WO2020035728A2 - Systems and methods for navigating with safe distances - Google Patents

Systems and methods for navigating with safe distances Download PDF

Info

Publication number
WO2020035728A2
WO2020035728A2 PCT/IB2019/000726 IB2019000726W WO2020035728A2 WO 2020035728 A2 WO2020035728 A2 WO 2020035728A2 IB 2019000726 W IB2019000726 W IB 2019000726W WO 2020035728 A2 WO2020035728 A2 WO 2020035728A2
Authority
WO
WIPO (PCT)
Prior art keywords
host vehicle
vehicle
target vehicle
distance
pedestrian
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.)
Ceased
Application number
PCT/IB2019/000726
Other languages
English (en)
French (fr)
Other versions
WO2020035728A3 (en
Inventor
Shai SHALEV-SHWARTZ
Shaked Shammah
Amnon Shashua
Barak Cohen
Zeev ADELMAN
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
Priority to EP25167780.3A priority Critical patent/EP4596359A3/en
Priority to KR1020217007561A priority patent/KR102867125B1/ko
Priority to EP21156822.5A priority patent/EP3842304B1/en
Priority to JP2021507580A priority patent/JP7609528B2/ja
Priority to CN201980043159.2A priority patent/CN112601686B/zh
Priority to CN202411207097.3A priority patent/CN119078812A/zh
Priority to CN202511016204.9A priority patent/CN120863620A/zh
Priority to EP21156819.1A priority patent/EP3842303B1/en
Priority to EP25167759.7A priority patent/EP4606672A3/en
Priority to EP24200665.8A priority patent/EP4474240A3/en
Priority to EP21156813.4A priority patent/EP3854646B8/en
Priority to EP19779091.8A priority patent/EP3787947B1/en
Application filed by Mobileye Vision Technologies Ltd filed Critical Mobileye Vision Technologies Ltd
Publication of WO2020035728A2 publication Critical patent/WO2020035728A2/en
Publication of WO2020035728A3 publication Critical patent/WO2020035728A3/en
Priority to US17/106,746 priority patent/US11840258B2/en
Priority to US17/174,937 priority patent/US12037019B2/en
Priority to US17/174,844 priority patent/US11897508B2/en
Priority to US17/174,689 priority patent/US12037018B2/en
Anticipated expiration legal-status Critical
Priority to US17/208,180 priority patent/US11932277B2/en
Priority to US18/750,716 priority patent/US20250033669A1/en
Priority to JP2024220846A priority patent/JP7808176B2/ja
Ceased legal-status Critical Current

Links

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
    • B60W30/095—Predicting travel path or likelihood of collision
    • B60W30/0953—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic 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
    • B60W10/00—Conjoint control of vehicle sub-units of different type or different function
    • B60W10/18—Conjoint control of vehicle sub-units of different type or different function including control of braking systems
    • 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
    • B60W10/00—Conjoint control of vehicle sub-units of different type or different function
    • B60W10/20—Conjoint control of vehicle sub-units of different type or different function including control of steering systems
    • 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
    • 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
    • B60W30/18—Propelling the vehicle
    • 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
    • B60W30/181—Preparing for stopping
    • 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
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient 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
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • B60W40/105—Speed
    • 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
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • B60W40/107—Longitudinal acceleration
    • 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
    • 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
    • B60W60/0015—Planning or execution of driving tasks specially adapted for safety
    • B60W60/0017—Planning or execution of driving tasks specially adapted for safety of other traffic participants
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • 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
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting 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
    • 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
    • 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
    • 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
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • 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
    • 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
    • B60W2510/00—Input parameters relating to a particular sub-units
    • B60W2510/18—Braking system
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/04—Vehicle stop
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • B60W2520/105—Longitudinal acceleration
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/12—Lateral speed
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/12—Lateral speed
    • B60W2520/125—Lateral acceleration
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/14—Yaw
    • 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
    • B60W2530/00—Input parameters relating to vehicle conditions or values, not covered by groups B60W2510/00 or B60W2520/00
    • B60W2530/201—Dimensions of vehicle
    • 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
    • B60W2552/45—Pedestrian sidewalk
    • 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
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/402—Type
    • 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
    • B60W2554/4042—Longitudinal speed
    • 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
    • B60W2554/4043—Lateral speed
    • 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
    • B60W2554/4044—Direction of movement, e.g. backwards
    • 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
    • B60W2554/4045—Intention, e.g. lane change or imminent movement
    • 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
    • B60W2554/806—Relative heading
    • 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
    • B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
    • B60W2555/60—Traffic rules, e.g. speed limits or right of way
    • 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
    • B60W2720/00—Output or target parameters relating to overall vehicle dynamics
    • B60W2720/10—Longitudinal speed
    • 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
    • B60W2754/00—Output or target parameters relating to objects
    • B60W2754/10—Spatial relation or speed relative to objects
    • B60W2754/20—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
    • B60W2754/00—Output or target parameters relating to objects
    • B60W2754/10—Spatial relation or speed relative to objects
    • B60W2754/30—Longitudinal distance
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60Y—INDEXING SCHEME RELATING TO ASPECTS CROSS-CUTTING VEHICLE TECHNOLOGY
    • B60Y2300/00—Purposes or special features of road vehicle drive control systems
    • B60Y2300/08—Predicting or avoiding probable or impending collision
    • B60Y2300/095—Predicting travel path or likelihood of collision
    • B60Y2300/0952—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60Y—INDEXING SCHEME RELATING TO ASPECTS CROSS-CUTTING VEHICLE TECHNOLOGY
    • B60Y2300/00—Purposes or special features of road vehicle drive control systems
    • B60Y2300/08—Predicting or avoiding probable or impending collision
    • B60Y2300/095—Predicting travel path or likelihood of collision
    • B60Y2300/0954—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60Y—INDEXING SCHEME RELATING TO ASPECTS CROSS-CUTTING VEHICLE TECHNOLOGY
    • B60Y2300/00—Purposes or special features of road vehicle drive control systems
    • B60Y2300/18—Propelling the vehicle
    • B60Y2300/18008—Propelling the vehicle related to particular drive situations
    • B60Y2300/18091—Preparing for stopping
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G01S2013/9323—Alternative operation using light waves
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06T2207/30196—Human being; Person
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06T2207/30261—Obstacle
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection

