inc. Systems, methods, and vehicles for classifying driving behavior of a target vehicle
WO2024012660A1 (en) * 2022-07-12 2024-01-18 Volvo Autonomous Solutions AB A computer-implemented method for determining a speed profile along a predetermined travelling path for an autonomous vehicle
WO2024108123A1 (en) * 2022-11-18 2024-05-23 Cornell University Lane-change timing determinations in autonomous vehicle routing
CN115716447A (zh) * 2022-11-30 2023-02-28 北京百度网讯科技有限公司 自动调节后视镜的方法、装置及自动驾驶车辆
CN116028882B (zh) * 2023-03-29 2023-06-02 深圳市傲天科技股份有限公司 用户标注和分类方法、装置、设备及存储介质
CN117349884B (zh) * 2023-10-10 2024-06-07 耀维(深圳)科技有限公司 智能机器人应用管理系统
CN117911988A (zh) * 2024-02-06 2024-04-19 苏州市欧冶半导体有限公司 用于辅助驾驶的目标检测方法、装置和计算机设备
CN117994985B (zh) * 2024-04-03 2024-06-07 华东交通大学 一种基于混驾环境的智能汽车行驶规划系统

Family Cites Families (160)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3104533B2 (ja) * 1993-12-02 2000-10-30 トヨタ自動車株式会社 車載用の物体検出装置
US5955945A (en) * 1995-07-10 1999-09-21 Fuhrer; Kenneth Fail safe system for providing warning signals upon the failure of motorcycle brake or tail lights
JPH11210513A (ja) * 1998-01-21 1999-08-03 Honda Motor Co Ltd 車両の駆動力制御装置
JP3805923B2 (ja) * 1999-04-28 2006-08-09 本田技研工業株式会社 車両通信装置
US6122593A (en) * 1999-08-03 2000-09-19 Navigation Technologies Corporation Method and system for providing a preview of a route calculated with a navigation system
AU2002225741A1 (en) * 2000-11-06 2002-05-15 Cathy D. Santa Cruz Method and apparatus used for installation and operation of a front vehicle brake light
US20030128112A1 (en) * 2002-01-09 2003-07-10 Cho-Ki Chow Wireless speed indicating system of automobile
EP1504276B1 (en) * 2002-05-03 2012-08-08 Donnelly Corporation Object detection system for vehicle
US6778897B2 (en) * 2002-11-27 2004-08-17 Visteon Global Technologies, Inc. Adaptive cruise control system and strategy
US7774137B2 (en) * 2003-06-24 2010-08-10 Steve Thorne Speed-monitoring radar-activated brake light
JP3925474B2 (ja) * 2003-07-18 2007-06-06 日産自動車株式会社 車線変更支援装置
JP2005115484A (ja) * 2003-09-17 2005-04-28 Fujitsu Ten Ltd 運転支援装置
ATE396470T1 (de) 2004-04-08 2008-06-15 Mobileye Technologies Ltd Kollisionswarnsystem
DE102004031933A1 (de) * 2004-06-27 2006-02-09 Stiftung Alfred-Wegener-Institut Für Polar- Und Meeresforschung Rechnergestütztes Planungsverfahren für einen Reiseplan
JP2006251888A (ja) * 2005-03-08 2006-09-21 Denso Corp 車両用運転支援装置及び車両用ナビゲーション装置
JP2006260217A (ja) * 2005-03-17 2006-09-28 Advics:Kk 車両用走行支援装置
DE102005062275A1 (de) * 2005-12-24 2007-06-28 Daimlerchrysler Ag Verfahren zur Erkennung eines drohenden Heckaufpralls
JP4400584B2 (ja) * 2006-03-01 2010-01-20 トヨタ自動車株式会社 障害物検出方法及び障害物検出装置
EP1862988B1 (en) * 2006-05-30 2009-11-04 Mazda Motor Corporation A driving assist for a vehicle
JP4914234B2 (ja) * 2007-01-31 2012-04-11 富士重工業株式会社 先行車両検出装置
JP4900104B2 (ja) * 2007-07-18 2012-03-21 船井電機株式会社 ナビゲーション装置
TWI314115B (en) * 2007-09-27 2009-09-01 Ind Tech Res Inst Method and apparatus for predicting/alarming the moving of hidden objects
JP2009116692A (ja) * 2007-11-07 2009-05-28 Toyota Motor Corp 走行支援装置
DE102008011228A1 (de) * 2008-02-26 2009-08-27 Robert Bosch Gmbh Verfahren zur Unterstützung eines Nutzers eines Fahrzeugs, Steuereinrichtung für ein Fahrerassistenzsystem eines Fahrzeugs und Fahrzeug mit einer derartigen Steuereinrichtung
JP5345350B2 (ja) * 2008-07-30 2013-11-20 富士重工業株式会社 車両の運転支援装置
JP4957747B2 (ja) * 2009-05-18 2012-06-20 トヨタ自動車株式会社 車両環境推定装置
JP5441549B2 (ja) * 2009-07-29 2014-03-12 日立オートモティブシステムズ株式会社 道路形状認識装置
JP2011107088A (ja) * 2009-11-20 2011-06-02 Alpine Electronics Inc ナビゲーション装置およびその案内表示方法
JP5381665B2 (ja) * 2009-12-02 2014-01-08 トヨタ自動車株式会社 車両制御装置
JP5609604B2 (ja) * 2009-12-11 2014-10-22 株式会社デンソー ナビゲーション装置
JP5545022B2 (ja) * 2010-05-14 2014-07-09 トヨタ自動車株式会社 障害物認識装置
SG10201505499PA (en) * 2010-07-16 2015-08-28 Univ Carnegie Mellon Methods and systems for coordinating vehicular traffic using in-vehicle virtual traffic control signals enabled by vehicle-to-vehicle communications
JP5475138B2 (ja) * 2010-09-08 2014-04-16 トヨタ自動車株式会社 移動物予測装置、仮想可動物予測装置、プログラム、移動物予測方法、及び仮想可動物予測方法
DE102010040803A1 (de) * 2010-09-15 2012-03-15 Continental Teves Ag & Co. Ohg Visuelles Fahrerinformations- und Warnsystem für einen Fahrer eines Kraftfahrzeugs
JP5583540B2 (ja) * 2010-10-01 2014-09-03 パナソニック株式会社 事故要因領域特定装置および事故要因領域特定プログラム
US8509982B2 (en) * 2010-10-05 2013-08-13 Google Inc. Zone driving
DE102010052406A1 (de) * 2010-11-24 2011-07-07 Daimler AG, 70327 Verfahren zur Vermeidung oder Verminderung von Fahrzeugkollisionen
JP5189157B2 (ja) * 2010-11-30 2013-04-24 株式会社豊田中央研究所 可動物の目標状態決定装置及びプログラム
JP5766941B2 (ja) * 2010-12-01 2015-08-19 トヨタ自動車株式会社 走行支援装置
DE102011012793B4 (de) * 2011-03-02 2023-05-04 Volkswagen Ag Fahrerassistenzverfahren und Fahrerassistenzsystem
JP5754509B2 (ja) * 2011-08-10 2015-07-29 トヨタ自動車株式会社 運転支援装置
US20130057397A1 (en) * 2011-09-01 2013-03-07 GM Global Technology Operations LLC Method of operating a vehicle safety system
DE102011116169A1 (de) * 2011-10-14 2013-04-18 Continental Teves Ag & Co. Ohg Vorrichtung zur Unterstützung eines Fahrers beim Fahren eines Fahrzeugs oder zum autonomen Fahren eines Fahrzeugs
US8854223B2 (en) * 2012-01-18 2014-10-07 Xerox Corporation Image-based determination of CO and CO2 concentrations in vehicle exhaust gas emissions
JP5863481B2 (ja) * 2012-01-30 2016-02-16 日立マクセル株式会社 車両用衝突危険予測装置
US9020760B2 (en) * 2012-02-08 2015-04-28 Telogis, Inc. System for classifying streets for vehicle navigation
US8731742B2 (en) * 2012-04-05 2014-05-20 GM Global Technology Operations LLC Target vehicle movement classification
US20130278441A1 (en) * 2012-04-24 2013-10-24 Zetta Research and Development, LLC - ForC Series Vehicle proxying
US8504233B1 (en) * 2012-04-27 2013-08-06 Google Inc. Safely navigating on roads through maintaining safe distance from other vehicles