Definitions

  • the present disclosure relates generally to autonomous vehicle navigation.
  • this disclosure relates to systems and methods for navigating according to potential accident liability constraints.
  • 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.
  • the navigational system may need to adhere to certain imposed constraints. In some cases, those constraints may relate to interactions between a host vehicle and one or more other objects, such as other vehicles, pedestrians, etc. In other cases, the constraints may relate to liability rules to be followed in implementing one or more navigational actions for a host vehicle.
  • 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, etc.), and/or other map data.
  • GPS global positioning system
  • a system for navigating a host vehicle may comprise at least one processing device programmed to receive, from an image capture device, at least one image representative of an environment of the host vehicle; determine, based on at least one driving policy, a planned navigational action for accomplishing a navigational goal of the host vehicle; analyze the at least one image to identify a target vehicle in the environment of the host vehicle, wherein a direction of travel of the target vehicle is toward the host vehicle; determine a next-state distance between the host vehicle and the target vehicle that would result if the planned navigational action was taken; determine a host vehicle braking rate, a host vehicle maximum acceleration capability, and a current speed of the host vehicle; determine a stopping distance for the host vehicle based on the host vehicle braking rate, the host vehicle maximum acceleration capability, and the current speed of the host vehicle; determine a current speed of the target vehicle, a target vehicle maximum acceleration capability, and a target vehicle braking rate; determine a stopping distance for the target vehicle based on the target vehicle braking
  • a method for navigating a host vehicle may comprise receiving, from an image capture device, at least one image representative of an environment of the host vehicle; determining, based on at least one driving policy, a planned navigational action for accomplishing a navigational goal of the host vehicle; analyzing the at least one image to identify a target vehicle in the environment of the host vehicle, wherein a direction of travel of the target vehicle is toward the host vehicle; determining a next-state distance between the host vehicle and the target vehicle that would result if the planned navigational action was taken; determining a host vehicle braking rate, a host vehicle maximum acceleration capability, and a current speed of the host vehicle; determining a stopping distance for the host vehicle based on the host vehicle braking rate, the host vehicle maximum acceleration capability, and the current speed of the host vehicle; determining a current speed of the target vehicle, a target vehicle maximum acceleration capability, and a target vehicle braking rate; determining a stopping distance for the target vehicle based on the target vehicle braking rate
  • a system for navigating a host vehicle may comprise at least one processing device programmed to receive, from an image capture device, at least one image representative of an environment of the host vehicle; determine, based on at least one driving policy, a planned navigational action for accomplishing a navigational goal of the host vehicle; analyze the at least one image to identify a target vehicle in the environment of the host vehicle; determine a next- state lateral distance between the host vehicle and the target vehicle that would result if the planned navigational action was taken; determine a maximum yaw rate capability of the host vehicle, a maximum change in turn radius capability of the host vehicle, and a current lateral speed of the host vehicle;
  • a lateral braking distance for the host vehicle based on the maximum yaw rate capability of the host vehicle, the maximum change in turn radius capability of the host vehicle, and the current lateral speed of the host vehicle; determine a current lateral speed of the target vehicle, a target vehicle maximum yaw rate capability, and a target vehicle maximum change in turn radius capability; determine a lateral braking distance for the target vehicle based on the current lateral speed of the target vehicle, the target vehicle maximum yaw rate capability, and the target vehicle maximum change in turn radius capability; and implement the planned navigational action if the determined next-state lateral distance is greater than a sum of the lateral braking distance for the host vehicle and the lateral braking distance of the target vehicle.
  • a method for navigating a host vehicle may comprise receiving, from an image capture device, at least one image representative of an environment of the host vehicle; determining, based on at least one driving policy, a planned navigational action for accomplishing a navigational goal of the host vehicle; analyzing the at least one image to identify a target vehicle in the environment of the host vehicle; determining a next-state lateral distance between the host vehicle and the target vehicle that would result if the planned navigational action was taken; determining a maximum yaw rate capability of the host vehicle, a maximum change in turn radius capability of the host vehicle, and a current lateral speed of the host vehicle; determining a lateral braking distance for the host vehicle based on the maximum yaw rate capability of the host vehicle, the maximum change in turn radius capability of the host vehicle, and the current lateral speed of the host vehicle; determining a current lateral speed of the target vehicle, a target vehicle maximum yaw rate capability, and a target vehicle maximum change in
  • a system for navigating a host vehicle in proximity to a pedestrian crosswalk may comprise at least one processing device programmed to: receive, from an image capture device, at least one image representative of an environment of the host vehicle; detect, based on analysis of the at least one image, a representation of a pedestrian crosswaik in the at least one image; determine, based on analysis of the at least one image, whether a representation of a pedestrian appears in the at least one image; detect a presence of a traffic light in the environment of the host vehicle; determine whether the detected traffic light is relevant to the host vehicle and the pedestrian crosswalk; determine a state of the detected traffic light; determine, when a representation of a pedestrian appears in the at least one image, a proximity of the pedestrian relative to the detected pedestrian crosswalk; determine, based on at least one driving policy, a planned navigational action for causing the host vehicle to navigate relative to the detected pedestrian crosswalk, wherein determination of the planned navigational action is further based on the determined state of the detected traffic
  • a method for navigating a host vehicle in proximity to a pedestrian crosswalk may comprise receiving, from an image capture device, at least one image representative of an environment of the host vehicle; detecting, based on analysis of the at least one image, a representation of a pedestrian crosswalk in the at least one image; determining, based on analysis of the at least one image, whether a representation of a pedestrian appears in the at least one image; detecting a presence of a traffic light in the environment of the host vehicle; determining whether the detected traffic light is relevant to the host vehicle and the pedestrian crosswalk; determining a state of the detected traffic light; determining, when a representation of a pedestrian appears in the at least one image, a proximity of the pedestrian relative to the detected pedestrian crosswalk; determining, based on at least one driving policy, a planned navigational action for causing the host vehicle to navigate relative to the detected pedestrian crosswalk, wherein determination of the planned navigational action is further based on the determined state of the detected traffic light and the determined proximity
  • a method for navigating a host vehicle in proximity to a pedestrian crosswalk may comprise receiving, from an image capture device, at least one image representing an environment of the host vehicle; detecting a starting and an ending location of a crosswalk; determining, based on an analysis of the at least one image, whether a pedestrian is present in a proximity of the crosswalk; detecting a presence of a traffic light in the environment of the host vehicle; determining whether the traffic light is relevant to the host vehicle and the crosswalk; determining a state of the traffic light; determining a navigational action for the host vehicle in vicinity of the detected crosswalk, based on: the relevancy of the traffic light; the determined state of the traffic light; a presence of the pedestrian in the proximity of the crosswalk; a shortest distance selected between the pedestrian and one of the starting or the ending location of the crosswalk; and a motion vector of the pedestrian; and causing one or more actuator systems of the host vehicle to implement the navigational action.
  • 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. 1 1A, 1 IB, and 1 1 C provide a schematic representation of navigational options of a host vehicle in a merge zone consistent with the disclosed embodiments.
  • Fig. 1 ID provide a diagrammatic depiction of a double merge scenario consistent with the disclosed embodiments.
  • Fig. 1 IE provides an options graph potentially useful in a double merge scenario consistent with the disclosed embodiments.
  • 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.
  • FIGs. 20A and 20B illustrate examples of a vehicle cutting in in front of another vehicle consistent with the disclosed embodiments.
  • Fig. 21 illustrates an example of a vehicle following another vehicle consistent with the disclosed embodiments.
  • Fig. 22 illustrates an example of a vehicle exiting a parking lot and merging into a possibly busy road consistent with the disclosed embodiments.
  • Fig. 23 illustrates a vehicle traveling on a road consistent with the disclosed embodiments.
  • Fig. 27 illustrates an example scenario consistent with the disclosed embodiments.
  • FIGs. 28A and 28B illustrate an example of a scenario in which a vehicle is following another vehicle consistent with the disclosed embodiments.
  • Figs. 29A and 29B illustrate example blame in cut-in scenarios consistent with the disclosed embodiments.
  • Figs. 30A and 30B illustrate example blame in cut-in scenarios consistent with the disclosed embodiments.
  • Figs. 31 A-3 ID illustrate example blame in drifting scenarios consistent with the disclosed embodiments.
  • Figs. 32A and 32B illustrate example blame in two-way traffic scenarios consistent with the disclosed embodiments.
  • Figs. 33A and 33B illustrate example blame in two-way traffic scenarios consistent with the disclosed embodiments.
  • Figs. 34A and 34B illustrate example blame in route priority scenarios consistent with the disclosed embodiments.
  • Figs. 35A and 35B illustrate example blame in route priority scenarios consistent with the disclosed embodiments.
  • Figs. 36A and 36B illustrate example blame in route priority scenarios consistent with the disclosed embodiments.
  • Figs. 37A and 37B illustrate example blame in route priority scenarios consistent with the disclosed embodiments.
  • Figs. 38A and 38B illustrate example blame in route priority scenarios consistent with the disclosed embodiments.
  • Figs. 39A and 39B illustrate example blame in route priority scenarios consistent with the disclosed embodiments.
  • Figs. 40A and 40B illustrate example blame in traffic light scenarios consistent with the disclosed embodiments.
  • Figs. 41A and 41B illustrate example blame in traffic light scenarios consistent with the disclosed embodiments.
  • Figs. 43A-43C illustrate example vulnerable road users (VRUs) scenarios consistent with the disclosed embodiments.
  • Figs. 44A-44C illustrate example vulnerable road users (VRUs) scenarios consistent with the disclosed embodiments.
  • Figs. 45A-45C illustrate example vulnerable road users (VRUs) scenarios consistent with the disclosed embodiments.
  • Figs. 46A-46D illustrate example vulnerable road users (VRUs) scenarios consistent with the disclosed embodiments.
  • FIG. 47 A is an illustration of blame time and proper responses, consistent with the disclosed embodiments.
  • FIG. 47B is an illustration of route priority for routes of differing geometries, consistent with the disclosed embodiments.
  • FIG. 47C is an illustration of longitudinal ordering on routes of differing geometries, consistent with the disclosed embodiments.
  • FIG. 47E is an illustration of a situation in which a vehicle cannot predict the path of another vehicle, consistent with the disclosed embodiments.
  • FIG. 47G is an illustration of exemplary unstructured routes, consistent with the disclosed embodiments.
  • FIG. 471 is an illustration of exposure time and blame time at an area of occlusion, consistent with the disclosed embodiments.
  • Fig. 48A illustrates an example scenario of two vehicles traveling in opposite directions consistent with the disclosed embodiments.
  • Fig. 48B illustrates an example of a target vehicle traveling towards a host vehicle consistent with the disclosed embodiments.
  • Fig. 49 illustrates an example of host vehicle maintaining a safe longitudinal distance consistent with the disclosed embodiments.
  • Fig. 51 A illustrates an example scenario with two vehicles spaced laterally from each other consistent with the disclosed embodiments.
  • Fig. 52B shows an example of a host vehicle determining whether to perform a navigation action.
  • Figs. 53A and 53B provide a flowchart depicting an example process for maintaining a safe lateral distance consistent with the disclosed embodiments.
  • Fig. 54 is a schematic illustration of a roadway including crosswalks, consistent with the disclosed embodiments.
  • Figs. 55A and 55B are schematic diagrams of possible navigational actions executed by vehicles traveling along a roadway, consistent with the disclosed embodiments.
  • Figs. 55C and 55D show examples of estimating a distance from a pedestrian to a crosswalk, consistent with the disclosed embodiments.
  • Fig. 56 is a flowchart describing a process of navigating a vehicle in the proximity of a crosswalk, 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 enviromnent 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 1 10, 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 1 10 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.).
  • 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 1 10).
  • 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 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.
  • the use of 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.
  • 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 FOV 202
  • 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. For example, in some embodiments, 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.
  • FOV such as FOV 204
  • FOV 206 FOV
  • 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.
  • 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.
  • 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 x 480 and another device includes an image sensor with a resolution of 1280 x 960, then more time will be required to acquire a frame of image data from the sensor having the higher resolution.
  • 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.
  • 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 1266
  • images of more distant objects e.g., greater than 20 m, 50 m, 100 m, 150 m, etc.
  • 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).
  • system 100 may provide various notifications (e.g
  • 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).
  • system 100 may include a configuration of any number of cameras (e.g., one, two, three, four, five, six, seven, eight, etc.)
  • system 100 may include “clusters” of cameras.
  • a cluster of cameras including any appropriate number of cameras, e.g., one, four, eight, etc.
  • system 100 may include multiple clusters of cameras, with each cluster oriented in a particular direction to capture images from a particular region of a vehicle’s environment.
  • 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.
  • 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
  • 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.).
  • 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.
  • 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.
  • stereo image analysis module 404 may store instructions (such as computer vision software) which, when executed by processing unit 1 10, 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 1 10 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 1 10 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 1 10 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 1 10 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 1 10 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. Such data may include position and speed information associated with nearby vehicles, pedestrians, and road objects, target position information for vehicle 200, and the like. Additionally, in some embodiments, 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 1 10 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, for example, turning the steering wheel of
  • 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.
  • Processing unit 1 10 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 1 10 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.
  • 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 1 10 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 1 10 may use one or more sets of criteria to reject false candidates from the set of candidate objects.
  • processing unit 1 10 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 1 10 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 1 10 may estimate parameters for the detected object and compare the object’s frame-by-frame position data to a predicted position. [0185] At step 546, processing unit 1 10 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.
  • processing unit 1 10 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 1 10 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 1 10 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 1 10 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.
  • processing unit 1 10 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 1 10 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 1 10 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 1 10 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 1 10 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 500D for detecting traffic lights in a set of images, consistent with disclosed embodiments.
  • Processing unit 1 10 may execute monocular image analysis module 402 to implement process 500D.
  • processing unit 1 10 may scan the set of images and identify objects appearing at locations in the images likely to contain traffic lights.
  • processing unit 1 10 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 1 10 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 1 10 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 1 10 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 1 10 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 500E 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, 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 determine a look-ahead point (expressed in coordinates as (x / , z / )) 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).
  • processing unit 110 may determine a heading error and yaw rate command based on the look-ahead point determined at step 574.
  • Processing unit 1 10 may determine the heading error by calculating the arctangent of the look-ahead point, e.g., arctan (xi / zi).
  • Processing unit 110 may determine the yaw rate command as the product of the heading error and a high-level control gain.
  • the high-level control gain may be equal to: (2 / look-ahead time), if the look-ahead distance is not at the lower bound. Otherwise, the high-level control gain may be equal to: (2 * speed of vehicle 200 / lookahead distance).
  • Fig. 5F is a flowchart showing an exemplary process 500F for determining whether a leading vehicle is changing lanes, consistent with the disclosed embodiments.
  • processing unit 1 10 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 1 10 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.
  • 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 5B, above.
  • processing unit 110 may analyze the navigation information determined at step 580.
  • processing unit 1 10 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 1 10 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 1 10 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 1 10 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 1 10 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 1 10 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: (d z 2 + d c 2 ) 11 1 (d c ), where d c represents the lateral distance traveled and d 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 1 10 may determine that the leading vehicle is likely changing lanes. In another embodiment, processing unit 1 10 may analyze the position of the leading vehicle.
  • a predetermined threshold e.g. 500 to 700 meters
  • processing unit 1 10 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 1 10 may determine that the (closer) leading vehicle is likely changing lanes.
  • processing unit 1 10 may determine whether or not leading vehicle 200 is changing lanes based on the analysis performed at step 582. For example, processing unit 1 10 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 such as image capture devices 122 and 124 having fields of view 202 and 204 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 1 10.
  • 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 1 10 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 1 10 may consider information from both the first and second plurality of images, rather than information from one set of images alone. For example, processing unit 1 10 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 1 10 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.
  • 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 1 10.
  • 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 1 10 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 1 10 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 1 10 may perform a combination of monocular and stereo image analyses.
  • processing unit 1 10 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— including their respective locations and fields of view 202, 204, and 206— may influence the types of analyses conducted on the first, second, and third plurality of images.
  • 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 1 10 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 1 10 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 1 10 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.
  • 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 1 10 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.
  • Navigational responses may include, for example, a turn, a lane shift, a change in acceleration, and the like.
  • Processing unit 1 10 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 1 10 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.
  • Sensing module 801 which may be implemented using processing unit 110, 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.
  • 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.
  • 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
  • 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 decide on an action C ⁇ based on a policy « ⁇ 5 Based on the decided action (and implementation of the action), the environment moves to the next state
  • the feedback to the learning system is a reward signal 1 1 1 2 ; ⁇ ⁇ ⁇ .
  • the value of the initial state s may be defined as:
  • 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,, a,), where s, is the state and a, 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 p such that ⁇ a t .
  • the learning is supervised and happens offline (there is no need to apply the agent in the learning process).
  • a disadvantage of this method is that different human drivers, and even the same human drivers, are not deterministic in their policy choices. Hence, learning a function for which c>t II is very small is often infeasible. And, even small errors may accumulate over time to yield large errors.
  • 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., argmax stochastic gradient descent).
  • argmax stochastic gradient descent a suitable optimization technique
  • the approach is to directly solve the problem given in p
  • 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 p is an iterative process, where at iteration j we have a non-perfect policy, p,, and to construct the next policy p,, we must interact with the environment while acting based on p,.
  • 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,, a,) and yields a distribution over the next state s t+i .
  • the optimization problem may be solved to find the policy p 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,, s i+i ).
  • 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 p that maps the state into ⁇ C K " , where the first component of p (s) is the desired acceleration command and the second component of p (s) is the yaw rate.
  • the following policies can be constructed:
  • ACC+Left policy S -+ A.
  • q lc 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).
  • 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 91 1 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.
  • 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. 1 1 A, host vehicle 1 105 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 11 1 1. 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. 1 IB the situation is slightly different.
  • host vehicle 1 105 senses one or more target vehicles 1 107 entering the main roadway 1 1 12 from merge lane 11 1 1.
  • driving policy module 803 may choose to initiate an overtake left maneuver in order to avoid the merging situation.
  • 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. 11 A-l 1C 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,) to .v, +i can be learned such that Si +t ⁇ s t+ 1 , This may be similar to“model-based” reinforcement learning.
  • a +i may be replaced by the actual value of s, + 1, therefore eliminating the problem of error accumulation.
  • the role of prediction of .v, . i 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.”
  • An important element that may be provided in some scenarios is a differentiable path from future losses/rewards back to decisions on actions.
  • 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 a may be referred to as additive noise.
  • supervised learning may be used together with real data.
  • the 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. For example, given an initial implementation of the other agents (cars/pedestrians) that may be experienced, 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 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.
  • the learning system may prefer a policy that performs an accident (or adopt in general a reckless driving policy) in order to fulfill the takeover maneuver successfully more often than a policy that would be more defensive at the expense of having some takeover maneuvers not complete successfully.
  • the gradient of E[A.(S)] may be estimated. The following lemma shows that the variance of the random variable grows with , which is larger than fo
  • the policy function may be decomposed into a leamable part and a non-learnable part.
  • the policy function may be structured as maps the (agnostic) state space into a set of Desires (e.g., desired
  • the function W 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.
  • a double merge navigational situation as depicted in Fig. 1 ID, provides an example further illustrating these concepts.
  • a double merge vehicles approach the merge area 1 130 from both left and right sides. And, from each side, a vehicle, such as vehicle 1 133 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.
  • P may be the Cartesian product of the following sets:
  • a driving trajectory may be represented by the (lateral, longitudinal) location of the host vehicle (in ego-centric units) at time ' l .
  • T - 0.
  • IstJC 10.
  • 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.
  • Assigning a weight to each of these costs may provide a single objective function for
  • the decision making may be further decomposed into semantically meaningful components.
  • the size of ⁇ might be large and even continuous.
  • the gradient estimator may involve the term ) .
  • 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 lOFIz and the merge area 1 130 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. 1 ID is shown in Fig. 1 IE.
  • 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.
  • a potential benefit of the options is the interpretability of the results. Another potential benefit is that the decomposable structure of the set O 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.
  • 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 if ⁇ t% p ial t
  • trajectory prediction may be relatively
  • 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.
  • 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 closers to the edges of the lane, a curb, or a pedestrian more than might ordinarily be permitted.
  • 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.
  • 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. In some cases, 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 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.
  • 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).
  • 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. 12, that 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.
  • 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.
  • 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
  • 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 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.
  • 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.
  • 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 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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 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.
  • 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.
  • selection of available actions may be made based on determined differences between expected rewards. For example, a second potential action determined at step 1607 may be selected if a difference between an expected reward associated with a future action determined at step 1621 and expected reward 1606 is greater than a difference between expected reward 1608 and expected reward 1606 (assuming + sign differences). In another example, a second potential action determined at step 1607 may be selected if a difference between an expected reward associated with a future action determined at step 1621 and an expected reward associated with a future action determined at step 1619 is greater than a difference between expected reward 1608 and expected reward 1606.
  • 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.
  • the host vehicle may be inclined to give way to the target vehicle.
  • a level of aggression of the target vehicle may also be discerned based on a determined behavior of the target vehicle relative to one or more obstacles in a path of or in a vicinity of the target vehicle (e.g., a leading vehicle, obstacle in the road, traffic light, etc.).
  • 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.
  • p 0.5
  • the navigation system of the host vehicle may be provided with no information about the type of the other drivers. The types of other drivers may be chosen at random at the beginning of the episode.
  • 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.
  • the next state, s t+i may be decomposed into a sum of a predictable part, “f) , and a non-predictable part,
  • ma y represent the dynamics of vehicle locations and velocities (which may be well-defined in a differentiable manner), while Vt may represent the target vehicles’ acceleration.
  • ⁇ ( •‘ T can be expressed as a combination of ReLU functions over an affine transformation, hence it is differentiable with respect to s, and a t .
  • the vector ''' 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.
  • Figs. 17A and 17B Two frames from such a simulator are shown in Figs. 17A and 17B.
  • a host vehicle 1701 learned to slowdown as it approached the entrance of the roundabout. It also learned to give way to aggressive vehicles (e.g., vehicles 1703 and 1705), and to safely continue when merging in front of defensive vehicles (e.g., vehicles 1706, 1708, and 1710).
  • the navigation system of host vehicle 1701 is not provided with the type of target vehicles. Rather, whether a particular vehicle is determined to be aggressive or defensive is determined through inference based on observed position and acceleration, for example, of the target vehicles.
  • host vehicle 1701 may determine that vehicle 1703 has an aggressive tendency and, therefore, host vehicle 1701 may stop and wait for target vehicle 1703 to pass rather than attempting to merge in front of target vehicle 1703.
  • 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.
  • Various 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.
  • such 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. Patent 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.
  • 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.
  • the aggressive/defensive determination may be made based on any observed navigational characteristic alone, the determination may also depend on any combination of observed characteristics. For example, as noted above, in some cases, 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.
  • a predetermined amount which may be the same as or different than the threshold applied where the determination is based on distance alone
  • 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. In other cases, however, 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 0.5G acceleration or deceleration (e.g., jerk 5m/s3), a vehicle has a lateral acceleration of 0.5G 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 0.3G deceleration or jerk of 3m/s3, and/or a vehicle changes two lanes without stopping.
  • 0.5G acceleration or deceleration e.g., jerk 5m/s3
  • references to a quantity exceeding a range may indicate that the quantity either exceeds all values associated with the range or falls within the range.
  • references to a quantity falling below a range may indicate that the quantity either falls below all values associated with the range or falls within the range.
  • any other suitable quantities may be used. For example, a time to collision may calculation may be used or any indirect indicator of distance, acceleration, and/or velocity of the target vehicle.
  • 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.
  • the observed navigational characteristic (e.g., a location, distance, acceleration, etc.) may be referenced relative to the host vehicle in order to make the aggressive/defensive determination.
  • 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.
  • planned navigational actions may be tested against predetermined constraints to ensure compliance with certain rules.
  • this concept may be extended to considerations of potential accident liability.
  • a primary goal of autonomous navigation is safety.
  • absolute safety may be impossible (e.g., at least because a particular host vehicle under autonomous control cannot control the other vehicles in its surroundings— it can only control its own actions)
  • potential accident liability as a consideration in autonomous navigation and, indeed, as a constraint to planned actions may help ensure that a particular autonomous vehicle does not take any actions that are deemed unsafe-e.g., those for which potential accident liability may attach to the host vehicle.
  • host vehicle 1901 drives on a multi-lane highway, and while host vehicle 1901 can control its own actions relative to the target vehicles 1903, 1905, 1907, and 1909, it cannot control the actions of the target vehicles surrounding it.