JP6024229B2 (ja) * 2012-06-14 2016-11-09 富士通株式会社 監視装置、監視方法、及びプログラム
JP6163718B2 (ja) * 2012-08-30 2017-07-19 トヨタ自動車株式会社 車両制御装置
JP6065201B2 (ja) * 2012-10-11 2017-01-25 サクサ株式会社 撮影装置及び渋滞判定システム
US8825258B2 (en) * 2012-11-30 2014-09-02 Google Inc. Engaging and disengaging for autonomous driving
CN103903478A (zh) * 2012-12-29 2014-07-02 富泰华工业（深圳）有限公司 行车预警系统
US8788134B1 (en) * 2013-01-04 2014-07-22 GM Global Technology Operations LLC Autonomous driving merge management system
US9092986B2 (en) * 2013-02-04 2015-07-28 Magna Electronics Inc. Vehicular vision system
GB2511750B (en) * 2013-03-11 2015-07-29 Jaguar Land Rover Ltd A driving assistance system, vehicle and method
WO2014152554A1 (en) * 2013-03-15 2014-09-25 Caliper Corporation Lane-level vehicle navigation for vehicle routing and traffic management
US9254846B2 (en) * 2013-05-03 2016-02-09 Google Inc. Predictive reasoning for controlling speed of a vehicle
US9260095B2 (en) * 2013-06-19 2016-02-16 Magna Electronics Inc. Vehicle vision system with collision mitigation
CN104422462A (zh) * 2013-09-06 2015-03-18 上海博泰悦臻电子设备制造有限公司 一种车辆导航的方法、装置
EP2848487B1 (en) * 2013-09-12 2020-03-18 Volvo Car Corporation Manoeuvre generation for automated drive
US9738280B2 (en) * 2013-10-03 2017-08-22 Robert Bosch Gmbh Adaptive cruise control with on-ramp detection
JP6138655B2 (ja) * 2013-10-10 2017-05-31 日立オートモティブシステムズ株式会社 車両の運動制御装置
US20150120244A1 (en) * 2013-10-31 2015-04-30 Here Global B.V. Method and apparatus for road width estimation
US9090260B2 (en) * 2013-12-04 2015-07-28 Mobileye Vision Technologies Ltd. Image-based velocity control for a turning vehicle
WO2015088522A1 (en) 2013-12-11 2015-06-18 Intel Corporation Individual driving preference adapted computerized assist or autonomous driving of vehicles
US9988047B2 (en) * 2013-12-12 2018-06-05 Magna Electronics Inc. Vehicle control system with traffic driving control
KR101500238B1 (ko) * 2013-12-23 2015-03-06 현대자동차주식회사 차량용 헤드업 디스플레이 조명 표시 방법
KR101541483B1 (ko) * 2014-01-03 2015-08-03 현대모비스(주) 차선 변경 감시 장치 및 그 제어 방법
JP6331402B2 (ja) * 2014-01-14 2018-05-30 株式会社デンソー 移動体検出装置および移動体検出方法
US9809219B2 (en) * 2014-01-29 2017-11-07 Continental Automotive Systems, Inc. System for accommodating a pedestrian during autonomous vehicle operation
US9365214B2 (en) * 2014-01-30 2016-06-14 Mobileye Vision Technologies Ltd. Systems and methods for determining the status of a turn lane traffic light
JP6281483B2 (ja) * 2014-04-17 2018-02-21 株式会社デンソー 故障検出システム、情報処理装置、及び車両搭載装置
EP2942765B1 (en) * 2014-05-07 2018-12-26 Honda Research Institute Europe GmbH Method and system for predictive lane change assistance, program software product and vehicle
KR20150137799A (ko) * 2014-05-30 2015-12-09 엘지전자 주식회사 이동 단말기 및 그 제어 방법
JP6331858B2 (ja) * 2014-08-07 2018-05-30 日産自動車株式会社 先行車追越支援装置
US9796326B2 (en) * 2014-08-08 2017-10-24 GM Global Technology Operations LLC Systems and methods for vehicle hazard light control with selectable lighting patterns
WO2016027270A1 (en) * 2014-08-18 2016-02-25 Mobileye Vision Technologies Ltd. Recognition and prediction of lane constraints and construction areas in navigation
US9229453B1 (en) * 2014-08-29 2016-01-05 GM Global Technology Operations LLC Unified motion planner for autonomous driving vehicle in avoiding the moving obstacle
KR102326062B1 (ko) * 2014-11-12 2021-11-12 현대모비스 주식회사 자율주행차량의 장애물 회피 시스템 및 방법
JP6156333B2 (ja) * 2014-11-19 2017-07-05 トヨタ自動車株式会社 自動運転車両システム
US9534910B2 (en) * 2014-12-09 2017-01-03 Toyota Motor Engineering & Manufacturing North America, Inc. Autonomous vehicle detection of and response to yield scenarios
US9528838B2 (en) * 2014-12-09 2016-12-27 Toyota Motor Engineering & Manufacturing North America, Inc. Autonomous vehicle detection of and response to intersection priority
JP6470039B2 (ja) 2014-12-26 2019-02-13 日立オートモティブシステムズ株式会社 車両制御システム
US9406234B2 (en) * 2015-01-02 2016-08-02 Atieva, Inc. Automatically activated blind spot camera system
US10395541B2 (en) * 2015-01-16 2019-08-27 Texas Instruments Incorporated Integrated fault-tolerant augmented area viewing system
JP2016142612A (ja) * 2015-02-02 2016-08-08 日立オートモティブシステムズ株式会社 車両制御装置、距離算出装置および距離算出方法
US20160231746A1 (en) * 2015-02-06 2016-08-11 Delphi Technologies, Inc. System And Method To Operate An Automated Vehicle
KR102534792B1 (ko) * 2015-02-10 2023-05-19 모빌아이 비젼 테크놀로지스 엘티디. 자율 주행을 위한 약도
KR102034722B1 (ko) * 2015-03-19 2019-10-21 현대자동차주식회사 차량, 차량의 통신 방법 및 차량에 포함된 무선 통신 장치
KR20160112552A (ko) * 2015-03-19 2016-09-28 현대자동차주식회사 차량, 차량의 통신 방법 및 차량에 포함된 무선 통신 장치
JP6237694B2 (ja) * 2015-04-28 2017-11-29 トヨタ自動車株式会社 走行制御装置
CN104776854B (zh) * 2015-04-30 2018-01-23 上海卓易科技股份有限公司 跟车导航方法及系统、导航系统
EP3091370B1 (en) * 2015-05-05 2021-01-06 Volvo Car Corporation Method and arrangement for determining safe vehicle trajectories
KR102366402B1 (ko) * 2015-05-21 2022-02-22 엘지전자 주식회사 운전자 보조 장치 및 그 제어방법
KR101843773B1 (ko) * 2015-06-30 2018-05-14 엘지전자 주식회사 차량 운전 보조 장치, 차량용 디스플레이 장치 및 차량
US9511767B1 (en) * 2015-07-01 2016-12-06 Toyota Motor Engineering & Manufacturing North America, Inc. Autonomous vehicle action planning using behavior prediction
US10421491B2 (en) * 2015-07-31 2019-09-24 Hitachi Automotive Systems, Ltd. Vehicular steering assistance control device
US9550528B1 (en) * 2015-09-14 2017-01-24 Ford Global Technologies, Llc Lane change negotiation
CN105679090B (zh) * 2015-10-21 2017-11-28 天津师范大学 一种基于智能手机的夜间司机驾驶辅助方法
US10800455B2 (en) * 2015-12-17 2020-10-13 Ford Global Technologies, Llc Vehicle turn signal detection
US20170190286A1 (en) * 2016-01-03 2017-07-06 Edward Yavitz GPS Vehicle Speed and Velocity Change Indicator
CN108431549B (zh) * 2016-01-05 2020-09-04 御眼视觉技术有限公司 具有施加的约束的经训练的系统
JP6597344B2 (ja) 2016-01-29 2019-10-30 トヨタ自動車株式会社 車両制御装置