  • host vehicle 1901 may be unable to avoid an accident with at least one of the target vehicles should vehicle 1905, for example, suddenly cut in to the host vehicle’s lane on a collision course with the host vehicle.
  • a typical response of autonomous vehicle practitioners is to resort to a statistical data-driven approach where safety validation becomes tighter as data over more mileage is collected.
  • the amount of data required to guarantee a probability of 10 9 fatality per hour of driving is proportional to its inverse (i.e., 10 9 hours of data) which is roughly on the order of thirty billion miles.
  • a multi-agent system interacts with its environment and likely cannot be validated offline (unless a realistic simulator emulating real human driving with all its richness and complexities such as reckless driving is available— but the problem of validating the simulator would be even more difficult than creating a safe autonomous vehicle agent).
  • a second primary challenge in developing a safe driving model for autonomous vehicles is the need for scalability.
  • the premise underlying AV goes beyond“building a better world” and instead is based on the premise that mobility without a driver can be sustained at a lower cost than with a driver.
  • This premise is invariably coupled with the notion of scalability— in the sense of supporting mass production of AVs (in the millions) and more importantly of supporting a negligible incremental cost to enable driving in a new city. Therefore the cost of computing and sensing does matter, if AV is to be mass manufactured, the cost of validation and the ability to drive“everywhere” rather than in a select few cities is also a necessary requirement to sustain a business.
  • the disclosed embodiments represent a solution that may provide the target levels of safety (or may even surpass safety targets) and may also be scalable to systems including millions of autonomous vehicles (or more).
  • a model called“Responsibility Sensitive Safety” (RSS) is introduced that formalizes the notion of“accident blame,” is interpretable and explainable, and incorporates a sense of“responsibility” into the actions of a robotic agent.
  • the definition of RSS is agnostic to the manner in which it is implemented— which is a key feature to facilitate a goal of creating a convincing global safety model. RSS is motivated by the observation (as in Fig.
  • the RSS model also includes a formal treatment of“cautious driving” under limited sensing conditions where not all agents are always visible (due to occlusions, for example).
  • One primary goal of the RSS model is to guarantee that an agent will never make an accident of its“blame” or for which it is responsible.
  • a model may be useful only if it comes with an efficient policy (e.g., a function that maps the“sensing state” to an action ) that complies with RSS. For example, an action that appears innocent at the current moment might lead to a catastrophic event in the far future (“butterfly effect”).
  • RSS may be useful for constructing a set of local constraints on the short-term future that may guarantee (or at least virtually guarantee) that no accidents will happen in the future as a result of the host vehicle’s actions.
  • a formal semantic language may be useful on multiple fronts connected to the computational complexity of planning that do not scale up exponentially with time and number of agents, to the manner in which safety and comfort interact, to the way the computation of sensing is defined and the specification of sensor modalities and how they interact in a fusion methodology.
  • a fusion methodology (based on the semantic language) may ensure that the RSS model achieves the required 10 '9 probability of fatality, per one hour of driving, all while performing only offline validation over a dataset of the order of 10 5 hours of driving data.
  • semantics may allow for distinguishing between mistakes that affect safety versus those mistakes that affect the comfort of driving.
  • PAC Probably Approximate Correct
  • PAC-learning terminology a PAC model (Probably Approximate Correct (PAC)), borrowing Valiants PAC-learning terminology ) for sensing which is tied to the Q-function and show how measurement mistakes are incorporated into planning in a manner that complies with RSS yet allows for optimization of the comfort of driving.
  • the language of semantics may be important for the success of certain aspects of this model as other standard measures of error, such as error with respect to a global coordinate system, may not comply with the PAC sensing model.
  • the semantic language may be an important enabler for defining HD-maps that can be constructed using low-bandwidth sensing data and thus be constructed through crowdsourcing and support scalability.
  • the disclosed embodiments may include a formal model that covers important ingredients of an AV: sense, plan, and act.
  • the model may help ensure that from a planning perspective there will be no accident of the AVs own responsibility.
  • the described fusion methodology may require only offline data collection of a very reasonable magnitude to comply with the described safety model.
  • the model may tie together safety and scalability through the language of semantics, thereby providing a complete methodology for a safe and scalable AV.
  • the RSS model may generally follow a classic sense-plan-act robotic control methodology.
  • the sensing system may be responsible for understanding a present state of the environment of a host vehicle.
  • the planning part which may be referred to as a“driving policy” and which may be implemented by a set of hard-coded instructions, through a trained system (e.g., a neural network), or a combination, may be responsible for determining what is the best next move in view of available options for accomplishing a driving goal (e.g., how to move from the left lane to a right lane in order to exit a highway).
  • the acting portion is responsible for implementing the plan (e.g., the system of actuators and one or more controllers for steering, accelerating, and/or braking, etc. a vehicle in order to implement a selected navigational action).
  • plan e.g., the system of actuators and one or more controllers for steering, accelerating, and/or braking, etc. a vehicle in order to implement a selected navigational action.
  • the described embodiments below focus primarily on the sensing and planning parts.
  • Errors in a sensing system may be easier to validate, because sensing can be independent of the vehicle actions, and therefore we can validate the probability of a severe sensing error using“offline” data. But, even collecting offline data of more than 10 9 hours of driving is challenging.
  • a fusion approach is described that can be validated using a significantly smaller amount of data.
  • the described RSS system may also be scalable to millions of cars.
  • the described semantic driving policy and applied safety constraints may be consistent with sensing and mapping requirements that can scale to millions of cars even in today's technology.
  • any statistical claim must be formalized to be measured. Claiming a statistical property over the number of accidents a system makes is significantly weaker than claiming“it drives in a safe manner.” In order to say that, one must formally define what is safety.
  • An action a taken by a car c may be deemed absolutely safe if no accident can follow the action at some future time. It can be seen that it is impossible to achieve absolute safety, by observing simple driving scenarios, for example, as depicted in Figure 19. From the perspective of vehicle 1901, no action can ensure that none of the surrounding cars will crash into it. Solving this problem by forbidding the autonomous car from being in such situations is also impossible. As every highway with more than two lanes will lead to it at some point, forbidding this scenario amounts to a requirement to remain in the garage. The implications might seem, at first glance, disappointing. None is absolutely safe.
  • Definitions may aid in distinction between two intuitively different sets of cases: simple ones, where no significant lateral maneuver is performed, and more complex ones, involving lateral movement.
  • the direction of a cut-in may describe movement in the direction of the relevant corridor boundary. These definitions may define cases with lateral movement. For the simple case where there is no such occurrence, such as the simple case of a car following another, the safe longitudinal distance is defined:
  • Lemma 2 calculates d as a function of the velocities of c r , Cf, the response time p, and the maximal acceleration a max, brake. Both p and t , brake are constants, which should be determined to some reasonable values by regulation.
  • d be the distance at time t. To prevent an accident, we must have that d, > L for every t. To construct d m in we need to find the tightest needed lower bound on do. Clearly, do must be at least L.
  • T r is the time on which c r arrives to a full stop (a velocity of 0) and 7 ⁇ is the time on which the other vehicle arrives to a full stop.
  • Blame Times may be split into two separate categories:
  • Definition 9 The Exposure Time of an object is the first time in which we see it.
  • the car is not to blame only if a pedestrian runs into its side, while the car does not ride faster than m into the pedestrian, or if the car is at stop, or if the pedestrian was running super-humanly fast, in some direction, not necessarily the hitting direction.
  • each induction step extends the proof to more and more involved cases.
  • c/ (Fig. 21).
  • the following constraint may be applied on the policy of c r .
  • the policy can pick any acceleration command such that even if c / will apply a deceleration of-a max , the resulting distance between c r and c/ at the next time step will be at least the safe longitudinal distance (defined in Definition 3 and Lemma 2). If no such action exists, c r must apply the deceleration -a raax .
  • the following lemma uses induction to prove that any policy that adheres to the above constraints will never make an accident with c/.
  • Definition 12 The Default Emergency Policy (DEP) is to apply maximum braking power, and maximum heading change towards 0 heading w.r.t. the lane. The maximum braking power and heading change are derived from physical parameters of the car (and maybe also from weather and road conditions).
  • Definition 13 A state s is safe if performing DEP starting from it will not lead to an accident of our blame. As in the simple case of a car following another, we define a command to be cautious if it leads to a safe state.
  • Definition 14 (Cautious command) Suppose we are currently at state so- A command a is cautious if the next state, si, will be safe with respect to a set A of possible commands that other vehicles might perform now. The above definition depends on the worst-case commands, in the set A, other vehicles might perform. We will construct the set A based on reasonable upper bounds on maximum braking/acceleration and lateral movements.
  • a first observation is that a state is not safe if and only if there exists a specific vehicle, c, which can perform commands from the set A which lead to an accident of our blame while we execute the DEP. Therefore, in a scene with a single target car, denoted c, and in the general case, the procedure may be executed sequentially, for each of the other vehicles in the scene.
  • a different approach attempts to perform offline calculations in order to construct an approximation of Q, denoted Q, and then during the online run of the policy, use Q as an approximation to Q, without explicitly rolling out the future.
  • One way to construct such an approximation is to discretize both the action domain and the state domain. Denote by A, S these discretized sets.
  • a semantic action space induces a subset of all possible geometrical curves, whose size is exponentially smaller (in T) than enumerating all possible geometrical curves.
  • the first immediate question is whether the set of short-term prefixes of this smaller search space contains all geometric commands that we will ever want to use. This is indeed sufficient in the following sense. If the road is free of other agents, then there is no reason to make changes except setting a lateral goal and/or absolute acceleration commands and/or speed constraints on certain positions. If the road contains other agents, we may want to negotiate the right of way with the other agents. In this case, it suffices to set longitudinal goals relatively to the other agents. The exact implementation of these goals in the long run may vary, but the short-term prefixes will not change by much. Hence, we obtain a very good cover of the relevant short-term geometrical commands.
  • Another potential advantage of applying machine learning is for the sake of generalization: we may set an adequate evaluation function for every road, by a manual inspection of the properties of the road, which may involve some trial and error.
  • a machine learning approach as discussed above, can be trained on a large variety of road types so as to generalize to unseen roads as well.
  • the semantic action space according to the disclosed embodiments may allow for potential benefits: semantic actions contain information on a long-time horizon, hence we can obtain a very accurate evaluation of their quality while being resource efficient.
  • s is almost optimal, namely, Q(s, n(s(x))) 3 Q(s, n(s)) - e, for some parameter e.
  • s is e-accurate w.r.t. O in such case.
  • d the sensing system to fail with some small probability d.
  • s is Probably (w.p. of at least 1 - d), Approximately (up to e), Correct, or PAC for short (borrowing Valiant’s PAC learning terminology).
  • Definition 17 (PAC sensing system) Let ((ei , di),..., (e*, ⁇ 3 ⁇ 4)) be a set of
  • a sensing system positions a set of objects, O, in an e-ego-accurate way, if for every o E O, the (relative) error between p(o) and p(o) is at most e.
  • the following example demonstrates that an e-ego-accurate sensing state does not guarantee PAC sensing system with respect to every reasonable Q. Indeed, consider a scenario in which the host vehicle drives at a speed of 30 m/s, and there is a stopped vehicle 150 meters in front of it.
  • the sensing system may be e-ego-accurate for a rather small value of e (less than 3.5% error), and yet, for any reasonable O function, the values of Q are completely different since we are confusing between a situation in which we need to brake strongly and a situation in which we do not need to brake strongly.
  • Definition 18 (semantic units) A lane center is a simple natural curve , namely, it is a
  • the requirements from a sensing system both in terms of comfort and safety, have been described.
  • an approach for building a sensing system that meets these requirements while being scalable is described.
  • the first is long range, 360 degrees coverage, of the scene based on cameras.
  • the three main advantages of cameras are: (1) high resolution, (2) texture, (3) price.
  • the low price enables a scalable system.
  • the texture enables to understand the semantics of the scene, including lane marks, traffic light, intentions of pedestrians, and more.
  • the high resolution enables a long range of detection.
  • detecting lane marks and objects in the same domain enables excellent semantic lateral accuracy.
  • the two main disadvantages of cameras are: (1) the information is 2D and estimating longitudinal distance is difficult, (2) sensitivity to lighting conditions (low sun, bad weather). We overcome these difficulties using the next two components of our system.
  • the second component of our system is a semantic high-defmition mapping technology, called Road Experience Management (REM) (which involves navigation based on target trajectories predetermined and stored for road segments along with an ability to determine precise locations along the target trajectories based on the location (e.g., in images) of recognized landmarks identified in the environment of the host vehicle).
  • REM Road Experience Management
  • a common geometrical approach to map creation is to record a cloud of 3D points (obtained by a lidar) in the map creation process, and then, localization on the map is obtained by matching the existing lidar points to the ones in the map.
  • There are several disadvantages of this approach First, it requires a large memory per kilometer of mapping data, as we need to save many points.
  • the autonomous vehicles can receive the small sized mapping data over existing
  • REM may be used for several purposes. First, it gives us a foresight on the static structure of the road (we can plan for a highway exit way in advance). Second, it gives us another source of accurate information of all of the static information, which together with the camera detections yields a robust view of the static part of the world. Third, it solves the problem of lifting the 2D information from the image plane into the 3D world as follows. The map describes all of the lanes as curves in the 3D world. Localization of the ego vehicle on the map enables to trivially lift every object on the road from the image plane to its 3D position. This yields a positioning system that adheres to the accuracy in semantic units. A third component of the system may be complementary radar and lidar systems. These systems may serve two purposes. First, they can offer extremely high levels of accuracy for augmenting safety. Second, they can give direct measurements on speed and distances, which further improves the comfort of the ride.
  • w [Y mifact, Y max ] ® l + , mapping the longitudinal position Y into a positive lane width value.
  • the second generalization deals with two-way roads, in which there can be two cars driving at opposite directions.
  • the already established RSS definition is still valid, with the minor generalization of“safe distance” to oncoming traffic.
  • Controlled junctions that use traffic lights to dictate the flow of traffic, may be fully handled by the concepts of route priority and two-way roads.
  • Unstructured roads for example parking areas
  • RSS is still valid for this case, where the only needed modification is a way to define virtual routes and to assign each car to (possibly several) routes.
  • route priority states that if routes n, r 2 overlap, and n has priority over r 2 , then a vehicle coming from n that enters into the frontal corridor of a vehicle that comes from r is not considered to perform a cut-in.
  • n,... ,n be the routes defining the road’s structure.
  • n, r 2 the routes defining the road’s structure.
  • r ⁇ is the prioritized route. For example, suppose that n is a highway lane and r 2 is a merging lane. Having defined the route-based coordinate systems for each route, a first observation is that we can consider any maneuver in any route’s coordinate system.
  • the relevant lane has been defined as the one whose center is closest to the cut-in position. We can now reduce our to consideration of this lane (or, in the case of symmetry, deal with the two lanes separately, as in Definition 22).
  • the term“heading” denotes the arc tangent (in radians) of the lateral velocity divided by the longitudinal velocity.
  • Definition 23 ((/n, mi, /r )-Winning by Correct Driving Direction) Assume a, d are driving in opposite directions, namely vi ,i0ng ⁇ V2 ,iong ⁇ 0. Let xi, hi be their lateral positions and headings, w.r.t. the lane. We say that c (m ⁇ , mi, /r )-Wins by Correct Driving Direction if all of the following conditions hold:
  • Definition 25 (Safe Longitudinal Distance - Two-Way Traffic) A longitudinal distance between a car a and another car a which are driving in opposite directions and are both in the
  • C was not braking at a power of at least RBP .
  • Such rules may be applied during the planning phase; e.g., within a set of programmed instructions or within a trained model such that a proposed navigational action is developed by the system already in compliance with the rules.
  • a driving policy module may account for or be trained with, for example, one or more navigational rules upon which RSS is based.
  • the RSS safety constraint may be applied as a filter layer through which all proposed navigational actions proposed by the planning phase are tested against the relevant accident liability rules to ensure that the proposed navigational actions are in compliance. If a particular action is in compliance with the RSS safety constraint, it may be implemented. Otherwise, if the proposed navigational action is not in compliance with the RSS safety constraint (e.g., if the proposed action could result in accident liability to the host vehicle based on one or more of the above-described rules), then the action is not taken.
  • a particular implementation may include a navigation system for a host vehicle.
  • the host vehicle may be equipped with an image capture device (e.g., one or more cameras such as any of those described above) that, during operation, captures images representative of an environment of the host vehicle.
  • an image capture device e.g., one or more cameras such as any of those described above
  • a driving policy may take in a plurality of inputs and output a planned navigational action for accomplishing a navigational goal of the host vehicle.
  • the driving policy may include a set of programmed instructions, a trained network, etc., that may receive various inputs (e.g., images from one or more cameras showing the surroundings of the host vehicle, including target vehicles, roads, objects, pedestrians, etc.; output from LIDAR or RADAR systems; outputs from speed sensors, suspension sensors, etc.; information representing one or more goals of the host vehicle-e.g., a navigational plan for delivering a passenger to a particular location, etc.). Based on the input, the processor may identify a target vehicle in the environment of the host vehicle, e.g., by analyzing camera images, LIDAR output, RADAR output, etc.
  • various inputs e.g., images from one or more cameras showing the surroundings of the host vehicle, including target vehicles, roads, objects, pedestrians, etc.; output from LIDAR or RADAR systems; outputs from speed sensors, suspension sensors, etc.; information representing one or more goals of the host vehicle-e.g., a navigational plan for delivering a passenger
  • the processor may identify a target vehicle in the environment of the host vehicle by analyzing one or more inputs, such as one or more camera images, LIDAR output, and/or RADAR output. Further, in some embodiments, the processor may identify a target vehicle in the environment of the host vehicle based on an agreement of a majority or combination of sensor inputs (e.g., by analyzing one or more camera images, LIDAR output, and/or RADAR output, and receiving a detection result identifying the target vehicle based on a majority agreement or combination of the inputs).
  • an output may be provided in the form of one or more planned navigational actions for accomplishing a navigational goal of the host vehicle.
  • the RSS safety constraint may be applied as a filter of the planned navigational actions. That is, the planned navigational action, once developed, can be tested against at least one accident liability rule (e.g., any of the accident liability rules discussed above) for determining potential accident liability for the host vehicle relative to the identified target vehicle. And, as noted, if the test of the planned navigational action against the at least one accident liability rule indicates that potential accident liability may exist for the host vehicle if the planned navigational action is taken, then the processor may cause the host vehicle not to implement the planned navigational action. On the other hand, if the test of the planned navigational action against the at least one accident liability rule indicates that no accident liability would result for the host vehicle if the planned navigational action is taken, then the processor may cause the host vehicle to implement the planned navigational action.
  • at least one accident liability rule e.g., any of the accident liability rules discussed above
  • the system may test a plurality of potential navigational actions against the at least one accident liability rule. Based on the results of the test, the system may filter the potential navigational actions to a subset of the plurality of potential navigational actions. For example, in some embodiments, the subset may include only the potential navigational actions for which the test against the at least one accident liability rule indicates that no accident liability would result for the host vehicle if the potential navigational actions were taken. The system may then score and/or prioritize the potential navigational actions without accident liability and select one of the navigational actions to implement based on, for example, an optimized score, or a highest priority. The score and/or priority may be based, for example, one or more factors, such as the potential navigational action viewed as being the safest, most efficient, the most comfortable to passengers, etc.
  • the determination of whether to implement a particular planned navigational action may also depend on whether a default emergency procedure would be available in a next state following the planned action. If a DEP is available, the RSS filter may approve the planned action. On the other hand, if a DEP would not be available, the next state may be deemed an unsafe one, and the planned navigational action may be rejected. In some embodiments, the planned navigational action may include at least one default emergency procedure.
  • One benefit of the described system is that to ensure safe actions by the vehicle, only the host vehicle’s actions relative to a particular target vehicle need be considered.
  • the planned action for the host vehicle may be tested for an accident liability rule sequentially with respect to the target vehicles in an influence zone in the vicinity of the host vehicle (e.g., within 25 meters, 50 meters, 100 meters, 200 meters, etc.).
  • the at least one processor may be further programmed to: identify, based on analysis of the at least one image representative of an environment of the host vehicle (or based on LIDAR or RADAR information, etc.), a plurality of other target vehicles in the environment of the host vehicle and repeat the test of the planned navigational action against at least one accident liability rule for determining potential accident liability for the host vehicle relative to each of the plurality of other target vehicles. If the repeated tests of the planned navigational action against the at least one accident liability rule indicate that potential accident liability may exist for the host vehicle if the planned navigational action is taken, then the processor may cause the host vehicle not to implement the planned navigational action.
  • the processor may cause the host vehicle to implement the planned navigational action.
  • the at least one accident liability rule includes a following rule defining a distance behind the identified target vehicle within which the host vehicle may not proceed without a potential for accident liability.
  • the at least one accident liability rule includes a leading rule defining a distance forward of the identified target vehicle within which the host vehicle may not proceed without a potential for accident liability.
  • the test may be applied to more than one planned navigational action.
  • the at least one processor based on application of at least one driving policy may determine two or more planned navigational actions for accomplishing a navigational goal of the host vehicle. In these situations, the processor may test each of the two or more planned navigational actions against at least one accident liability rule for determining potential accident liability.
  • the processor may cause the host vehicle not to implement the particular one of the planned navigational actions.
  • the processor may identify the particular one of the two or more planned navigational actions as a viable candidate for implementation. Next, the processor may select a navigational action to be taken from among the viable candidates for
  • an accident liability tracking system for a host vehicle may include at least one processing device programmed to receive, from an image capture device, at least one image representative of an environment of the host vehicle and analyze the at least one image to identify a target vehicle in the environment of the host vehicle. Based on analysis of the at least one image, the processor may include programming to determine one or more characteristics of a navigational state of the identified target vehicle.
  • the navigational state may include various operational
  • the processor may compare the determined one or more characteristics of the navigational state of the identified target vehicle to at least one accident liability rule (e.g., any of the rules described above, such as winning by lateral velocity, directional priority, winning by proximity to lane center, following or leading distance and cut-in, etc.). Based on comparison of the state to one or more rules, the processor may store at least one value indicative of potential accident liability on the part of the identified target vehicle.
  • at least one accident liability rule e.g., any of the rules described above, such as winning by lateral velocity, directional priority, winning by proximity to lane center, following or leading distance and cut-in, etc.
  • the processor may provide an output of the stored at least one value (e.g., via any suitable data interface, either wired or wireless).
  • an output may be provided, for example, after an accident between the host vehicle and at least one target vehicle, and the output may be used for or may otherwise provide an indication of liability for the accident.
  • the at least one value indicative of potential accident liability may be stored at any suitable time and under any suitable conditions.
  • the at least one processing device may assign and store a collision liability value for the identified target vehicle if it is determined that the host vehicle cannot avoid a collision with the identified target vehicle.
  • the accident liability tracking capability is not limited to a single target vehicle, but rather can be used to track potential accident liability for a plurality of encountered target vehicles.
  • the at least one processing device may be programmed to detect a plurality of target vehicles in the environment of the host vehicle, determine navigational state characteristics for each of the plurality of target vehicles, and determine and store values indicative of potential accident liability on the part of respective ones of the plurality of target vehicles based on comparisons of the respective navigational state characteristics for each of the target vehicles to the at least one accident liability rule.
  • the accident liability rules used as the basis for liability tracking may include any of the rules described above or any other suitable rule.
  • the at least one accident liability rule may include a lateral velocity rule, a lateral position rule, a driving direction priority rule, a traffic light-based rule, a traffic sign-based rule, a route priority rule, etc.
  • the accident liability tracking function may also be coupled with safe navigation based on RSS considerations (e.g., whether any action of the host vehicle would result in potential liability for a resulting accident).
  • navigation can also be considered in terms of vehicle navigational states and a determination of whether a particular, future navigational state is deemed safe (e.g., whether a DEP exists such that accidents may be avoided or any resulting accident will not be deemed the fault of the host vehicle, as described in detail above).
  • the host vehicle can be controlled to navigate from safe state to safe state.
  • the driving policy may be used to generate one or more planned navigational actions, and those actions may be tested by determining if the predicted future states corresponding to each planned action would offer a DEP. If so, the planned navigational action or actions providing the DEP may be deemed safe and may qualify for implementation.
  • a navigation system for a host vehicle may include at least one processing device programmed to: receive, from an image capture device, at least one image representative of an environment of the host vehicle; determine, based on at least one driving policy, a planned navigational action for accomplishing a navigational goal of the host vehicle; analyze the at least one image to identify a target vehicle in the environment of the host vehicle; test the planned navigational action against at least one accident liability rule for determining potential accident liability for the host , vehicle relative to the identified target vehicle; if the test of the planned navigational action against the at least one accident liability rule indicates that potential accident liability may exists for the host vehicle if the planned navigational action is taken, then cause the host vehicle not to implement the planned navigational action; and if the test of the planned navigational action against the at least one accident liability rule indicates that no accident liability would result for the host vehicle if the planned navigational action is taken, then cause the host vehicle to implement the planned navigational action.
  • a navigation system for a host vehicle may include at least one processing device programmed to: receive, from an image capture device, at least one image representative of an environment of the host vehicle; determine, based on at least one driving policy, a plurality of potential navigational actions for the host vehicle; analyze the at least one image to identify a target vehicle in the environment of the host vehicle; test the plurality of potential navigational actions against at least one accident liability rule for determining potential accident liability for the host vehicle relative to the identified target vehicle; select one of the potential navigational actions for which the test indicates that no accident liability would result for the host vehicle if the selected potential navigational action is taken; and cause the host vehicle to implement the selected potential navigational action.
  • the selected potential navigational action may be selected from a subset of the plurality of potential navigational actions for which the test indicates that no accident liability would result for the host vehicle if any of the subset of the plurality of potential navigational action were taken. Further, in some instances, the selected potential navigational action may be selected according to a scoring parameter.
  • a system for navigating a host vehicle may include at least one processing device programmed to receive, from an image capture device, at least one image
  • the processor may also analyze the at least one image to identify a target vehicle in the environment of the host vehicle; determine a next-state distance between the host vehicle and the target vehicle that would result if the planned navigational action was taken; determine a current maximum braking capability of the host vehicle and a current speed of the host vehicle; determine a current speed of the target vehicle and assume a maximum braking capability of the target vehicle based on at least one recognized characteristic of the target vehicle; and implement the planned navigational action if, given the maximum braking capability of the host vehicle and current speed of the host vehicle, the host vehicle can be stopped within a stopping distance that is less than the determined next-state distance summed together with a target vehicle travel distance determined based on the current speed of the target vehicle and the assumed maximum braking capability of the target vehicle.
  • the stopping distance may further include a distance over which the host vehicle travels during a reaction time without braking.
  • the recognized characteristic of the target vehicle upon which the maximum braking capability of the target vehicle is determined may include any suitable characteristic.
  • the characteristic may include a vehicle type (e.g., motorcycle, car, bus, truck, each of which may be associated with different braking profiles), vehicle size, a predicted or known vehicle weight, a vehicle model (e.g., that may be used to look up a known braking capability), etc.