JP2019059245A (ja) 2016-02-05 2019-04-18 マクセル株式会社 ヘッドアップディスプレイ装置及びその表示制御方法
EP3208786B1 (en) * 2016-02-22 2023-06-07 Volvo Car Corporation Method and system for evaluating inter-vehicle traffic gaps and time instances to perform a lane change manoeuvre
JP6272559B1 (ja) * 2016-02-25 2018-01-31 株式会社日立製作所 移動体の制御方法、移動体及び移動体の制御システム
US10160437B2 (en) * 2016-02-29 2018-12-25 Magna Electronics Inc. Vehicle control system with reverse assist
DE102016002927A1 (de) * 2016-03-10 2016-10-06 Daimler Ag Verfahren zumindest zur Verringerung einer Kollisionsschwere für ein Fahrzeug
JP6380766B2 (ja) * 2016-03-14 2018-08-29 本田技研工業株式会社 車両制御装置、車両制御方法、および車両制御プログラム
JP6270227B2 (ja) * 2016-03-14 2018-01-31 本田技研工業株式会社 車両制御装置、車両制御方法、および車両制御プログラム
US9857795B2 (en) * 2016-03-24 2018-01-02 Honda Motor Co., Ltd. System and method for trajectory planning for unexpected pedestrians
CN109074733A (zh) * 2016-04-28 2018-12-21 本田技研工业株式会社 车辆控制系统、车辆控制方法及车辆控制程序
KR101795249B1 (ko) * 2016-05-02 2017-11-07 현대자동차주식회사 차량 및 그것의 주행 안전 지원 방법
US20170329332A1 (en) * 2016-05-10 2017-11-16 Uber Technologies, Inc. Control system to adjust operation of an autonomous vehicle based on a probability of interference by a dynamic object
US20170329346A1 (en) * 2016-05-12 2017-11-16 Magna Electronics Inc. Vehicle autonomous parking system
WO2018005441A2 (en) * 2016-06-27 2018-01-04 Mobileye Vision Technologies Ltd. Controlling host vehicle based on detected parked vehicle characteristics
JP6380919B2 (ja) * 2016-09-01 2018-08-29 マツダ株式会社 車両制御装置
JP6680170B2 (ja) * 2016-09-30 2020-04-15 株式会社デンソー 運転支援装置及び運転支援方法
EP3496033A4 (en) * 2016-10-07 2019-10-23 Aisin Aw Co., Ltd. DISPLACEMENT ASSISTING DEVICE AND COMPUTER PROGRAM
US10515390B2 (en) * 2016-11-21 2019-12-24 Nio Usa, Inc. Method and system for data optimization
JP6916609B2 (ja) * 2016-11-21 2021-08-11 パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカＰａｎａｓｏｎｉｃ Ｉｎｔｅｌｌｅｃｔｕａｌ Ｐｒｏｐｅｒｔｙ Ｃｏｒｐｏｒａｔｉｏｎ ｏｆ Ａｍｅｒｉｃａ 交差点情報配信装置及び交差点情報配信方法
JP6536554B2 (ja) * 2016-12-13 2019-07-03 トヨタ自動車株式会社 ウィンカ判定装置及び自動運転システム
KR102383427B1 (ko) * 2016-12-16 2022-04-07 현대자동차주식회사 자율주행 제어 장치 및 방법
JP6478415B2 (ja) * 2016-12-20 2019-03-06 本田技研工業株式会社 車両制御システム、車両制御方法、および車両制御プログラム
KR102535540B1 (ko) * 2017-01-12 2023-05-23 모빌아이 비젼 테크놀로지스 엘티디. 차량 움직임에 기반한 항법
US10453344B2 (en) * 2017-02-16 2019-10-22 Panasonic Intellectual Corporation Of America Information processing apparatus and non-transitory recording medium
KR102646644B1 (ko) * 2017-03-01 2024-03-13 모빌아이 비젼 테크놀로지스 엘티디. 감지 불확실성이 있는 항법을 위한 시스템 및 방법
US10133275B1 (en) * 2017-03-01 2018-11-20 Zoox, Inc. Trajectory generation using temporal logic and tree search
JP6935813B2 (ja) * 2017-03-02 2021-09-22 日産自動車株式会社 運転支援方法及び運転支援装置
JP2018151858A (ja) * 2017-03-13 2018-09-27 株式会社デンソーテン 車載機器、駐車管理装置、駐車管理システム、出庫準備方法、及び駐車管理方法
CN110520916A (zh) * 2017-04-19 2019-11-29 日产自动车株式会社 行驶辅助方法及行驶辅助装置
US20180307245A1 (en) * 2017-05-31 2018-10-25 Muhammad Zain Khawaja Autonomous Vehicle Corridor
WO2019008716A1 (ja) * 2017-07-06 2019-01-10 マクセル株式会社 可視外計測装置および可視外計測方法
US10620638B2 (en) * 2017-08-18 2020-04-14 Wipro Limited Method, system, and device for guiding autonomous vehicles based on dynamic extraction of road region
US10788585B2 (en) * 2017-09-15 2020-09-29 Toyota Research Institute, Inc. System and method for object detection using a probabilistic observation model
US11787287B2 (en) * 2017-11-17 2023-10-17 Aisin Corporation Vehicle drive assist system, vehicle drive assist method, and vehicle drive assist program
US20190278294A1 (en) * 2018-03-07 2019-09-12 Casio Computer Co., Ltd. Autonomous mobile apparatus, autonomous move method, and recording medium
KR102423172B1 (ko) * 2018-03-20 2022-07-22 모빌아이 비젼 테크놀로지스 엘티디 차량의 항법을 위한 시스템 및 방법
US10895468B2 (en) * 2018-04-10 2021-01-19 Toyota Jidosha Kabushiki Kaisha Dynamic lane-level vehicle navigation with lane group identification
US10642275B2 (en) * 2018-06-18 2020-05-05 Zoox, Inc. Occulsion aware planning and control
RU2768091C1 (ru) * 2018-07-12 2022-03-23 Ниссан Мотор Ко., Лтд. Способ помощи при вождении и устройство помощи при вождении
US11724691B2 (en) * 2018-09-15 2023-08-15 Toyota Research Institute, Inc. Systems and methods for estimating the risk associated with a vehicular maneuver
JP7067400B2 (ja) * 2018-10-05 2022-05-16 オムロン株式会社 検知装置、移動体システム、及び検知方法
US10627819B1 (en) * 2018-10-11 2020-04-21 Pony Ai Inc. On-site notification from autonomous vehicle for traffic safety
JP6958537B2 (ja) * 2018-12-20 2021-11-02 オムロン株式会社 検知装置、移動体システム、及び検知方法
US11188082B2 (en) * 2019-01-11 2021-11-30 Zoox, Inc. Occlusion prediction and trajectory evaluation
JP7275623B2 (ja) * 2019-02-12 2023-05-18 株式会社デンソー 運転支援装置
US11016492B2 (en) * 2019-02-28 2021-05-25 Zoox, Inc. Determining occupancy of occluded regions
JP7199269B2 (ja) * 2019-03-20 2023-01-05 日立Astemo株式会社 外界センシング情報処理装置
DE112020002666T5 (de) * 2019-06-06 2022-05-12 Mobileye Vision Technologies Ltd. Systeme und verfahren für die fahrzeugnavigation
US20210031760A1 (en) * 2019-07-31 2021-02-04 Nissan North America, Inc. Contingency Planning and Safety Assurance
US11403943B2 (en) * 2020-07-14 2022-08-02 Argo AI, LLC Method and system for vehicle navigation using information from smart node
US11473917B2 (en) * 2020-07-14 2022-10-18 Argo AI, LLC System for augmenting autonomous vehicle perception using smart nodes
US12071156B2 (en) * 2020-09-29 2024-08-27 Waymo Llc Planning for occlusions with surfel maps
US11295147B1 (en) * 2020-11-27 2022-04-05 HCL Technologies Italy S.p.A. Method and system for detecting and managing obfuscation of a road sign
US20220185267A1 (en) * 2020-12-16 2022-06-16 Zoox, Inc. Object determination in an occluded region
CN114643996A (zh) * 2020-12-19 2022-06-21 荷兰移动驱动器公司 辅助驾驶方法以及车辆
JP2022128712A (ja) * 2021-02-24 2022-09-05 本田技研工業株式会社 道路情報生成装置