  • the safe state determination may be made relative to more than one target vehicle.
  • a safe state determination (based on distance and braking capabilities) may be based on two or more identified target vehicles leading a host vehicle. Such a determination may be useful especially where information regarding what is ahead of the foremost target vehicle is not available.
  • it may be assumed for purposes of determining a safe state, safe distance, and/or available DEP that the foremost detectable vehicle will experience an imminent collision with an immovable or nearly immovable obstacle, such that the target vehicle following may reach a stop more quickly than its own braking profile allows (e.g., the second target vehicle may collide with a first, foremost vehicle and therefore reach a stop more quickly than expected max braking conditions).
  • such a safe state to safe state navigation system may include at least one processing device programmed to receive, from an image capture device, at least one image representative of an environment of the host vehicle.
  • the image information captured by an image capture device e.g., a camera
  • the image information used to navigate may even originate from a LIDAR or RADAR system, rather than from an optical camera.
  • the at least one processor may determine, based on at least one driving policy, a planned navigational action for accomplishing a navigational goal of the host vehicle.
  • the processor may analyze the at least one image (e.g., obtained from any of a camera, a RADAR, a LIDAR, or any other device from which an image of the environment of the host vehicle may be obtained, whether optically based, distance map-based, etc.) to identify a first target vehicle ahead of the host vehicle and a second target vehicle ahead of the first target vehicle.
  • the processor may then determine a next-state distance between the host vehicle and the second target vehicle that would result if the planned navigational action was taken.
  • the processor may determine a current maximum braking capability of the host vehicle and a current speed of the host vehicle.
  • the processor may implement the planned navigational action if, given the maximum braking capability of the host vehicle and the current speed of the host vehicle, the ' host vehicle can be stopped within a stopping distance that is less than the determined next-state distance between the host vehicle and the second target vehicle.
  • the host vehicle processor determines that there is enough distance to stop in a next-state distance between the leading visible target vehicle and the host vehicle, without collision or without collision for which responsibility would attach to the host vehicle and assuming the leading visible target vehicle will suddenly at any moment come to a complete stop, then the processor of the host vehicle may take the planned navigational action. On the other hand, if there would be insufficient room to stop the host vehicle without collision, then the planned navigational action may not be taken.
  • next-state distance may be used as a benchmark in some embodiments, in other cases, a different distance value may be used to determine whether to take the planned navigational action.
  • the actual distance in which the host vehicle may need to be stopped to avoid a collision may be less than the predicted next-state distance. For example, where the leading, visible target vehicle is followed by one or more other vehicles (e.g., the first target vehicle in the example above), the actual predicted required stopping distance would be the predicted next-state distance less the length of the target vehicle(s) following the leading visible target vehicle.
  • the host vehicle processor can evaluate the next-state distance less the summed lengths of any intervening target vehicles between the host vehicle and the leading, visible/detected target vehicle to determine whether there would be sufficient space to bring the host vehicle to a halt under max braking conditions without a collision.
  • the benchmark distance for evaluating a collision between the host vehicle and one or more leading target vehicles may be greater than the predicted next-state distance.
  • the leading visible/detected target vehicle may come to a quick, but not immediate stop, such that the leading visible/detected target vehicle travels a short distance after the assumed collision. For example, if that vehicle hits a parked car, the colliding vehicle may still travel some distance before coming to a complete stop. The distance traveled after the assumed collision may be less than an assumed or determined minimum stopping distance for the relevant target vehicle.
  • the processor of the host vehicle may lengthen the next-state distance in its evaluation of whether to take the planned navigational action.
  • the next-state distance may be increased by 5%, 10%, 20%, etc. or may be supplemented with a predetermined fixed distance (10 m, 20 m, 50 m, etc.) to account for a reasonable distance that the leading/visible target vehicle may travel after an assumed imminent collision.
  • a predetermined fixed distance 10 m, 20 m, 50 m, etc.
  • next-state distance in addition to lengthening the next-state distance in the evaluation by an assumed distance value, the next-state distance may be modified by both accounting for a distance traveled after collision by the leading visible/detected target vehicle and the lengths of any target vehicles following the leading visible/detected target vehicle (which may be assumed to pile up with the leading visible/detected vehicle after its sudden stop).
  • the host vehicle may continue to account for the braking capability of one or more leading vehicles in its determination.
  • the host vehicle processor may continue to determine a next-state distance between the host vehicle and the first target vehicle (e.g., a target vehicle following the leading visible/detected target vehicle) that would result if the planned navigational action was taken; determine a current speed of the first target vehicle and assume a maximum braking capability of the first target vehicle based on at least one recognized characteristic of the first target vehicle; and not implement the planned navigational action if, given the maximum braking capability of the host vehicle and the current speed of the host vehicle, the host vehicle cannot be stopped within a stopping distance that is less than the determined next-state distance between the host vehicle and the first target vehicle summed together with a first target vehicle travel distance determined based on the current speed of the first target vehicle and the assumed maximum braking capability of the first target vehicle.
  • the recognized characteristic of the first target vehicle may include a vehicle type, a vehicle size, a vehicle model, etc.
  • the host vehicle may determine that a collision is imminent and unavoidable.
  • the processor of the host vehicle may be configured to select a navigational action (if available) for which the resulting collision would result in no liability to the host vehicle.
  • the processor of the host vehicle may be configured to select a navigational action that would offer less potential damage to the host vehicle or less potential damage to a target object than the current trajectory or relative to one or more other navigational options.
  • the host vehicle processor may select a navigational action based on considerations of the type of object or objects for which a collision is expected.
  • the action offering the lower potential damage to the host vehicle may be selected.
  • the action offering the lower potential damage to the host vehicle e.g., the action resulting in a collision with the moving car
  • the action offering the lower potential damage to the host vehicle may be selected.
  • the action offering any alternative to colliding with a pedestrian may be selected.
  • the system for navigating a host vehicle may include at least one processing device programmed to receive, from an image capture device, at least one image representative of an environment of the host vehicle (e.g., a visible image, LIDAR image, RADAR image, etc.); receive from at least one sensor an indicator of a current navigational state of the host vehicle; and determine, based on analysis of the at least one image and based on the indicator of the current navigational state of the host vehicle, that a collision between the host vehicle and one or more objects is unavoidable.
  • the processor may evaluate available alternatives.
  • the processor may determine, based on at least one driving policy, a first planned navigational action for the host vehicle involving an expected collision with a first object and a second planned navigational action for the host vehicle involving an expected collision with a second object.
  • the first and second planned navigational actions may be tested against at least one accident liability rule for determining potential accident liability. If the test of the first planned navigational action against the at least one accident liability rule indicates that potential accident liability may exist for the host vehicle if the first planned navigational action is taken, then the processor may cause the host vehicle not to implement the first planned navigational action.
  • the processor may cause the host vehicle to implement the second planned navigational action.
  • the objects may include other vehicles or non-vehicle objects (e.g., road debris, trees, poles, signs, pedestrians, etc.).
  • a host vehicle may avoid taking an action that would result in blame attributable to the host vehicle for a resulting accident if the action is taken.
  • Figs. 28A and 28B illustrate example following scenarios and rules.
  • the region surrounding vehicle 2804 e.g., a target vehicle
  • vehicle 2802 e.g., a host vehicle
  • vehicle 2802 must maintain a minimum safe distance by remaining in the region surrounding vehicle 2802.
  • Fig. 28B if vehicle 2804 brakes, then vehicle 2802 will be at fault if there is an accident.
  • Figs. 29A and 29B illustrate example blame in cut-in scenarios.
  • safe corridors around vehicle 2902 determine the fault in cut-in maneuvers.
  • vehicle 2902 is cutting in front of vehicle 2902, violating the safe distance (depicted by the region surrounding vehicle 2902) and therefore is at fault.
  • vehicle 2902 is cutting in front of vehicle 2902, but maintains a safe distance in front of vehicle 2904.
  • Figs. 30A and 30B illustrate example blame in cut-in scenarios.
  • safe corridors around vehicle 3004 determine whether vehicle 3002 is at fault.
  • vehicle 3002 is traveling behind vehicle 3006 and changes into the lane in which target vehicle 3004 is traveling. In this scenario, vehicle 3002 violates a safe distance and therefore is at fault if there is an accident.
  • vehicle 3002 cuts in behind vehicle 3004 and maintains a safe distance.
  • Figs. 31 A-3 ID illustrate example blame in drifting scenarios.
  • the scenario starts with a slight lateral maneuver by vehicle 3104, cutting-in to the wide corridor of vehicle 3102.
  • vehicle 3104 continues cutting into the normal corridor of the vehicle 3102, violating a safe distance region.
  • Vehicle 3104 is to blame if there is an accident.
  • Fig. 31C vehicle 3104 maintains its initial position, while vehicle 3102 moves laterally“forcing” a violation of ae normal safe distance corridor.
  • Vehicle 3102 is to blame if there is an accident.
  • Fig. 3 IB vehicle 3102 and 3104 move laterally towards each other. The blame is shared by both vehicles if there is an accident.
  • Figs. 32A and 32B illustrate example blame in two-way traffic scenarios.
  • vehicle 3202 overtakes vehicle 3206, and vehicle 3202 has performed a cut-in maneuver maintaining a safe distance from vehicle 3204. If there is an accident, vehicle 3204 is to blame for not braking with reasonable force.
  • vehicle 3202 cuts- ⁇ h without keeping safe longitudinal distance from vehicle 3204. In case of an accident, vehicle 3202 is to blame.
  • Figs. 33A and 33B illustrate example blame in two-way traffic scenarios.
  • vehicle 3302 drifts into the path of oncoming vehicle 3204, maintaining a safe distance.
  • vehicle 3204 is to blame for not braking with reasonable force.
  • Fig. 33B vehicle 3202 drifts into the path of the oncoming vehicle 3204, violating a safe longitudinal distance. In case of an accident, vehicle 3204 is to blame.
  • Figs. 34A and 34B illustrate example blame in route priority scenarios.
  • vehicle 3202 runs a stop sign.
  • Blame is attributed to vehicle 3202 for not respecting the priority assigned to vehicle 3204 by the traffic light.
  • Fig. 34B although vehicle 3202 did not have priority, it was already in the intersection when vehicle 3204’s light turned green. If vehicle 3204 hits 3202, vehicle 3204 would be to blame.
  • Figs. 35A and 35B illustrate example blame in route priority scenarios.
  • vehicle 3502 backing-up into the path of an oncoming vehicle 3504.
  • Vehicle 3502 performs a cut-in maneuver maintaining a safe distance.
  • vehicle 3504 is to blame for not braking with reasonable force.
  • Fig. 35B vehicle 3502 car cuts-in without keeping a safe longitudinal distance.
  • vehicle 3502 is to blame.
  • Figs. 36A and 36B illustrate example blame in route priority scenarios.
  • vehicle 3602 and vehicle 3604 are driving in the same direction, while vehicle 3602 turns left across the path of vehicle 3604.
  • Vehicle 3602 performs cut-in maneuver maintaining safe distance.
  • vehicle 3604 is to blame for not braking with reasonable force.
  • Fig. 36B vehicle 3602 cuts-in without keeping safe longitudinal distance. In case of an accident, vehicle 3602 is to blame.
  • Figs. 37A and 37B illustrate example blame in route priority scenarios.
  • vehicle 3702 wants to turn left, but must give way to the oncoming vehicle 3704.
  • Vehicle 3702 turns left, violating safe distance with respect to vehicle 3704.
  • Blame is on vehicle 3702.
  • vehicle 3702 turns left, maintaining a safe distance with respect to vehicle 3704.
  • vehicle 3704 is to blame for not braking with reasonable force.
  • Figs. 38A and 38B illustrate example blame in route priority scenarios.
  • vehicle 3802 and vehicle 3804 are driving straight, and vehicle 3802 has a stop sign. Vehicle 3802 enters the intersection, violating a safe distance with respect to vehicle 3804. Blame is on vehicle 3802.
  • Fig. 38B vehicle 3802 enters the intersection while maintaining a safe distance with respect to vehicle 3804.
  • Figs. 39A and 39B illustrate example blame in route priority scenarios.
  • vehicle 3902 wants to turn left, but must give way to vehicle 3904 coming from its right. Vehicle 3902 enters the intersection, violating the right-of-way and a safe distance with respect to vehicle 3904. Blame is on vehicle 3902.
  • Fig. 39B vehicle 3902 enters the intersection while maintaining the right-of-way and a safe distance with respect to vehicle 3904. In case of an accident, vehicle 3904 is to blame for not braking with reasonable force.
  • Figs. 40A and 40B illustrate example blame in traffic light scenarios. In Fig. 40A, vehicle 4002 is running a red light.
  • Blame is attributed to vehicle 4002 for not respecting the priority assigned to vehicle 4004 by the traffic light.
  • Fig. 40B although vehicle 4002 did not have priority, it was already in the intersection when the light for vehicle 4004 turned green. If vehicle 4004 hits vehicle 4002, vehicle 4004 would be to blame.
  • Figs. 41 A and 4 IB illustrate example blame in traffic light scenarios.
  • Vehicle 4102 is turning left across the path of the oncoming vehicle 4104.
  • Vehicle 4104 has priority.
  • Fig. 41 vehicle 4102 turns left, violating a safe distance with respect to vehicle 4104.
  • Blame is attributed to vehicle 4102.
  • Fig. 4 IB vehicle 4102 turns left, maintaining a safe distance with respect to vehicle 4104.
  • vehicle 4104 is to blame for not braking with reasonable force.
  • Figs. 42A and 42B illustrate example blame in traffic light scenarios.
  • vehicle 4202 is turning right, cutting into the path of vehicle 4204, which is driving straight. Right-on-red is assumed to be a legal maneuver, but vehicle 4204 has right of way, as vehicle 4202 violates a safe distance with respect to vehicle 4204. Blame is attributed to vehicle 4202.
  • Fig. 42B vehicle 4202 turns right, maintaining a safe distance with respect to vehicle 4204. In case of an accident, vehicle 4204 is to blame for not braking with reasonable force.
  • Figs. 43A-43C illustrate example vulnerable road users (VRUs) scenarios.
  • VRUs vulnerable road users
  • Fig. 43A vehicle 4302 cuts into the path of an animal (or VRU) while maintaining safe distance and ensuring an accident can be avoided.
  • Fig. 43B vehicle 4302 cuts into the path of an animal (or VRU) violating safe distance.
  • Blame is attributed to vehicle 4302.
  • Fig. 43C vehicle 4302 notices the animal and stops, giving the animal sufficient time to stop. If the animal hits the car, the animal is to blame.
  • Figs. 44A-44C illustrate example vulnerable road users (VRUs) scenarios.
  • VRUs vulnerable road users
  • vehicle 4402 is turning left at a signalized intersection and encounters a pedestrian in the crosswalk.
  • Vehicle 4402 has a red light and the VRU has a green.
  • Vehicle 4402 is at fault.
  • vehicle 4402 has a green light, and the VRU has a red light. If the VRU enters the crosswalk, the VRU is at fault.
  • Fig. 44C vehicle 4402 has a green light, and the VRU has a red light. If the VRU was already in the crosswalk, vehicle 4402 is it fault.
  • Figs. 45A-45C illustrate example vulnerable road users (VRUs) scenarios.
  • VRUs vulnerable road users
  • vehicle 4402 is turning right and encounters a cyclist.
  • the cyclist has a green light.
  • Vehicle 4502 is at fault.
  • Fig. 45B the cyclist has a red light. If the cyclist enters the intersection, the cyclist is at fault.
  • Fig. 45C the cyclist has a red light, but was already in the intersection. Vehicle 4502 is at fault.
  • Figs. 46A-46D illustrate example vulnerable road users (VRUs) scenarios.
  • VRUs vulnerable road users
  • Fig. 46A vehicle 4602 must always make sure to maintain safe distance and ensuring an accident can be avoided with a VRU.
  • Fig. 46B if vehicle 4602 does not maintain safe distance, vehicle 4602 is to blame.
  • Fig. 46C if vehicle 4602 does not maintain sufficiently low speed as to avoid colliding with a VRU that is potentially occluded by vehicle 5604, or drives above the legal limit, vehicle 4602 is to blame.
  • Fig. 46D in another scenario with a potential occlusion of a VRU by vehicle 4604, if vehicle 4602 maintains sufficiently low speed, but the VRUs speed is above a reasonable threshold, the VRU is to blame.
  • RSS defines a framework for multi-agent scenarios. Accidents with static objects, road departures, loss of control or vehicle failure are blamed on the host. RSS defines cautious maneuvers, which will not allow accidents with other objects, unless other objects maneuvers dangerously into the path of the host (in which case they are to blame). In the case of a sure-collision where blame is on the target, the host will apply its brakes. The system may consider evasive steering only if the maneuver is“cautious” (perceived not to cause another accident).
  • Non-collision incidents include accidents initiated by vehicle fires, potholes, falling objects, etc.
  • the blame may default to the host, except for scenarios which the host can avoid, such as potholes and falling objects, which may be classified as a“static object” scenario, assuming they become visible at safe distance or that a cautious evasive maneuver exists.
  • the host vehicle was stationary, the host is not to blame.
  • the target essentially performed a non-safe cut-in. For example, if a cyclist rides into a stationary car, the host is not to blame.
  • RSS also includes guidelines for assigning blame where the road is not structured clearly, such as parking lots or wide roundabouts without lane marks. In these unstructured road scenarios, blame is assigned by examining deviations of each vehicle from its path to determine if they allowed sufficient distance to allow other objects in the area to adjust.
  • RSS Responsibility Sensitive Safety
  • RSS is constructed by formalizing the following four rules: (1) keep a safe distance from the car in front, such that if the car in front brakes abruptly you will be able to stop in time; (2) keep a safe distance from cars on either side, and, when performing lateral maneuvers and cutting-in to another car’s trajectory, leave the other car enough space to respond; (3) respect“right- of-way” rules, where“right-of-way” is given not taken; and (4) be cautious of occluded areas, for example, an area behind a parked car.
  • the formal model should satisfy soundness, e.g., when the model says that the self-driving car is not responsible for an accident, the model should match the“common sense” of human judgement, and usefulness, e.g., a policy that guarantees to never cause accidents while still maintaining normal flow of traffic.
  • the model assigns responsibility on the self-driving car in fuzzy scenarios, possibly resulting in extra cautiousness, as long as the model is still useful.
  • the first basic concept formalized in the discussion of RSS is that the trailing car is always at fault if the trailing car hits a leading car.
  • two cars ⁇ y, c r may be driving at the same speed, one behind the other, along a straight road, without performing any lateral maneuvers.
  • cy the car at the front, suddenly brakes because of an obstacle appearing on the road, and manages to avoid it.
  • c r did not keep enough of a distance from cy, is not able to respond in time, and crashes into cy’s rear side.
  • the blame is on c r ; it is the responsibility of the rear car to keep safe distance from the front car, and to be ready for unexpected, yet reasonable, braking.
  • Definition 27 (Safe longitudinal distance— same direction): A longitudinal distance between a car c r that drives behind another car C f , where both cars are driving at the same direction, is safe with respect to a response time p if, for any braking of at most a maX brake performed by Cf, c r will accelerate by, at most, a max> accei during the response time and then will brake by at least a min, brake until a full stop then it will not collide with Cf.
  • the safe longitudinal distance depends on parameters: p, u m ax, accei ⁇ a max, brake» a min, brake ⁇
  • these parameters may be determined, for example, by regulation.
  • the parameters are set differently for a robotic car and a human driven car. For example, the response time of a robotic car may be smaller than that of a human driver and a robotic car may brake more effectively than a typical human driver, hence a mm brake may be a larger value for a robotic car than for a human-driven car.
  • the parameters may be set differently for different road conditions (wet road, ice, snow), which may be sensed, for example, by analysis of images acquired from one or more onboard cameras, or based on outputs from any other suitable sensors (e.g., windshield sensors, wheel slip sensors, etc.).
  • road conditions wet road, ice, snow
  • sensors e.g., windshield sensors, wheel slip sensors, etc.
  • Lemma 11 below calculates the safe distance as a function of the velocities of cy
  • Lemma 11 Let c r be a vehicle which is behind Cf on the longitudinal axis. Let p, a max, brake » a max accei » a min, brake be as in Definition 27. Let v r , V f be the longitudinal velocities of the cars. Then, the minimal safe longitudinal distance between the front-most point of c r and the rear-most point of c f i s:
  • the safe distance between cars that drive in opposite directions may be defined as the distance required so that, if both cars brake (after a given response time), then no crash will occur. However, it may be assumed that the car that drives in the opposite direction to the lane direction should brake harder than the one driving in the correct direction. This leads to the following definition.
  • Definition 28 (Safe longitudinal distance— opposite directions: Consider cars c 1; c 2 driving on a lane with longitudinal velocities v 1; v 2 , where v 2 ⁇ 0 and v x > 0 (the sign of the longitudinal velocity is according to the allowed direction of driving on the lane).
  • the longitudinal distance between the cars is safe with respect to a response time p, braking parameters a min _ brake , a min , b rake , correc t* and an acceleration parameter a raaX acce i, if in case c , c 2 will increase the absolute value of their velocities at rate a max accei during the response time, and from there on will decrease the absolute value of their velocities at rate a min> bra e correct , a min , b rake * respectively, until a full stop, then there will not be a collision.
  • Definition 29 (Dangerous Longitudinal Situation and Blame Time): Let time t be dangerous for cars c 1 ? c 2 if the distance between them at time t is non-safe (according to Definition 27 or Definition 28). Given a dangerous time t, its Blame Time, denoted t b , is the earliest non-dangerous time such that all the times in the interval (t b , t] are dangerous. For example, an accident can only happen at time t if it is dangerous, and thus the blame time of the accident is the blame time of t.
  • Ci acceleration must be at most a max acce
  • the following car is allowed to accelerate at a rate up to its maximum acceleration capability (e.g., full throttle level) during the reaction time period, but then, must decelerate at a rate associated with a braking rate between a selected minimum braking rate for the car and the car’s maximum braking rate.
  • the selected minimum braking rate may be regulation dependent or selected based on any other suitable criteria.
  • c 2 acceleration must be at least brake until reaching a full stop, after which, any non-negative acceleration is allowed. That is, the leading car is allowed to decelerate at a rate up to a deceleration rate associated with the leading car’s maximum braking capability.
  • c x acceleration must be at most a max accei during the interval [t b , t b + p) and at most— a mjn correct from time t b + P until reaching a full stop, after which any non-positive acceleration is allowed.
  • Car c may accelerate toward car ci at a maximum acceleration capability during the reaction time, but then, must decelerate at a rate associated with a braking rate between a selected minimum braking rate for the car and the car’s maximum braking rate.
  • the selected minimum braking rate may be regulation dependent or selected based on any other suitable criteria.
  • c 2 acceleration must be at least— a max acce] during the interval [t b , t b + p) and at most a min brake from time t b + p until reaching a full stop, after which any nonnegative acceleration is allowed.
  • car c 2 may accelerate toward car ci at a rate up to a maximum acceleration rate for car c 2 during car cj’s reaction time.
  • car c 2 must decelerate at a rate associated with a braking rate between a selected minimum braking rate for the car and the car’s maximum braking rate.
  • the selected minimum braking rate may be regulation dependent or selected based on any other suitable criteria.
  • the selected minimum braking rate of car c 2 may be different than the selected minimum braking rate of car ci (e.g., the minimum braking rate that must be applied by the car driving in the incorrect direction may be higher than the minimum braking rate required of the car driving in the correct direction).
  • the responsibility for accidents may be assigned to the agent(s) that did not respond properly to the dangerous situation preceding the collision.
  • the definition below may apply to scenarios in which no lateral maneuvers are performed (that is, each car keeps its lateral position in the lane).
  • the definition may be extended to the case in which cars can perform lateral maneuvers.
  • Definition 31 (Responsibility for an Accident— no lateral maneuvers): Consider an accident between c x and c 2 at time t and let t b be the corresponding blame time. Car c x is responsible for the accident if it did not follow the constraints defined by the“proper response to dangerous situations” (Definition 30) at some time in the interval (t b , t].
  • both c and c 2 share the responsibility for an accident (e.g., if both of them did not comply with the proper response constraints).
  • the RSS model may formally define responsibility when cars are performing lateral maneuvers.
  • a first example assumes a straight road on a planar surface, where the lateral, longitudinal axes are the x, y axes, respectively.
  • the longitudinal and lateral velocities may be the derivatives of the longitudinal and lateral positions on the straight virtual road obtained by a bijection between the actual curved road and a straight road.
  • accelerations may be second derivatives of positions.
  • a calculation of the lateral safe distance may be given in the lemma below.
  • the model may use modified definitions of Dangerous Situation and Blame Time.
  • Definition 34 (Dangerous Situation and Blame Time): Let time t be dangerous for cars c l5 c 2 if both the longitudinal and lateral distances between them are non-safe (according to Definition 27, Definition 28, and Definition 33). Given a dangerous time t, its Blame Time, denoted t b , is the earliest non-dangerous time such that all the times in the interval (t b , t] are dangerous. In this example, an accident may only happen at time t if it is dangerous, and in that case the blame time of the accident is the blame time of t.
  • both cars can do any lateral action as long as their lateral acceleration, a, satisfies
  • ci must have at least a minimum lateral acceleration in one direction
  • c 2 must have at least a minimum lateral acceleration in the opposite direction
  • c t may have any non-positive m- lateral-velocity and c 2 may have any non-negative m-lateral-velocity
  • c 2 did not behave correctly. Nevertheless, c 1 is expected to make an effort to avoid a potential collision, for example, by applying braking of at least a mjn brake evasive . This may reduce the duration of a dangerous situation (unless both cars are at a zero longitudinal and lateral velocity).
  • Definition 36 (Responsibility for an Accident): Consider, for example, an accident between ci and c 2 at time t and let 3 ⁇ 4 be the corresponding Blame Time. Car c may be responsible for the accident if it did not respond properly according to Definition 35 at some time in (3 ⁇ 4, t], as illustrated in Fig. 47A.
  • Fig. 47A the vertical lines around each car show the possible lateral position of the car if it will accelerate laterally during the response time and then will brake laterally.
  • the rectangles show the possible longitudinal positions of the car (e.g., if the car either brakes by a max, brake or accelerates during the response time and then will brake by a m in, brake).
  • the top two rows (rows a and b), before the blame time there was a safe lateral distance, hence the proper response is to brake laterally.
  • the parameters am l a x,ac ceh 3 ⁇ 4nax,accei, and a m ax, brake do not necessarily reflect a physical limitation, but instead they may represent an upper bound on reasonable behavior expected from road users. In some embodiments, based on these definitions, if a driver does not comply with these parameters at a dangerous time he immediately becomes responsible for the accident.
  • the definitions above hold for vehicles of arbitrary shapes, by taking the worst-case with respect to all points of each car.
  • the model may account for semitrailers or a car with an open door.
  • Fig. 47B shows exemplary road geometries including a roundabout 4706, junctions 4704 and 4708, and merges onto highways 4702.
  • one route, shown in solid line may have priority over others, shown in dashed line, and vehicles riding on that route have the right of way.
  • a route may be a subset of R 2 .
  • ci, c 2 are driving on different routes, n, r 2 .
  • the definitions are described solely with reference to n.
  • the lateral distance between ci and c 2 is safe if the restrictions of n, r 2 to the lateral intervals [xi mi ,,, Xi. max ], [X2 ,min , X2 ,max ] are at a distance of at least m.
  • the restriction of r, to the lateral intervals [x , min , Xi. max ] may be the subset of R 2 obtained by all points (x, y) e p for which the semantic lateral position of (x, y) is in the interval [xi ,min , x; ,max]
  • Definition 38 is an exemplary quantification of the ordering between two cars when no common longitudinal axis exists (e.g., if the cars are not driving one in front of the other).
  • Definition 38 (Longitudinal Ordering for Two Routes of Different Geometry): Consider, for example, ci, c 2 , 4710 and 4712, respectively, driving on routes n, r 2 , 4714 and 4716, respectively, that intersect as shown in Fig. 47C.
  • ci (vehicle 4710) is longitudinally in front of C2 (vehicle 4712) if either of the following holds: for every i, if both vehicles are on r, then ci is in front of C2 according to r,; or ci is outside G2 and C2 is outside n, and the longitudinal distance from ci to the set h P r 2 , with respect to n, is larger than the longitudinal distance from c 2 to the set n P r 2 , with respect to G2.
  • Fig. 47D is an exemplary illustration of Definition 39.
  • Frame 4720 is an exemplary safe situation in which car 4722 has priority because car 4724 must stop prior to entering the roadway.
  • Frame 4726 is another exemplary safe situation in which car 4722 is in front of car 4724, thus giving car 4724 time to stop if car 4722 stops or slows.
  • frame 4728 If car 4722 is at a full stop and car 4724 is at a full lateral stop, the situation is safe by the definition of item (3) of Definition 39.
  • Definition 40 (Dangerous & Blame Times, Proper Response, and Responsibility for Routes of Different Geometry): Consider, for example, vehicles ci, C2 driving on routes n, ft. Time t may be dangerous if both the lateral and longitudinal distances are non-safe (according to Definition 1 1 and Definition 13). The corresponding blame time may be the earliest non-dangerous time 3 ⁇ 4 such that all times in (3 ⁇ 4 radical t] are dangerous. The proper response of ci and/or C2 may depend on the situation immediately before the blame time: • If the lateral distance was safe, then both cars should respond according to the description of lateral safe distance in Definition 37.
  • both cars can drive normally if t-t b ⁇ p, and otherwise, both cars should brake laterally and longitudinally by at least a ⁇ jn brake , a min, brake (each one with respect to its own route).
  • a vehicle may encounter a situation involving a traffic light. It may not hold that“if one car’s route has the green light and the other car’s route has a red light, then the blame is on the one whose route has the red light.” Rather, consider for example the scenario depicted in Fig. 47F. Even if the car 4734’s route has a green light, it is not expected it to ignore car 4736 that is already in the intersection. The route that has a green light may have a priority over routes that have a red light. Therefore, the concept of a situation with a traffic light reduces to the route priority situation previously described. In some embodiments, the rule for route priority may be simplified conceptually as the right of way is given, not taken.
  • a vehicle may encounter unstructured roads, for example, as shown in Fig. 47G.
  • Fig. 47G Consider first the scenario 4718.
  • the partition of the road area to lanes is not well defined
  • the partition of the road to multiple routes is well defined. Since our definitions of responsibility only depend on the route geometry, they apply as is to such scenarios.
  • Definition 41 (Trajectories): Consider, for example, a vehicle c riding on some road.
  • a future trajectory of c may be represented as a function t : R + R 2 , where t (t) is the position of c in t seconds from the current time.
  • the tangent vector to the trajectory at t, denoted t (t), is the Jacobian of t at t.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Human Computer Interaction (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Mathematical Physics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Electromagnetism (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
  • Lighting Device Outwards From Vehicle And Optical Signal (AREA)
PCT/IB2019/000726 2018-08-14 2019-08-14 Systems and methods for navigating with safe distances Ceased WO2020035728A2 (en)