Cited By (44)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11135719B2 (en) * 2015-09-21 2021-10-05 Rainbow Robotics Real-time control system, real-time control device and system control method
US11500380B2 (en) 2017-02-10 2022-11-15 Nissan North America, Inc. Autonomous vehicle operational management including operating a partially observable Markov decision process model instance
US11113973B2 (en) * 2017-02-10 2021-09-07 Nissan North America, Inc. Autonomous vehicle operational management blocking monitoring
US10836405B2 (en) 2017-10-30 2020-11-17 Nissan North America, Inc. Continual planning and metareasoning for controlling an autonomous vehicle
US11027751B2 (en) 2017-10-31 2021-06-08 Nissan North America, Inc. Reinforcement and model learning for vehicle operation
US11702070B2 (en) 2017-10-31 2023-07-18 Nissan North America, Inc. Autonomous vehicle operation with explicit occlusion reasoning
US11084504B2 (en) * 2017-11-30 2021-08-10 Nissan North America, Inc. Autonomous vehicle operational management scenarios
US11874120B2 (en) 2017-12-22 2024-01-16 Nissan North America, Inc. Shared autonomous vehicle operational management
US11110941B2 (en) 2018-02-26 2021-09-07 Renault S.A.S. Centralized shared autonomous vehicle operational management
US11492837B2 (en) * 2018-03-29 2022-11-08 Toyoda Gosei Co., Ltd. Vehicle door opening/closing device
US20200386031A1 (en) * 2018-03-29 2020-12-10 Toyoda Gosei Co., Ltd. Vehicle door opening/closing device
US11400935B2 (en) * 2018-04-23 2022-08-02 Renault S.A.S. Method for a motor vehicle to select a preferred traffic lane to cross a toll area
US10816968B2 (en) * 2018-05-08 2020-10-27 GM Global Technology Operations LLC System and method for access to restricted areas by an autonomous vehicle
US11510404B2 (en) * 2018-05-24 2022-11-29 Blue River Technology Inc. Boom sprayer including machine feedback control
US11120688B2 (en) 2018-06-29 2021-09-14 Nissan North America, Inc. Orientation-adjust actions for autonomous vehicle operational management
US11647685B2 (en) * 2018-07-12 2023-05-16 Raven Industries, Inc. Implement position control system and method for same
US10752258B2 (en) * 2018-09-17 2020-08-25 GM Global Technology Operations LLC Apparatus and method for audible driver confirmation for maneuvers in an autonomous vehicle
US11295609B1 (en) 2018-12-06 2022-04-05 Nissan Motor Co., Ltd. Travel assistance method and travel assistance device
US20220392232A1 (en) * 2018-12-10 2022-12-08 Motional Ad Llc Systems and methods for validating sensor calibration
US11443524B2 (en) * 2018-12-10 2022-09-13 Motional Ad Llc Systems and methods for validating sensor calibration
US12067786B2 (en) * 2018-12-10 2024-08-20 Motional Ad Llc Systems and methods for validating sensor calibration
US11209822B2 (en) * 2019-06-28 2021-12-28 Zoox, Inc. Techniques for contacting a teleoperator
US11275370B2 (en) 2019-06-28 2022-03-15 Zoox, Inc. Techniques for navigating vehicles using teleoperator instructions
US12110012B2 (en) 2019-07-26 2024-10-08 Denso Corporation Vehicle control apparatus and vehicle control method
US20210101625A1 (en) * 2019-10-08 2021-04-08 Motional Ad Llc Navigating multi-way stop intersections with an autonomous vehicle
US11834045B2 (en) 2019-10-08 2023-12-05 Motional Ad Llc Navigating multi-way stop intersections with an autonomous vehicle
US11899454B2 (en) 2019-11-26 2024-02-13 Nissan North America, Inc. Objective-based reasoning in autonomous vehicle decision-making
US11635758B2 (en) 2019-11-26 2023-04-25 Nissan North America, Inc. Risk aware executor with action set recommendations
US12001211B2 (en) 2019-11-26 2024-06-04 Nissan North America, Inc. Risk-aware executor with action set recommendations
US11940539B2 (en) 2019-12-18 2024-03-26 Motional Ad Llc Camera-to-LiDAR calibration and validation
US11613269B2 (en) 2019-12-23 2023-03-28 Nissan North America, Inc. Learning safety and human-centered constraints in autonomous vehicles
US11300957B2 (en) 2019-12-26 2022-04-12 Nissan North America, Inc. Multiple objective explanation and control interface design
US11513603B2 (en) * 2020-01-30 2022-11-29 Toyota Motor Engineering & Manufacturing North America, Inc. System and method for interpreting gestures
US20210240274A1 (en) * 2020-01-30 2021-08-05 Toyota Motor Engineering & Manufacturing North America, Inc. System and method for interpreting gestures
US11577746B2 (en) 2020-01-31 2023-02-14 Nissan North America, Inc. Explainability of autonomous vehicle decision making
US11714971B2 (en) 2020-01-31 2023-08-01 Nissan North America, Inc. Explainability of autonomous vehicle decision making
CN113276864A (zh) * 2020-02-20 2021-08-20 操纵技术Ip控股公司 用于障碍物接近检测的系统和方法
CN111301410A (zh) * 2020-02-24 2020-06-19 新石器慧通（北京）科技有限公司 自动驾驶车辆及其车速调节方法
US20210284191A1 (en) * 2020-03-11 2021-09-16 Cartica Ai Ltd Autonomous driving using local driving patterns
US11782438B2 (en) 2020-03-17 2023-10-10 Nissan North America, Inc. Apparatus and method for post-processing a decision-making model of an autonomous vehicle using multivariate data
US20230249778A1 (en) * 2020-06-26 2023-08-10 Robert Bosch Gmbh Controller for straddle-type vehicle, rider-assistance system, and control method for straddle-type vehicle
US12037015B2 (en) 2020-07-28 2024-07-16 Denso Corporation Vehicle control device and vehicle control method
US20230356741A1 (en) * 2020-11-19 2023-11-09 Nissan Motor Co., Ltd. Travel Control Method and Travel Control Apparatus for Vehicle
US11952014B2 (en) 2021-10-29 2024-04-09 Waymo Llc Behavior predictions for active emergency vehicles