Priority Applications (19)

Application Number Priority Date Filing Date Title
EP21156813.4A EP3854646B8 (en) 2018-08-14 2019-08-14 Systems and methods for navigating with safe distances
EP21156822.5A EP3842304B1 (en) 2018-08-14 2019-08-14 Systems and methods for navigating with safe distances
JP2021507580A JP7609528B2 (ja) 2018-08-14 2019-08-14 安全な距離でナビゲートするためのシステム及び方法
CN201980043159.2A CN112601686B (zh) 2018-08-14 2019-08-14 具有安全距离的导航的系统和方法
CN202411207097.3A CN119078812A (zh) 2018-08-14 2019-08-14 具有安全距离的导航的系统和方法
KR1020217007561A KR102867125B1 (ko) 2018-08-14 2019-08-14 안전 거리로 항법하기 위한 시스템 및 방법
EP21156819.1A EP3842303B1 (en) 2018-08-14 2019-08-14 Systems and methods for navigating with safe distances
EP25167759.7A EP4606672A3 (en) 2018-08-14 2019-08-14 Systems and methods for navigating with safe distances
EP24200665.8A EP4474240A3 (en) 2018-08-14 2019-08-14 Systems and methods for navigating with safe distances
EP19779091.8A EP3787947B1 (en) 2018-08-14 2019-08-14 Systems and methods for navigating with safe distances
CN202511016204.9A CN120863620A (zh) 2018-08-14 2019-08-14 具有安全距离的导航的系统和方法
EP25167780.3A EP4596359A3 (en) 2018-08-14 2019-08-14 NAVIGATION SYSTEMS AND METHODS WITH SAFETY DISTANCES
US17/106,746 US11840258B2 (en) 2018-08-14 2020-11-30 Systems and methods for navigating with safe distances
US17/174,937 US12037019B2 (en) 2018-08-14 2021-02-12 Navigation with a safe longitudinal distance
US17/174,844 US11897508B2 (en) 2018-08-14 2021-02-12 Navigation with a safe lateral distance
US17/174,689 US12037018B2 (en) 2018-08-14 2021-02-12 Navigation relative to pedestrians at crosswalks
US17/208,180 US11932277B2 (en) 2018-08-14 2021-03-22 Navigation with a safe longitudinal distance
US18/750,716 US20250033669A1 (en) 2018-08-14 2024-06-21 Systems and methods for navigating with safe distances
JP2024220846A JP7808176B2 (ja) 2018-08-14 2024-12-17 安全な距離でナビゲートするためのシステム及び方法

Applications Claiming Priority (8)

Application Number Priority Date Filing Date Title
US201862718554P 2018-08-14 2018-08-14
US62/718,554 2018-08-14
US201862724355P 2018-08-29 2018-08-29
US62/724,355 2018-08-29
US201862772366P 2018-11-28 2018-11-28
US62/772,366 2018-11-28
US201862777914P 2018-12-11 2018-12-11
US62/777,914 2018-12-11

Related Child Applications (4)

Application Number Title Priority Date Filing Date
US17/106,746 Continuation US11840258B2 (en) 2018-08-14 2020-11-30 Systems and methods for navigating with safe distances
US17/174,844 Continuation US11897508B2 (en) 2018-08-14 2021-02-12 Navigation with a safe lateral distance
US17/174,689 Continuation US12037018B2 (en) 2018-08-14 2021-02-12 Navigation relative to pedestrians at crosswalks
US17/174,937 Continuation US12037019B2 (en) 2018-08-14 2021-02-12 Navigation with a safe longitudinal distance

Publications (2)

Publication Number Publication Date
WO2020035728A2 true WO2020035728A2 (en) 2020-02-20
WO2020035728A3 WO2020035728A3 (en) 2020-04-30

Family

ID=68072846

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2019/000726 Ceased WO2020035728A2 (en) 2018-08-14 2019-08-14 Systems and methods for navigating with safe distances

Country Status (6)

Country Link
US (6) US11840258B2 (https=)
EP (7) EP4596359A3 (https=)
JP (2) JP7609528B2 (https=)
KR (1) KR102867125B1 (https=)
CN (3) CN120863620A (https=)
WO (1) WO2020035728A2 (https=)

Cited By (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210179097A1 (en) * 2019-12-12 2021-06-17 Baidu Usa Llc Lane-attention: predicting vehicles' moving trajectories by learning their attention over lanes
WO2021168452A3 (en) * 2020-02-21 2021-10-28 Bluespace Al, Inc. Method for object avoidance during autonomous navigation
CN114148328A (zh) * 2020-09-08 2022-03-08 现代摩比斯株式会社 用于控制车辆驾驶的装置和方法
EP4019353A1 (en) * 2020-12-22 2022-06-29 Beijing Baidu Netcom Science And Technology Co. Ltd. Vehicle control method and apparatus, electronic device and self-driving vehicle
WO2022162463A1 (en) * 2021-01-27 2022-08-04 Foretellix Ltd. Techniques for providing concrete instances in traffic scenarios by a transformation as a constraint satisfaction problem
EP4039557A1 (en) * 2021-02-09 2022-08-10 Aptiv Technologies Limited Trajectory validation for autonomous driving
CN114895295A (zh) * 2022-04-19 2022-08-12 中国电子科技集团公司第十研究所 一种基于k近邻的通信散点关联加速方法及系统
GB2604222A (en) * 2021-01-28 2022-08-31 Motional Ad Llc Sampling-based maneuver realizer
CN115140089A (zh) * 2022-06-21 2022-10-04 重庆长安汽车股份有限公司 车辆的辅助驾驶方法、装置、车辆及存储介质
US11481607B2 (en) 2020-07-01 2022-10-25 International Business Machines Corporation Forecasting multivariate time series data
US20230014874A1 (en) * 2020-10-22 2023-01-19 Tencent Technology (Shenzhen) Company Limited Obstacle detection method and apparatus, computer device, and storage medium
JP2023018930A (ja) * 2021-07-28 2023-02-09 株式会社Ｎｔｔデータオートモビリジェンス研究所 シミュレータ、学習装置、及び車両制御装置
FR3130232A1 (fr) * 2021-12-09 2023-06-16 Psa Automobiles Sa Contrôle autonome de la vitesse d’un véhicule après un freinage d’urgence
FR3130229A1 (fr) * 2021-12-10 2023-06-16 Psa Automobiles Sa Procédé et dispositif de contrôle de trajectoire d’un véhicule autonome
US11780461B2 (en) 2021-02-09 2023-10-10 Aptiv Technologies Limited Lateral acceleration control for autonomous driving
WO2023194801A1 (en) * 2022-04-06 2023-10-12 Mobileye Vision Technologies Ltd. Steering limiters for vehicle navigation
WO2023245073A1 (en) * 2022-06-14 2023-12-21 Motional Ad Llc Method and system for controlling an autonomous vehicle
CN117320935A (zh) * 2021-03-15 2023-12-29 动态Ad有限责任公司 制动仲裁
CN117615948A (zh) * 2021-07-05 2024-02-27 株式会社电装 行驶控制系统、行驶控制装置、行驶控制方法、行驶控制程序
FR3141424A1 (fr) * 2022-11-02 2024-05-03 Psa Automobiles Sa Procédé et dispositif de contrôle de gestion des messages d’alertes pour un système de régulation adaptative de vitesse d’un véhicule
US12030485B2 (en) 2021-01-28 2024-07-09 Motional Ad Llc Vehicle operation using maneuver generation
EP4247680A4 (en) * 2020-11-19 2024-10-23 Mobileye Vision Technologies Ltd. Vehicle operation safety model compliance measurement
US12227205B2 (en) 2021-01-15 2025-02-18 Tusimple, Inc. Proactive lane change for autonomous vehicles
US12263840B2 (en) 2021-03-26 2025-04-01 Aptiv Technologies AG Longitudinal acceleration control for autonomous driving
US20250187598A1 (en) * 2023-12-12 2025-06-12 Mobileye Vision Technologies Ltd. Systems and methods for navigating a vehicle using coast control
US12454288B2 (en) * 2021-03-05 2025-10-28 Denso Corporation Processing method, processing system, and storage medium storing processing program
US12487347B2 (en) 2021-12-30 2025-12-02 BlueSpace.ai, Inc. Method for calibrating offsets between doppler-based sensors on a mobile platform
US12548442B2 (en) 2021-02-03 2026-02-10 Denso Corporation Processing device, processing method, processing system, and storage medium
US12566434B2 (en) 2021-02-03 2026-03-03 Denso Corporation Processing device, processing method, processing system, storage medium

Families Citing this family (175)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9557736B1 (en) * 2015-04-08 2017-01-31 Google Inc. Detecting street parked vehicles
US10507807B2 (en) * 2015-04-28 2019-12-17 Mobileye Vision Technologies Ltd. Systems and methods for causing a vehicle response based on traffic light detection
JP6712936B2 (ja) * 2016-09-23 2020-06-24 株式会社小松製作所 作業車両の管理システム及び作業車両の管理方法
DE102017202415A1 (de) * 2017-02-15 2018-08-16 Bayerische Motoren Werke Aktiengesellschaft Kollisionsvermeidung mit Querverkehr
WO2018189912A1 (ja) * 2017-04-14 2018-10-18 日産自動車株式会社 車両制御方法及び車両制御装置
DE102017208168B4 (de) * 2017-05-15 2024-10-31 Vitesco Technologies GmbH Verfahren zum Betreiben einer Steuereinrichtung eines Kraftfahrzeugs und Steuereinrichtung
US10007269B1 (en) * 2017-06-23 2018-06-26 Uber Technologies, Inc. Collision-avoidance system for autonomous-capable vehicle
DE102017220139A1 (de) * 2017-11-13 2019-05-16 Robert Bosch Gmbh Verfahren und Vorrichtung zum Bereitstellen einer Position wenigstens eines Objekts
KR102337011B1 (ko) * 2018-03-20 2021-12-13 모빌아이 비젼 테크놀로지스 엘티디 차량의 항법을 위한 시스템 및 방법
WO2019222452A1 (en) * 2018-05-16 2019-11-21 Burkin Donald Vehicle messaging system and method of operation thereof
US10909866B2 (en) * 2018-07-20 2021-02-02 Cybernet Systems Corp. Autonomous transportation system and methods
US11326888B2 (en) * 2018-07-25 2022-05-10 Uatc, Llc Generation of polar occlusion maps for autonomous vehicles
DE102018120198A1 (de) * 2018-08-20 2020-02-20 Dr. Ing. H.C. F. Porsche Aktiengesellschaft Luftfahrzeug
EP3626553A1 (en) * 2018-09-18 2020-03-25 Ningbo Geely Automobile Research & Development Co. Ltd. Brake performance optimizer
KR102637599B1 (ko) * 2018-10-08 2024-02-19 주식회사 에이치엘클레무브 차량간 통신 정보를 이용한 차선변경 제어장치 및 방법과, 그를 위한 성향 정보 산출 장치
US10627819B1 (en) * 2018-10-11 2020-04-21 Pony Ai Inc. On-site notification from autonomous vehicle for traffic safety
KR102604821B1 (ko) * 2018-11-09 2023-11-20 에스케이텔레콤 주식회사 차량의 위치 추정 장치 및 방법
FR3088590B1 (fr) * 2018-11-16 2020-10-23 Psa Automobiles Sa Regulation de la vitesse d’un vehicule, avec prise en compte de la volonte du conducteur dans un virage
JP7271950B2 (ja) * 2019-01-04 2023-05-12 トヨタ自動車株式会社 車両の制御装置
DE102019200828A1 (de) * 2019-01-24 2020-07-30 Robert Bosch Gmbh Hauptobjektauswahl für eine Assistenzfunktion oder automatisierte Fahrfunktion eines Fahrerassistenz- oder Fahrsystems eines Kraftfahrzeugs
FR3093057B1 (fr) * 2019-02-21 2021-02-19 Renault Sas Procédé de sécurisation d’un véhicule.
DE102019202586A1 (de) 2019-02-26 2020-08-27 Volkswagen Aktiengesellschaft Verfahren zum Betreiben eines Fahrerinformationssystems in einem Ego-Fahrzeug und Fahrerinformationssystem
DE102019202585A1 (de) 2019-02-26 2020-08-27 Volkswagen Aktiengesellschaft Verfahren zum Betreiben eines Fahrerinformationssystems in einem Ego-Fahrzeug und Fahrerinformationssystem
DE102019202591A1 (de) 2019-02-26 2020-08-27 Volkswagen Aktiengesellschaft Verfahren zum Betreiben eines Fahrerinformationssystems in einem Ego-Fahrzeug und Fahrerinformationssystem
DE102019202587A1 (de) * 2019-02-26 2020-08-27 Volkswagen Aktiengesellschaft Verfahren zum Betreiben eines Fahrerinformationssystems in einem Ego-Fahrzeug und Fahrerinformationssystem
DE102019202576A1 (de) 2019-02-26 2020-08-27 Volkswagen Aktiengesellschaft Verfahren zum Betreiben eines Fahrerinformationssystems in einem Ego-Fahrzeug und Fahrerinformationssystem
DE102019202580A1 (de) 2019-02-26 2020-08-27 Volkswagen Aktiengesellschaft Verfahren zum Betreiben eines Fahrerinformationssystems in einem Ego-Fahrzeug und Fahrerinformationssystem
DE102019202592A1 (de) 2019-02-26 2020-08-27 Volkswagen Aktiengesellschaft Verfahren zum Betreiben eines Fahrerinformationssystems in einem Ego-Fahrzeug und Fahrerinformationssystem
DE102019202578A1 (de) 2019-02-26 2020-08-27 Volkswagen Aktiengesellschaft Verfahren zum Betreiben eines Fahrerinformationssystems in einem Ego-Fahrzeug und Fahrerinformationssystem
GB2582262B (en) 2019-03-02 2022-09-28 Jaguar Land Rover Ltd Imaging system and method
JP7093738B2 (ja) * 2019-03-08 2022-06-30 本田技研工業株式会社 車両制御装置
JP7261635B2 (ja) * 2019-03-28 2023-04-20 本田技研工業株式会社 車両制御装置
JP2020164045A (ja) * 2019-03-29 2020-10-08 マツダ株式会社 車両走行制御装置
EP3953236B1 (en) * 2019-04-12 2023-06-07 Volvo Truck Corporation A method of determining an allowable vehicle state space for an articulated vehicle
CN111947673B (zh) * 2019-05-17 2022-09-06 北京京东振世信息技术有限公司 无人车路径控制方法、装置和系统
US11798291B2 (en) * 2019-05-30 2023-10-24 Robert Bosch Gmbh Redundancy information for object interface for highly and fully automated driving
US12288166B2 (en) * 2019-06-28 2025-04-29 Intel Corporation Assessment and response mechanism for autonomous systems
US11263809B2 (en) * 2019-09-06 2022-03-01 Shandong University TBM-mounted virtual reconstruction system and method for surrounding rock structure of tunnel
US11537127B2 (en) * 2019-09-12 2022-12-27 Uatc, Llc Systems and methods for vehicle motion planning based on uncertainty
US20200019177A1 (en) * 2019-09-24 2020-01-16 Intel Corporation Cognitive robotic systems and methods with fear based action/reaction
US11279349B2 (en) * 2019-09-26 2022-03-22 Intel Corporation Safety module, automated driving system, and methods thereof
CN119693914A (zh) * 2019-09-30 2025-03-25 北京航迹科技有限公司 预测行人的移动轨迹的系统和方法
US11273806B2 (en) * 2019-10-17 2022-03-15 Ford Global Technologies, Llc Enhanced collision mitigation
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
US11499838B2 (en) * 2019-10-25 2022-11-15 Here Global B.V. Method, system, and computer program product for providing traffic data
CN114766022A (zh) * 2019-11-06 2022-07-19 俄亥俄州创新基金会 使用多时域优化的车辆动力学和动力总成控制系统和方法
CN112818727B (zh) * 2019-11-18 2025-08-08 深圳引望智能技术有限公司 一种道路约束确定方法及装置
DE102019133680B3 (de) * 2019-12-10 2021-03-04 Audi Ag Verfahren und System zum Durchführen einer Rekuperation
EP4077083B1 (en) * 2019-12-18 2024-07-03 Volvo Truck Corporation A method for providing a positive decision signal for a vehicle
US11385642B2 (en) * 2020-02-27 2022-07-12 Zoox, Inc. Perpendicular cut-in training
EP4121329B1 (en) * 2020-03-18 2026-02-25 Electra Vehicles, Inc. Systems and methods for managing velocity profiles
JP7507587B2 (ja) * 2020-03-30 2024-06-28 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
US12058592B2 (en) * 2020-05-12 2024-08-06 Qualcomm Incorporated Vehicle-to-vehicle maneuver sharing and coordinating
DE102020112899A1 (de) * 2020-05-13 2021-11-18 Audi Aktiengesellschaft Verfahren und System zur vollständig automatischen Führung eines Kraftfahrzeugs und Kraftfahrzeug
US12100224B1 (en) 2020-05-21 2024-09-24 Zoox, Inc. Key point detection
US12236705B1 (en) * 2020-05-21 2025-02-25 Zoox, Inc. Pedestrian attribute and gesture detection
US20210389138A1 (en) * 2020-06-15 2021-12-16 Google Llc Vehicle Communication System for Optimizing Traffic Flow
JP7315904B2 (ja) * 2020-06-19 2023-07-27 トヨタ自動車株式会社 車両制御装置
US11823395B2 (en) * 2020-07-02 2023-11-21 Magna Electronics Inc. Vehicular vision system with road contour detection feature
FR3112326B1 (fr) * 2020-07-10 2022-06-24 Renault Sas Procédé de commande d’un véhicule automobile muni de moyens de conduite autonome
EP3951673A1 (en) * 2020-08-04 2022-02-09 Aptiv Technologies Limited Method and system of collecting training data suitable for training an autonomous driving system of a vehicle
WO2022043675A2 (en) 2020-08-24 2022-03-03 Unlikely Artificial Intelligence Limited A computer implemented method for the automated analysis or use of data
US11814075B2 (en) * 2020-08-26 2023-11-14 Motional Ad Llc Conditional motion predictions
HU231455B1 (hu) * 2020-09-03 2023-12-28 Vie Technology (Europe) Kft. Eljárás és elrendezés jármű automatikus vészfékezési folyamatának megfelelő időben történő elindítására és a hosszirányú mozgás szabályozására
KR20220052430A (ko) * 2020-10-20 2022-04-28 현대자동차주식회사 자율주행차량의 거동 제어 장치 및 그 방법
US11738772B1 (en) * 2020-12-18 2023-08-29 Zoox, Inc. Object avoidance with perceived safety subgoal
CN117136343A (zh) * 2020-12-23 2023-11-28 舍沃特航天航空公司 用于平衡自动感应交通工具的能源探测和观测时间的系统
JP7633807B2 (ja) * 2020-12-28 2025-02-20 株式会社Subaru 車両の運転制御システム
US11462021B2 (en) * 2021-01-13 2022-10-04 GM Global Technology Operations LLC Obstacle detection and notification for motorcycles
CN112874521B (zh) * 2021-01-22 2022-06-14 北京罗克维尔斯科技有限公司 一种车辆跟停的控制方法、装置及车辆
US12559128B2 (en) 2021-02-02 2026-02-24 Toyota Research Institute, Inc. Systems and methods for updating the parameters of a model predictive controller with learned operational and vehicle parameters generated using simulations and machine learning
US12459497B2 (en) 2021-02-02 2025-11-04 Toyota Research Institute, Inc. Systems and methods for updating the parameters of a model predictive controller with learned controls parameters generated using simulations and machine learning
US11975725B2 (en) * 2021-02-02 2024-05-07 Toyota Research Institute, Inc. Systems and methods for updating the parameters of a model predictive controller with learned external parameters generated using simulations and machine learning
US11993281B2 (en) 2021-02-26 2024-05-28 Nissan North America, Inc. Learning in lane-level route planner
EP4056441A1 (en) * 2021-03-12 2022-09-14 Aptiv Technologies Limited Back propagation planning for adas/ad motion planning and control
US12024207B2 (en) * 2021-03-15 2024-07-02 Ford Global Technologies, Llc Vehicle autonomous mode operating parameters
US20220306156A1 (en) * 2021-03-29 2022-09-29 Nissan North America, Inc. Route Planner and Decision-Making for Exploration of New Roads to Improve Map
CN112937608B (zh) * 2021-03-31 2022-06-21 吉林大学 一种基于轨迹预测的冰雪环境无人驾驶车辆一体化滚动决策方法、装置及存储介质
US11945441B2 (en) 2021-03-31 2024-04-02 Nissan North America, Inc. Explainability and interface design for lane-level route planner
US20220314792A1 (en) * 2021-04-06 2022-10-06 Ford Global Technologies, Llc Vehicle speed limiting
EP4071024B1 (en) * 2021-04-08 2025-07-02 Qualcomm Auto Ltd. A vehicle control system
US12084023B2 (en) * 2021-04-12 2024-09-10 Nissan Motor Co., Ltd. Braking control method and braking control device
US11958503B2 (en) * 2021-04-16 2024-04-16 Motional Ad Llc Techniques for navigating an autonomous vehicle based on perceived risk
KR102457914B1 (ko) * 2021-04-21 2022-10-24 숭실대학교산학협력단 심층강화학습기반 자율주행차량을 이용한 정체 현상 해결 방법, 이를 수행하기 위한 기록 매체 및 장치
JP7680254B2 (ja) * 2021-04-27 2025-05-20 トヨタ自動車株式会社 運転支援装置
EP4330108A4 (en) 2021-04-30 2025-01-01 Glüxkind Technologies Inc. TROLLEY FOR GUIDED AUTONOMOUS LOCOMOTION
JP7505443B2 (ja) * 2021-05-07 2024-06-25 トヨタ自動車株式会社 遠隔監視装置、遠隔監視システム、遠隔監視方法、及び遠隔監視プログラム
DE102021205633A1 (de) * 2021-06-02 2022-12-08 Zf Friedrichshafen Ag Fahrzeugsystem zur Durchführung einer Bremsung
JP7250070B2 (ja) * 2021-06-18 2023-03-31 本田技研工業株式会社 警告制御装置、移動体、警告制御方法、及びプログラム
KR20230015114A (ko) * 2021-07-22 2023-01-31 삼성전자주식회사 차량의 측방 카메라를 이용한 도로의 기울기 결정 방법 및 장치
CN113537606B (zh) * 2021-07-22 2023-05-30 上汽通用五菱汽车股份有限公司 事故预测方法、装置及计算机可读存储介质
US11724739B2 (en) * 2021-07-22 2023-08-15 GM Global Technology Operations LLC Vehicle actuation commands to affect transient handling
CN113401144B (zh) * 2021-07-27 2022-10-11 阿波罗智能技术(北京)有限公司 自动驾驶车辆的控制方法、装置、设备和介质
US12548311B2 (en) 2021-08-04 2026-02-10 Motional Ad Llc Training a neural network using a data set with labels of multiple granularities
CN113674245B (zh) * 2021-08-20 2023-10-31 中汽创智科技有限公司 一种目标停车位的确定方法、装置、电子设备及存储介质
US11977854B2 (en) 2021-08-24 2024-05-07 Unlikely Artificial Intelligence Limited Computer implemented methods for the automated analysis or use of data, including use of a large language model
US12073180B2 (en) 2021-08-24 2024-08-27 Unlikely Artificial Intelligence Limited Computer implemented methods for the automated analysis or use of data, including use of a large language model
US11989507B2 (en) 2021-08-24 2024-05-21 Unlikely Artificial Intelligence Limited Computer implemented methods for the automated analysis or use of data, including use of a large language model
US12067362B2 (en) 2021-08-24 2024-08-20 Unlikely Artificial Intelligence Limited Computer implemented methods for the automated analysis or use of data, including use of a large language model
US11989527B2 (en) 2021-08-24 2024-05-21 Unlikely Artificial Intelligence Limited Computer implemented methods for the automated analysis or use of data, including use of a large language model
FR3126388A1 (fr) * 2021-08-25 2023-03-03 Psa Automobiles Sa Procédé et système pour gérer le guidage d’un véhicule automobile à l’approche d’un passage piéton
CN113744398B (zh) * 2021-09-03 2023-04-28 电子科技大学 一种基于激光与微波协同的地图重构融合方法
CN113852969B (zh) * 2021-09-14 2023-05-26 超讯通信股份有限公司 终端调度方法及装置
CN113911131A (zh) * 2021-09-24 2022-01-11 同济大学 面向自动驾驶环境人车冲突的责任敏感安全模型标定方法
JP7376547B2 (ja) * 2021-10-12 2023-11-08 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
JP7324819B2 (ja) * 2021-10-12 2023-08-10 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
US12136342B2 (en) * 2021-10-14 2024-11-05 Lear Corporation Passing assist system
US11794766B2 (en) * 2021-10-14 2023-10-24 Huawei Technologies Co., Ltd. Systems and methods for prediction-based driver assistance
JP7442948B2 (ja) * 2021-10-18 2024-03-05 矢崎総業株式会社 車外表示装置
US12229672B2 (en) * 2021-10-21 2025-02-18 EMC IP Holding Company LLC Detecting domain changes with domain classifiers in autonomous vehicles
US12172576B2 (en) * 2021-10-26 2024-12-24 Ford Global Technologies, Llc System and method for approaching vehicle detection
JP7191179B1 (ja) * 2021-10-27 2022-12-16 三菱電機株式会社 車両制御装置、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
CN114137524B (zh) * 2021-10-29 2025-07-01 际络科技(上海)有限公司 基于毫米波雷达的驾驶障碍物状态估计方法和系统
WO2023085468A1 (ko) * 2021-11-12 2023-05-19 충북대학교 산학협력단 차량 추월 제어 방법 및 이를 지원하는 차량 추월 제어 장치
US12030528B2 (en) * 2021-12-03 2024-07-09 Zoox, Inc. Vehicle perception system with temporal tracker
US12374125B1 (en) * 2021-12-17 2025-07-29 Zoox, Inc. Object destination and trajectory prediction based on semantic features
CN118984788A (zh) * 2021-12-29 2024-11-19 御眼视觉技术有限公司 计算针对道路曲线的车辆速度
KR20230102019A (ko) * 2021-12-29 2023-07-07 팅크웨어(주) 타겟 차량의 후면 검출을 위한 전자 장치 및 이의 동작 방법
KR20230109843A (ko) * 2022-01-14 2023-07-21 현대자동차주식회사 인프라 및 그와 통신하는 차량
CN114548335B (zh) * 2022-02-24 2022-12-06 四川省机场集团有限公司 基于行驶域特征点的无动力设备里程频度推算方法及系统
US12403908B2 (en) * 2022-03-14 2025-09-02 Garrett Transportation I Inc. Non-selfish traffic lights passing advisory systems
CN116788276A (zh) * 2022-03-15 2023-09-22 北京图森智途科技有限公司 一种车辆控制方法、车辆及存储介质
CN114889635A (zh) * 2022-03-29 2022-08-12 徐州徐工汽车制造有限公司 车辆自动驾驶控制系统、方法、商用车以及存储介质
US12087063B2 (en) * 2022-04-28 2024-09-10 Toyota Research Institute, Inc. Systems and methods for detecting traffic lights corresponding to a driving lane
US12360247B1 (en) * 2022-04-29 2025-07-15 Zoox, Inc. Partial sensor data processing for latency reduction
DE102022111538A1 (de) 2022-05-09 2023-11-09 Daimler Truck AG Verfahren und Vorrichtung zur Planung eines Spurwechsels eines Fahrzeugs
CN114659525B (zh) * 2022-05-19 2022-09-02 武汉理工大学 面向三维船舶场景的可扩展性实时快速应急路径规划方法
CN115062926B (zh) * 2022-05-30 2025-03-04 北京邮电大学 基于强化学习和数字孪生的拥挤缓解策略确定方法及装置
WO2023237486A1 (en) * 2022-06-07 2023-12-14 Swiss Reinsurance Company Ltd. Electronic vulnerability detection and measuring system and method for susceptibility or vulnerability of truck fleet to occurring accident events
KR20230168859A (ko) * 2022-06-08 2023-12-15 현대모비스 주식회사 자동차 조명 장치 및 그 작동 방법
AU2023283776B2 (en) 2022-06-09 2025-08-28 AeroCine Ventures, Inc. Localization processing service and observed scene reconstruction service
US12122370B2 (en) * 2022-06-15 2024-10-22 Gm Cruise Holdings Llc Collision detection system for autonomous vehicle
EP4303608A1 (en) * 2022-07-05 2024-01-10 Aptiv Technologies Limited Radar system for automotive applications
EP4303610A1 (en) * 2022-07-06 2024-01-10 Aptiv Technologies Limited Radar system for automotive applications
CN114872735B (zh) * 2022-07-10 2022-10-04 成都工业职业技术学院 基于神经网络算法的自动驾驶物流车辆决策方法和装置
CN114937081B (zh) * 2022-07-20 2022-11-18 之江实验室 基于独立非均匀增量采样的网联车位置估计方法及装置
IT202200017958A1 (it) * 2022-09-01 2024-03-01 Faiveley Transport Italia Spa Procedimento per la predizione di una decelerazione attesa di almeno un veicolo, e corrispondente sistema
US12497041B2 (en) 2022-10-19 2025-12-16 Garrett Transportation I Inc. Driver and lead vehicle prediction model
JP7548286B2 (ja) * 2022-11-29 2024-09-10 いすゞ自動車株式会社 決定装置、決定方法及びプログラム
US12344275B2 (en) * 2023-01-13 2025-07-01 Woven By Toyota, Inc. Systems and methods for avoidance of external odors in a vehicle
US20240244396A1 (en) * 2023-01-17 2024-07-18 Dell Products L.P. Unsupervised programmatic labeling for transitional interval in smart logistics
CN115841766B (zh) * 2023-02-22 2023-07-04 青岛慧拓智能机器有限公司 一种矿区作业区域停靠点车位推荐方法
CN116279504B (zh) * 2023-03-29 2025-07-25 赛力斯汽车有限公司 基于ar的车辆速度辅助系统及其方法
DE102023203275A1 (de) * 2023-04-11 2024-10-17 Robert Bosch Gesellschaft mit beschränkter Haftung Verfahren zur Auswertung einer Verkehrsszene mit mehreren Verkehrsteilnehmern
DE102023203279A1 (de) 2023-04-11 2024-10-17 Robert Bosch Gesellschaft mit beschränkter Haftung Verfahren und Vorrichtung zur Unfallvermeidung an einer Straßenkreuzungsanlage
CN116257069B (zh) * 2023-05-16 2023-08-08 睿羿科技(长沙)有限公司 一种无人车辆编队决策与速度规划的方法
CN116476808B (zh) * 2023-05-23 2025-04-22 东风汽车集团股份有限公司 一种提高辅助驾驶舒适性的横向控制方法及控制系统
CN116373552B (zh) * 2023-06-05 2023-09-08 北京博创联动科技有限公司 一种基于车载传感器技术的车辆运动控制系统
US20240419903A1 (en) * 2023-06-16 2024-12-19 Nvidia Corporation Processing sensor data using language models in map generation systems and applications
US20240420418A1 (en) * 2023-06-16 2024-12-19 Nvidia Corporation Using language models in autonomous and semi-autonomous systems and applications
US12583456B2 (en) * 2023-06-23 2026-03-24 GM Global Technology Operations LLC Probabilistic driving behavior modeling system for a vehicle
CN116767241A (zh) * 2023-06-27 2023-09-19 联创汽车电子有限公司 自车期望加速度修正方法、系统及存储介质
US12503107B2 (en) 2023-07-05 2025-12-23 Ford Global Technologies, Llc Interaction between host vehicle and target vehicle
DE102023206691A1 (de) * 2023-07-14 2025-01-16 Robert Bosch Gesellschaft mit beschränkter Haftung Verfahren zur Erhöhung einer Sicherheit an einer Querungsanlage
TWI870950B (zh) * 2023-07-31 2025-01-21 國立中央大學 可量測物件橫向/縱向/斜向速度之深度攝影機
US12485885B2 (en) * 2023-08-03 2025-12-02 GM Global Technology Operations LLC Vehicle lateral positioning on a non-divided road
CN119428645B (zh) * 2023-08-03 2025-11-21 芜湖伯特利智能驾驶有限公司 基于视觉的eba减速度请求方法、系统及汽车
CN116890878A (zh) * 2023-08-08 2023-10-17 东风汽车股份有限公司 自动驾驶人行横道通行方法、装置、设备及存储介质
US12485896B2 (en) * 2023-08-15 2025-12-02 Torc Robotics, Inc. Optimization function for turn planning
US12594945B2 (en) * 2023-08-28 2026-04-07 Toyota Motor Engineering & Manufacturing North America, Inc. Detection and remediation of an instability condition in a vehicle-trailer system
KR102714686B1 (ko) * 2023-08-30 2024-10-11 (주)오토노머스에이투지 특정 자율주행 차량의 측위를 수행하기 위한 방법 및 이를 이용한 컴퓨팅 장치
CN117429461B (zh) * 2023-09-04 2025-10-28 北方工业大学 一种用于城市无信号路段的自动驾驶汽车通行决策方法
CN116946162B (zh) * 2023-09-19 2023-12-15 东南大学 考虑路面附着条件的智能网联商用车安全驾驶决策方法
CN116968733B (zh) * 2023-09-22 2024-02-27 国汽(北京)智能网联汽车研究院有限公司 车辆安全风险评估方法及其装置、设备、介质
CN117601852B (zh) * 2023-10-30 2025-03-04 湖南大学苏州研究院 一种基于特征人体安全舒适性的紧急避障系统及控制方法
US20250187599A1 (en) * 2023-12-11 2025-06-12 Torc Robotics, Inc. Systems and methods for gap selection for lane change situations using ordered analysis results
US20250296558A1 (en) * 2024-03-20 2025-09-25 Janice H. Nickel Enhanced situational awareness of road objects
GB2640658A (en) * 2024-04-30 2025-11-05 Jaguar Land Rover Ltd Control system and method for a vehicle
GB2640656A (en) * 2024-04-30 2025-11-05 Jaguar Land Rover Ltd Control system and method for a vehicle
GB2640657A (en) * 2024-04-30 2025-11-05 Jaguar Land Rover Ltd Control system and method for a vehicle
US20260044158A1 (en) * 2024-08-12 2026-02-12 Textron Inc. Vehicle following system
CN119821448B (zh) * 2025-03-17 2025-05-23 安徽中科星驰自动驾驶技术有限公司 一种自动驾驶车辆检测系统及方法
CN120722904B (zh) * 2025-08-21 2025-11-14 北京和升达信息安全技术有限公司 一种分布式多机器人协同控制方法、系统及电子设备
CN121353344B (zh) * 2025-12-19 2026-04-10 湖南纳雷科技有限公司 一种车载雷达目标航向角滤波跟踪方法及系统

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9168868B2 (en) 2004-04-08 2015-10-27 Mobileye Vision Technologies Ltd. Collision Warning System

Family Cites Families (172)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3309589A (en) 1962-11-23 1967-03-14 Electricite Mecanique Et Appli Electrical device for precisely positioning a remote component
US3350882A (en) 1964-10-06 1967-11-07 Chrysler Corp Vehicle braking system
US7243945B2 (en) 1992-05-05 2007-07-17 Automotive Technologies International, Inc. Weight measuring systems and methods for vehicles
US7663502B2 (en) 1992-05-05 2010-02-16 Intelligent Technologies International, Inc. Asset system control arrangement and method
US7164117B2 (en) 1992-05-05 2007-01-16 Automotive Technologies International, Inc. Vehicular restraint system control system and method using multiple optical imagers
US7415126B2 (en) 1992-05-05 2008-08-19 Automotive Technologies International Inc. Occupant sensing system
US4610484A (en) 1983-09-23 1986-09-09 The Boeing Company Deceleration control brake system
US5610815A (en) 1989-12-11 1997-03-11 Caterpillar Inc. Integrated vehicle positioning and navigation system, apparatus and method
US5375059A (en) 1990-02-05 1994-12-20 Caterpillar Inc. Vehicle position determination system and method
US5170352A (en) 1990-05-07 1992-12-08 Fmc Corporation Multi-purpose autonomous vehicle with path plotting
DE69210840T2 (de) 1991-12-24 1996-09-26 Lucas Ind Plc Bremsverteilungssystem mit hintergrundsbremsmöglichkeit für ein fahrzeug mit vielen achsen
JP3456399B2 (ja) 1998-02-09 2003-10-14 日産自動車株式会社 無段変速機の変速制御装置
DE19847013A1 (de) * 1998-10-13 2000-04-20 Bosch Gmbh Robert Einparkhilfesystem
WO2000046062A1 (fr) 1999-02-08 2000-08-10 Toyota Jidosha Kabushiki Kaisha Vehicule freine par couple moteur et procede de commande du vehicule
JP2000285347A (ja) 1999-03-31 2000-10-13 Matsushita Electric Ind Co Ltd 緊急通報方法及び装置並びに車両緊急通報システム
US6737963B2 (en) 2001-03-30 2004-05-18 Koninklijke Philips Electronics N.V. Driver tailgating and following aid
JP4090726B2 (ja) 2001-11-26 2008-05-28 横浜ゴム株式会社 ブレーキ制御装置、ブレーキ制御方法および記録媒体
US7124027B1 (en) * 2002-07-11 2006-10-17 Yazaki North America, Inc. Vehicular collision avoidance system
US9950722B2 (en) 2003-01-06 2018-04-24 General Electric Company System and method for vehicle control
JP3975922B2 (ja) * 2003-01-17 2007-09-12 トヨタ自動車株式会社 カーブ半径推定装置
JP4285124B2 (ja) 2003-07-17 2009-06-24 株式会社アドヴィックス 最大路面摩擦力推定装置、及びブレーキトルク制御装置
NO320851B1 (no) 2004-04-15 2006-02-06 Oddvard Johnsen Kontrollerfunksjoner for brems basert pa en styring etter variasjoner i akselerasjonsverdier i hjulets horisontale plan
US7522982B2 (en) 2004-09-15 2009-04-21 Ford Global Technologies, Llc Methods and systems for detecting automobile rollover
US20070213911A1 (en) 2006-03-09 2007-09-13 Ford Global Technologies, Llc Trailbraking
US8744689B2 (en) 2007-07-26 2014-06-03 Hitachi, Ltd. Drive controlling apparatus for a vehicle
JP4416020B2 (ja) * 2007-08-03 2010-02-17 トヨタ自動車株式会社 走行計画生成装置
JP4538762B2 (ja) * 2008-05-20 2010-09-08 トヨタ自動車株式会社 車間距離制御装置
EP2291836B1 (de) * 2008-05-21 2018-09-12 ADC Automotive Distance Control Systems GmbH Fahrerassistenzsystem zur vermeidung von kollisionen eines fahrzeugs mit fussgängern
FR2931984B1 (fr) 2008-06-02 2014-12-12 Airbus France Procede et dispositif de generation d'une vitesse commandee pour un aeronef roulant sur le sol au sein d'un convoi d'aeronefs.
DE102008040241A1 (de) * 2008-07-08 2010-01-14 Robert Bosch Gmbh Ausweichfunktion zur Vermeidung von Kollisionen
DE102008045481A1 (de) 2008-08-28 2009-05-20 Daimler Ag Verfahren und Vorrichtung zur Auslösung eines selbsttätigen Notbremsvorgangs eines Fahrzeugs
JP5410730B2 (ja) * 2008-10-09 2014-02-05 日立オートモティブシステムズ株式会社 自動車の外界認識装置
DE102009000726A1 (de) 2009-02-09 2010-08-12 Robert Bosch Gmbh Verfahren und Vorrichtung zum Betreiben einer Lenkanordnung eines Kraftfahrzeugs
EP2221581B1 (en) 2009-02-18 2017-07-19 Harman Becker Automotive Systems GmbH Method of estimating a propulsion-related operating parameter
US8244408B2 (en) 2009-03-09 2012-08-14 GM Global Technology Operations LLC Method to assess risk associated with operating an autonomic vehicle control system
US8224551B2 (en) * 2009-03-24 2012-07-17 Bendix Commercial Vehicle Systems Llc ACC extended mode operation
US8352112B2 (en) * 2009-04-06 2013-01-08 GM Global Technology Operations LLC Autonomous vehicle management
US20110190972A1 (en) 2010-02-02 2011-08-04 Gm Global Technology Operations, Inc. Grid unlock
US8760030B2 (en) 2010-06-07 2014-06-24 David A. Ross Flexible rotor sequentially actuated motor/generator
JP5494332B2 (ja) * 2010-07-27 2014-05-14 トヨタ自動車株式会社 車両制御システム
US9145145B2 (en) 2010-12-31 2015-09-29 General Electric Company System and method for controlling a vehicle
JP5743576B2 (ja) * 2011-02-02 2015-07-01 スタンレー電気株式会社 物体検出システム
CN102393873B (zh) * 2011-06-28 2015-08-05 河海大学 一种内河船舶航行安全距离的计算方法
US20130030651A1 (en) * 2011-07-25 2013-01-31 GM Global Technology Operations LLC Collision avoidance maneuver through differential braking
JP5796632B2 (ja) 2011-09-26 2015-10-21 トヨタ自動車株式会社 車両の運転支援システム
US8694222B2 (en) * 2011-10-26 2014-04-08 GM Global Technology Operations LLC Collision avoidance system and method of operating the same
US8706393B2 (en) 2012-01-10 2014-04-22 Ford Global Technologies, Llc Intersection collision avoidance with adaptable vehicle dimensions
EP2618108B1 (en) * 2012-01-19 2018-10-17 Volvo Car Corporation Driver assisting system
KR101703144B1 (ko) 2012-02-09 2017-02-06 한국전자통신연구원 차량의 자율주행 장치 및 그 방법
DE102012002695B4 (de) * 2012-02-14 2024-08-01 Zf Cv Systems Hannover Gmbh Verfahren zur Ermittlung einer Notbremssituation eines Fahrzeuges
US9082239B2 (en) 2012-03-14 2015-07-14 Flextronics Ap, Llc Intelligent vehicle for assisting vehicle occupants
US20140310594A1 (en) 2013-04-15 2014-10-16 Flextronics Ap, Llc Configuration of haptic feedback and visual preferences in vehicle user interfaces
FR2988507B1 (fr) * 2012-03-23 2014-04-25 Inst Francais Des Sciences Et Technologies Des Transports De Lamenagement Et Des Reseaux Systeme d'assistance pour vehicule routier
US9495874B1 (en) * 2012-04-13 2016-11-15 Google Inc. Automated system and method for modeling the behavior of vehicles and other agents
DE102012206725A1 (de) 2012-04-24 2013-10-24 Ford Global Technologies, Llc Verfahren und Vorrichtung zum Versetzen eines autonom fahrenden Kraftfahrzeugs in einen sicheren Zustand
US20130278441A1 (en) 2012-04-24 2013-10-24 Zetta Research and Development, LLC - ForC Series Vehicle proxying
US9989637B2 (en) 2012-08-03 2018-06-05 Safie Holdings LLC Portable collision warning apparatus
US20160082885A1 (en) 2012-08-03 2016-03-24 Steve A. Safie Portable collision warning apparatus
SG2013067491A (en) 2012-09-07 2014-04-28 Agency Science Tech & Res A receiver for body channel communication and a method of operating a receiver therefrom
US8825258B2 (en) * 2012-11-30 2014-09-02 Google Inc. Engaging and disengaging for autonomous driving
AT513714B1 (de) 2012-12-12 2015-02-15 Avl List Gmbh Verfahren zur Beurteilung der Beherrschbarkeit eines Fahrzeuges
US9751534B2 (en) 2013-03-15 2017-09-05 Honda Motor Co., Ltd. System and method for responding to driver state
US8996224B1 (en) * 2013-03-15 2015-03-31 Google Inc. Detecting that an autonomous vehicle is in a stuck condition
US8849494B1 (en) * 2013-03-15 2014-09-30 Google Inc. Data selection by an autonomous vehicle for trajectory modification
US20160006034A1 (en) 2013-03-25 2016-01-07 Jsr Corporation Electrode active material, electrode and electrical storage device
DE102013009414A1 (de) 2013-06-05 2014-12-11 Hengstler Gmbh Verfahren und Vorrichtung zur Erzeugung und Ausgabe von Mauttickets
US8874301B1 (en) 2013-07-09 2014-10-28 Ford Global Technologies, Llc Autonomous vehicle with driver presence and physiological monitoring
US9099006B2 (en) 2013-08-22 2015-08-04 GM Global Technology Operations LLC Context-aware threat response arbitration
EP2869283B1 (en) * 2013-10-31 2017-08-16 Inria Institut National de Recherche en Informatique et en Automatique Method and system of driving assistance for collision avoidance
JP5988170B2 (ja) * 2013-11-29 2016-09-07 アイシン精機株式会社 車両挙動制御装置および車両挙動制御システム
CN110920609B (zh) * 2013-12-04 2023-08-22 移动眼视力科技有限公司 用于模仿前车的系统和方法
US20150161894A1 (en) 2013-12-05 2015-06-11 Elwha Llc Systems and methods for reporting characteristics of automatic-driving software
US9123250B2 (en) 2013-12-05 2015-09-01 Elwha Llc Systems and methods for reporting real-time handling characteristics
US20150158495A1 (en) * 2013-12-05 2015-06-11 Elwha Llc Systems and methods for reporting characteristics of operator performance
DE102013020435A1 (de) 2013-12-06 2014-06-18 Daimler Ag Verfahren zum Erkennen von Objekten in einer Fahrzeugumgebung
US9164507B2 (en) * 2013-12-06 2015-10-20 Elwha Llc Systems and methods for modeling driving behavior of vehicles
DE102013225970A1 (de) * 2013-12-13 2015-06-18 Continental Teves Ag & Co. Ohg Verfahren zur Regelung der Fahrstabilität
DE102013226599A1 (de) * 2013-12-19 2015-06-25 Robert Bosch Gmbh Verfahren und Vorrichtung zur adaptiven Abstands- und Geschwindigkeitsregelung eines Kraftfahrzeugs
DE102014201159A1 (de) * 2014-01-23 2015-07-23 Robert Bosch Gmbh Verfahren und Vorrichtung zum Klassifizieren eines Verhaltens eines Fußgängers beim Überqueren einer Fahrbahn eines Fahrzeugs sowie Personenschutzsystem eines Fahrzeugs
US9664789B2 (en) 2014-02-20 2017-05-30 Mobileye Vision Technologies Ltd. Navigation based on radar-cued visual imaging
EP3114574A4 (en) * 2014-03-03 2018-03-07 Inrix, Inc. Traffic obstruction detection
CN106457923B (zh) 2014-05-01 2019-03-12 横滨橡胶株式会社 充气轮胎
EP2942251B1 (en) * 2014-05-08 2017-04-05 Volvo Car Corporation Method for providing an object prediction representation
US9174649B1 (en) 2014-06-02 2015-11-03 Ford Global Technologies, Llc Redundancy for automated vehicle operations
US9707960B2 (en) * 2014-07-31 2017-07-18 Waymo Llc Traffic signal response for autonomous vehicles
DE102014215243B4 (de) 2014-08-01 2020-05-07 Bayerische Motoren Werke Aktiengesellschaft Robuste Totzeit- und Dynamikkompensation für Trajektorienfolgeregelung
US9767366B1 (en) 2014-08-06 2017-09-19 Waymo Llc Using obstacle clearance to measure precise lateral
US9731713B2 (en) 2014-09-10 2017-08-15 Volkswagen Ag Modifying autonomous vehicle driving by recognizing vehicle characteristics
US9925980B2 (en) * 2014-09-17 2018-03-27 Magna Electronics Inc. Vehicle collision avoidance system with enhanced pedestrian avoidance
US9248834B1 (en) 2014-10-02 2016-02-02 Google Inc. Predicting trajectories of objects based on contextual information
US9630318B2 (en) 2014-10-02 2017-04-25 Brain Corporation Feature detection apparatus and methods for training of robotic navigation
CN110254141A (zh) 2014-11-12 2019-09-20 横滨橡胶株式会社 防碰撞系统
US10050433B2 (en) 2014-12-11 2018-08-14 General Electric Company Power generation system and method with resistive braking capability
US10337594B2 (en) 2015-01-13 2019-07-02 Space Systems/Loral, Llc Incremental deployment device
CN112923936B (zh) 2015-02-10 2023-04-18 御眼视觉技术有限公司 用于车辆的导航系统、方法及计算机可读介质
CA3140464C (en) 2015-05-13 2023-01-17 Uber Technologies Inc. Autonomous vehicle operated with guide assistance
US9836056B2 (en) 2015-06-05 2017-12-05 Bao Tran Smart vehicle
US20160357187A1 (en) 2015-06-05 2016-12-08 Arafat M.A. ANSARI Smart vehicle
US20160357262A1 (en) 2015-06-05 2016-12-08 Arafat M.A. ANSARI Smart vehicle
US9711050B2 (en) 2015-06-05 2017-07-18 Bao Tran Smart vehicle
US9475491B1 (en) * 2015-06-08 2016-10-25 Toyota Motor Engineering & Manufacturing North America, Inc. Lane changing for autonomous vehicles
US9937795B2 (en) 2015-06-24 2018-04-10 Nissan North America, Inc. Vehicle operation assistance information management for autonomous vehicle control transfer
US10086699B2 (en) 2015-06-24 2018-10-02 Nissan North America, Inc. Vehicle operation assistance information management for autonomous vehicle control operation
US9630498B2 (en) 2015-06-24 2017-04-25 Nissan North America, Inc. Vehicle operation assistance information management
JP2017019421A (ja) * 2015-07-13 2017-01-26 日立オートモティブシステムズ株式会社 周辺環境認識装置、及び周辺環境認識プログラム
EP3328697B1 (en) 2015-07-27 2020-11-25 Volvo Truck Corporation Abs strategy for hybrid brake actuators
JP6776513B2 (ja) 2015-08-19 2020-10-28 ソニー株式会社 車両制御装置と車両制御方法と情報処理装置および交通情報提供システム
KR102422933B1 (ko) * 2015-08-26 2022-07-21 주식회사 에이치엘클레무브 차량용 감지장치 및 차량용 감지방법
US9604639B2 (en) * 2015-08-28 2017-03-28 Delphi Technologies, Inc. Pedestrian-intent-detection for automated vehicles
US10099705B2 (en) 2015-08-31 2018-10-16 Uber Technologies, Inc. Control system for autonomous-capable vehicles
US9849852B1 (en) * 2015-09-04 2017-12-26 Waymo Llc Intelligent deployment of safety mechanisms for autonomous vehicles
US9910441B2 (en) 2015-11-04 2018-03-06 Zoox, Inc. Adaptive autonomous vehicle planner logic
US9958864B2 (en) 2015-11-04 2018-05-01 Zoox, Inc. Coordination of dispatching and maintaining fleet of autonomous vehicles
KR20170054186A (ko) 2015-11-09 2017-05-17 현대자동차주식회사 자율주행차량 제어 장치 및 그 방법
US9862364B2 (en) * 2015-12-04 2018-01-09 Waymo Llc Collision mitigated braking for autonomous vehicles
FR3045563B1 (fr) 2015-12-18 2018-02-09 Messier-Bugatti-Dowty Procede et systeme de commande de freinage d’un aeronef equipe d’un systeme d’inversion de poussee
WO2017120336A2 (en) * 2016-01-05 2017-07-13 Mobileye Vision Technologies Ltd. Trained navigational system with imposed constraints
KR102509433B1 (ko) * 2016-01-19 2023-03-13 주식회사 에이치엘클레무브 충돌방지장치 및 충돌방지방법
JP6586380B2 (ja) 2016-03-01 2019-10-02 富士フイルム株式会社 画像処理装置、画像処理方法、プログラムおよび記録媒体
CN108712981A (zh) * 2016-03-07 2018-10-26 本田技研工业株式会社 车辆控制装置、车辆控制方法及车辆控制程序
US9645577B1 (en) 2016-03-23 2017-05-09 nuTonomy Inc. Facilitating vehicle driving and self-driving
US9857795B2 (en) 2016-03-24 2018-01-02 Honda Motor Co., Ltd. System and method for trajectory planning for unexpected pedestrians
US9896096B2 (en) * 2016-04-11 2018-02-20 David E. Newman Systems and methods for hazard mitigation
US10112610B2 (en) * 2016-04-15 2018-10-30 Robert Bosch Gmbh Regional adjustment for driver assistance functions
KR101850392B1 (ko) 2016-05-12 2018-04-19 엘지전자 주식회사 차량에 구비된 제어장치 및 이의 제어방법
US9989966B2 (en) * 2016-05-20 2018-06-05 Delphi Technologies, Inc. Intersection cross-walk navigation system for automated vehicles
US10077050B2 (en) 2016-05-24 2018-09-18 GM Global Technology Operations LLC Automated driving system for evaluating lane cut-out and method of using the same
EP3465371A4 (en) 2016-05-31 2019-12-18 Peloton Technology Inc. STATE MACHINE OF A COLUMN CONTROL UNIT
US10081357B2 (en) * 2016-06-23 2018-09-25 Honda Motor Co., Ltd. Vehicular communications network and methods of use and manufacture thereof
US9953535B1 (en) * 2016-06-27 2018-04-24 Amazon Technologies, Inc. Annotated virtual track to inform autonomous vehicle control
US9988046B2 (en) 2016-07-26 2018-06-05 Ford Global Technologies, Llc Enhanced collision avoidance
DE102016009760A1 (de) * 2016-08-11 2018-02-15 Trw Automotive Gmbh Steuerungssystem und Steuerungsverfahren zum Führen eines Kraftfahrzeugs entlang eines Pfades
KR101946940B1 (ko) * 2016-11-09 2019-02-12 엘지전자 주식회사 차량에 구비된 차량 제어 장치 및 차량의 제어방법
KR102039487B1 (ko) * 2016-11-11 2019-11-26 엘지전자 주식회사 차량 주행 제어 장치 및 방법
US10248874B2 (en) * 2016-11-22 2019-04-02 Ford Global Technologies, Llc Brake light detection
US10338591B2 (en) * 2016-11-22 2019-07-02 Amazon Technologies, Inc. Methods for autonomously navigating across uncontrolled and controlled intersections
US10196058B2 (en) * 2016-11-28 2019-02-05 drive.ai Inc. Method for influencing entities at a roadway intersection
KR102496178B1 (ko) 2016-12-15 2023-02-03 현대자동차주식회사 연료전지 차량에 탑재되는 수소차단밸브의 제어 방법
CN119773813A (zh) * 2016-12-23 2025-04-08 御眼视觉技术有限公司 用于导航主车辆的系统和方法
JP6828428B2 (ja) * 2016-12-27 2021-02-10 株式会社デンソー 車両用衝突回避支援装置および車両の衝突回避支援方法
US10503176B2 (en) 2016-12-30 2019-12-10 Bendix Commercial Vehicle Systems Llc Self-ordering of fleet vehicles in a platoon
US10073464B2 (en) 2016-12-30 2018-09-11 Bendix Commercial Vehicle Systems Llc Varying the distance between vehicles in a platoon
US10403145B2 (en) * 2017-01-19 2019-09-03 Ford Global Technologies, Llc Collison mitigation and avoidance
US10220850B2 (en) * 2017-01-30 2019-03-05 GM Global Technology Operations LLC Vehicle propulsion systems and methods
US10509120B2 (en) 2017-02-16 2019-12-17 GM Global Technology Operations LLC Lidar-radar relative pose calibration
KR102265376B1 (ko) 2017-03-07 2021-06-16 현대자동차주식회사 차량 및 그 제어방법과 이를 이용한 자율 주행 시스템
US10699142B2 (en) 2017-04-20 2020-06-30 GM Global Technology Operations LLC Systems and methods for traffic signal light detection
US10460180B2 (en) 2017-04-20 2019-10-29 GM Global Technology Operations LLC Systems and methods for visual classification with region proposals
US10409288B2 (en) * 2017-05-03 2019-09-10 Toyota Research Institute, Inc. Systems and methods for projecting a location of a nearby object into a map according to a camera image
US10507813B2 (en) * 2017-05-10 2019-12-17 Baidu Usa Llc Method and system for automated vehicle emergency light control of an autonomous driving vehicle
DE202018006696U1 (de) 2017-05-15 2022-04-01 Ouster, Inc. Optischer Bildübertrager mit Helligkeitsverbesserung
CA3068943A1 (en) 2017-07-05 2019-01-10 Ouster, Inc. Light ranging device with electronically scanned emitter array and synchronized sensor array
DE102017212020B3 (de) 2017-07-13 2018-05-30 Carl Zeiss Microscopy Gmbh Verfahren zur In-situ-Präparation und zum Transfer mikroskopischer Proben, Computerprogrammprodukt sowie mikroskopische Probe
US10549732B2 (en) 2017-09-15 2020-02-04 Bendix Commercial Vehicle Systems Llc Towing vehicle controller using trailer braking strategy and trailer braking control method
US10525950B2 (en) 2017-09-15 2020-01-07 Bendix Commercial Vehicle Systems Llc Braking controller and method using verification of reported trailer capabilities
US10549739B2 (en) 2017-09-15 2020-02-04 Bendix Commercial Vehicle Systems Llc Towing vehicle controller using trailer braking strategy and trailer braking control method
US10814844B2 (en) 2017-09-15 2020-10-27 Bendix Commercial Vehicle Systems Llc Braking controller and method using verification of reported trailer capabilities
US10691962B2 (en) 2017-09-22 2020-06-23 Toyota Motor Engineering & Manufacturing North America, Inc. Systems and methods for rear signal identification using machine learning
US9934440B1 (en) 2017-10-04 2018-04-03 StradVision, Inc. Method for monitoring blind spot of monitoring vehicle and blind spot monitor using the same
US10782138B2 (en) * 2017-10-06 2020-09-22 Here Global B.V. Method, apparatus, and computer program product for pedestrian behavior profile generation
US10535138B2 (en) 2017-11-21 2020-01-14 Zoox, Inc. Sensor data segmentation
US11163309B2 (en) * 2017-11-30 2021-11-02 Direct Current Capital LLC Method for autonomous navigation
US11340336B2 (en) 2017-12-07 2022-05-24 Ouster, Inc. Rotating light ranging system with optical communication uplink and downlink channels
US10467907B2 (en) 2017-12-28 2019-11-05 Bendix Commercial Vehicle Systems Llc Initialization and safety maintenance strategy for platooning vehicles
US11164463B2 (en) 2017-12-29 2021-11-02 Bendix Commercial Vehicle Systems Llc Brake performance monitoring for vehicle platooning operation
DE112019000065B4 (de) 2018-02-02 2025-01-09 Nvidia Corporation Sicherheitsprozeduranalyse zur hindernisvermeidung in einem autonomen fahrzeug
US11789449B2 (en) * 2018-02-09 2023-10-17 Nvidia Corporation Controlling autonomous vehicles using safe arrival times
KR102337011B1 (ko) 2018-03-20 2021-12-13 모빌아이 비젼 테크놀로지스 엘티디 차량의 항법을 위한 시스템 및 방법
US10807592B2 (en) * 2018-06-18 2020-10-20 Micron Technology, Inc. Vehicle navigation using object data received from other vehicles
US11454975B2 (en) * 2018-06-28 2022-09-27 Uatc, Llc Providing actionable uncertainties in autonomous vehicles
US10909866B2 (en) * 2018-07-20 2021-02-02 Cybernet Systems Corp. Autonomous transportation system and methods
US11623622B2 (en) * 2019-12-27 2023-04-11 Intel Corporation System and method for emergency braking

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9168868B2 (en) 2004-04-08 2015-10-27 Mobileye Vision Technologies Ltd. Collision Warning System

Cited By (46)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210179097A1 (en) * 2019-12-12 2021-06-17 Baidu Usa Llc Lane-attention: predicting vehicles' moving trajectories by learning their attention over lanes
US11860634B2 (en) * 2019-12-12 2024-01-02 Baidu Usa Llc Lane-attention: predicting vehicles' moving trajectories by learning their attention over lanes
US11719821B2 (en) 2020-02-21 2023-08-08 BlueSpace.ai, Inc. Method for object avoidance during autonomous navigation
CN115461258B (zh) * 2020-02-21 2023-09-05 蓝色空间人工智能公司 用于自主导航期间对象避让的方法
AU2021222055B2 (en) * 2020-02-21 2022-12-01 Bluespace Ai, Inc. Method for object avoidance during autonomous navigation
WO2021168452A3 (en) * 2020-02-21 2021-10-28 Bluespace Al, Inc. Method for object avoidance during autonomous navigation
US11235785B2 (en) 2020-02-21 2022-02-01 BlueSpace.ai, Inc. Method for object avoidance during autonomous navigation
CN115461258A (zh) * 2020-02-21 2022-12-09 蓝色空间人工智能公司 用于自主导航期间对象避让的方法
US11481607B2 (en) 2020-07-01 2022-10-25 International Business Machines Corporation Forecasting multivariate time series data
CN114148328A (zh) * 2020-09-08 2022-03-08 现代摩比斯株式会社 用于控制车辆驾驶的装置和方法
EP3964414A1 (en) * 2020-09-08 2022-03-09 Hyundai Mobis Co., Ltd. Apparatus and method for controlling driving of vehicle
CN114148328B (zh) * 2020-09-08 2024-02-09 现代摩比斯株式会社 用于控制车辆驾驶的装置和方法
US20230014874A1 (en) * 2020-10-22 2023-01-19 Tencent Technology (Shenzhen) Company Limited Obstacle detection method and apparatus, computer device, and storage medium
US12374126B2 (en) * 2020-10-22 2025-07-29 Tencent Technology (Shenzhen) Company Limited Obstacle detection method and apparatus, computer device, and storage medium
EP4247680A4 (en) * 2020-11-19 2024-10-23 Mobileye Vision Technologies Ltd. Vehicle operation safety model compliance measurement
US12194975B2 (en) 2020-11-19 2025-01-14 Mobileye Vision Technologies Ltd. Vehicle operation safety model compliance measurement
US11878685B2 (en) 2020-12-22 2024-01-23 Beijing Baidu Netcom Science Technology Co., Ltd. Vehicle control method and apparatus, electronic device and self-driving vehicle
EP4019353A1 (en) * 2020-12-22 2022-06-29 Beijing Baidu Netcom Science And Technology Co. Ltd. Vehicle control method and apparatus, electronic device and self-driving vehicle
US12227205B2 (en) 2021-01-15 2025-02-18 Tusimple, Inc. Proactive lane change for autonomous vehicles
WO2022162463A1 (en) * 2021-01-27 2022-08-04 Foretellix Ltd. Techniques for providing concrete instances in traffic scenarios by a transformation as a constraint satisfaction problem
US12030485B2 (en) 2021-01-28 2024-07-09 Motional Ad Llc Vehicle operation using maneuver generation
GB2604222B (en) * 2021-01-28 2023-03-22 Motional Ad Llc Sampling-based maneuver realizer
GB2604222A (en) * 2021-01-28 2022-08-31 Motional Ad Llc Sampling-based maneuver realizer
US12566434B2 (en) 2021-02-03 2026-03-03 Denso Corporation Processing device, processing method, processing system, storage medium
US12548442B2 (en) 2021-02-03 2026-02-10 Denso Corporation Processing device, processing method, processing system, and storage medium
US11780461B2 (en) 2021-02-09 2023-10-10 Aptiv Technologies Limited Lateral acceleration control for autonomous driving
US11794776B2 (en) 2021-02-09 2023-10-24 Aptiv Technologies Limited Trajectory validation for autonomous driving
EP4039557A1 (en) * 2021-02-09 2022-08-10 Aptiv Technologies Limited Trajectory validation for autonomous driving
US12454288B2 (en) * 2021-03-05 2025-10-28 Denso Corporation Processing method, processing system, and storage medium storing processing program
CN117320935A (zh) * 2021-03-15 2023-12-29 动态Ad有限责任公司 制动仲裁
US12263840B2 (en) 2021-03-26 2025-04-01 Aptiv Technologies AG Longitudinal acceleration control for autonomous driving
CN117615948A (zh) * 2021-07-05 2024-02-27 株式会社电装 行驶控制系统、行驶控制装置、行驶控制方法、行驶控制程序
JP2023018930A (ja) * 2021-07-28 2023-02-09 株式会社Ｎｔｔデータオートモビリジェンス研究所 シミュレータ、学習装置、及び車両制御装置
FR3130232A1 (fr) * 2021-12-09 2023-06-16 Psa Automobiles Sa Contrôle autonome de la vitesse d’un véhicule après un freinage d’urgence
FR3130229A1 (fr) * 2021-12-10 2023-06-16 Psa Automobiles Sa Procédé et dispositif de contrôle de trajectoire d’un véhicule autonome
US12487347B2 (en) 2021-12-30 2025-12-02 BlueSpace.ai, Inc. Method for calibrating offsets between doppler-based sensors on a mobile platform
GB2632069A (en) * 2022-04-06 2025-01-22 Rojas Ronen Steering limiters for vehicle navigation
WO2023194801A1 (en) * 2022-04-06 2023-10-12 Mobileye Vision Technologies Ltd. Steering limiters for vehicle navigation
CN114895295A (zh) * 2022-04-19 2022-08-12 中国电子科技集团公司第十研究所 一种基于k近邻的通信散点关联加速方法及系统
CN114895295B (zh) * 2022-04-19 2023-06-02 中国电子科技集团公司第十研究所 一种基于k近邻的通信散点关联加速方法及系统
US12479471B2 (en) 2022-06-14 2025-11-25 Motional Ad Llc Autonomous vehicle yielding
WO2023245073A1 (en) * 2022-06-14 2023-12-21 Motional Ad Llc Method and system for controlling an autonomous vehicle
CN115140089A (zh) * 2022-06-21 2022-10-04 重庆长安汽车股份有限公司 车辆的辅助驾驶方法、装置、车辆及存储介质
WO2024094941A1 (fr) * 2022-11-02 2024-05-10 Stellantis Auto Sas Procédé et dispositif de contrôle de gestion des messages d'alertes pour un système de régulation adaptative de vitesse d'un véhicule
FR3141424A1 (fr) * 2022-11-02 2024-05-03 Psa Automobiles Sa Procédé et dispositif de contrôle de gestion des messages d’alertes pour un système de régulation adaptative de vitesse d’un véhicule
US20250187598A1 (en) * 2023-12-12 2025-06-12 Mobileye Vision Technologies Ltd. Systems and methods for navigating a vehicle using coast control

Also Published As

Publication number Publication date
JP7609528B2 (ja) 2025-01-07
EP3854646B1 (en) 2024-05-29
EP3842303A3 (en) 2021-09-15
EP4606672A3 (en) 2025-10-08
EP3787947A2 (en) 2021-03-10
US20210191406A1 (en) 2021-06-24
CN120863620A (zh) 2025-10-31
US20210162995A1 (en) 2021-06-03
US11932277B2 (en) 2024-03-19
EP4596359A3 (en) 2025-12-31
US11897508B2 (en) 2024-02-13
US20210240197A1 (en) 2021-08-05
EP3842304B1 (en) 2024-09-18
US20250033669A1 (en) 2025-01-30
CN112601686A (zh) 2021-04-02
EP3842304C0 (en) 2024-09-18
EP4474240A3 (en) 2025-03-05
EP4474240A2 (en) 2024-12-11
CN112601686B (zh) 2025-08-08
EP4606672A2 (en) 2025-08-27
US11840258B2 (en) 2023-12-12
WO2020035728A3 (en) 2020-04-30
US12037018B2 (en) 2024-07-16
EP3854646B8 (en) 2024-07-17
KR20210042387A (ko) 2021-04-19
EP3842303B1 (en) 2024-05-15
EP3854646A3 (en) 2021-09-22
US20210200235A1 (en) 2021-07-01
EP4596359A2 (en) 2025-08-06
EP3787947B1 (en) 2025-04-02
US20210094577A1 (en) 2021-04-01
EP3842304A3 (en) 2021-09-15
CN119078812A (zh) 2024-12-06
KR102867125B1 (ko) 2025-10-01
JP2025061662A (ja) 2025-04-11
EP3854646A2 (en) 2021-07-28
EP3842304A2 (en) 2021-06-30
JP7808176B2 (ja) 2026-01-28
JP2021536599A (ja) 2021-12-27
EP3842303A2 (en) 2021-06-30
US12037019B2 (en) 2024-07-16

Similar Documents

Publication Publication Date Title
US11897508B2 (en) Navigation with a safe lateral distance
US12182878B2 (en) Safe state to safe state navigation
US12485883B2 (en) Systems and methods for navigating a vehicle
US11210744B2 (en) Navigation based on liability constraints
US20230286536A1 (en) Systems and methods for evaluating domain-specific navigation system capabilities
US20220227367A1 (en) Systems and methods for vehicle navigation
WO2025075621A1 (en) Selectable multi-mode policy control for an autonomous vehicle

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2019779091

Country of ref document: EP

Effective date: 20201202

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19779091

Country of ref document: EP

Kind code of ref document: A2

ENP Entry into the national phase

Ref document number: 2021507580

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 20217007561

Country of ref document: KR

Kind code of ref document: A

WWG Wipo information: grant in national office

Ref document number: 2019779091

Country of ref document: EP

WWG Wipo information: grant in national office

Ref document number: 201980043159.2

Country of ref document: CN