Also Published As

Publication number Publication date
US11034346B2 (en) 2021-06-15
KR102551130B1 (ko) 2023-07-05
CN110383008B (zh) 2024-01-23
EP3548845A2 (en) 2019-10-09
US11608057B2 (en) 2023-03-21
WO2018132614A2 (en) 2018-07-19
US20190329773A1 (en) 2019-10-31
IL293713A (en) 2022-08-01
WO2018132608A3 (en) 2018-08-23
WO2018132614A3 (en) 2018-08-23
EP3657130B1 (en) 2023-05-10
JP2022173452A (ja) 2022-11-18
EP3545265A2 (en) 2019-10-02
US20190329768A1 (en) 2019-10-31
US11173900B2 (en) 2021-11-16
US20230347877A1 (en) 2023-11-02
US12090994B2 (en) 2024-09-17
CN110383008A (zh) 2019-10-25
JP2020506838A (ja) 2020-03-05
EP4230964A1 (en) 2023-08-23
JP7159533B2 (ja) 2022-10-25
IL267857B (en) 2021-12-01
WO2018132608A2 (en) 2018-07-19
JP2020015504A (ja) 2020-01-30
IL293713B2 (en) 2023-06-01
KR20190107057A (ko) 2019-09-18
US20210269021A1 (en) 2021-09-02
IL287819A (en) 2022-01-01
EP3657130A1 (en) 2020-05-27
US20190333381A1 (en) 2019-10-31
KR102535540B1 (ko) 2023-05-23
US20220363248A1 (en) 2022-11-17
CN110325823B (zh) 2023-08-29
JP7283680B2 (ja) 2023-05-30
KR102513185B1 (ko) 2023-03-23
WO2018132607A3 (en) 2018-08-23
CN110657820A (zh) 2020-01-07
IL267857A (en) 2019-09-26
WO2018132607A2 (en) 2018-07-19
US10875528B2 (en) 2020-12-29
US20190329769A1 (en) 2019-10-31
US11738741B2 (en) 2023-08-29
JP2020516971A (ja) 2020-06-11
US20190329783A1 (en) 2019-10-31
CN110325823A (zh) 2019-10-11
IL287819B (en) 2022-07-01
EP3548845B1 (en) 2021-10-13
JP7160251B2 (ja) 2022-10-25
KR20190099088A (ko) 2019-08-23
KR20190107071A (ko) 2019-09-18
CA3049770A1 (en) 2018-07-19

Similar Documents

Publication Publication Date Title
US20220363248A1 (en) Temporary rule suspension for autonomous navigation
US10627830B2 (en) Suboptimal immediate navigational response based on long term planning
US11181926B2 (en) Trajectory selection for an autonomous vehicle
US20220269277A1 (en) Systems and methods for navigating with sensing uncertainty

Legal Events

Date Code Title Description
AS Assignment

Owner name: MOBILEYE VISION TECHNOLOGIES LTD., ISRAEL

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:SHALEV-SHWARTZ, SHAI;SHASHUA, AMNON;SHAMMAH, SHAKED;SIGNING DATES FROM 20180117 TO 20180128;REEL/FRAME:049717/0984

STPP Information on status: patent application and granting procedure in general

Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION

STPP Information on status: patent application and granting procedure in general

Free format text: NON FINAL ACTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER

STPP Information on status: patent application and granting procedure in general

Free format text: FINAL REJECTION MAILED

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION