US20190248381A1 - Method and apparatus for evaluating pedestrian collision risks and determining driver warning levels - Google Patents
Method and apparatus for evaluating pedestrian collision risks and determining driver warning levels Download PDFInfo
- Publication number
- US20190248381A1 US20190248381A1 US15/896,669 US201815896669A US2019248381A1 US 20190248381 A1 US20190248381 A1 US 20190248381A1 US 201815896669 A US201815896669 A US 201815896669A US 2019248381 A1 US2019248381 A1 US 2019248381A1
- Authority
- US
- United States
- Prior art keywords
- vehicle
- pedestrian
- time
- ref
- warning
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 230000004044 response Effects 0.000 claims abstract description 16
- 230000007613 environmental effect Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 230000003247 decreasing effect Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 description 15
- 238000011156 evaluation Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000001351 cycling effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—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
- 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
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18154—Approaching an intersection
-
- 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
-
- 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
- B60W40/112—Roll 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0097—Predicting future conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/161—Decentralised systems, e.g. inter-vehicle communication
- G08G1/162—Decentralised systems, e.g. inter-vehicle communication event-triggered
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/143—Alarm means
-
- 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
- B60W2520/14—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
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/45—External transmission of data to or from 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
- B60W2556/00—Input parameters relating to data
- B60W2556/45—External transmission of data to or from the vehicle
- B60W2556/50—External transmission of data to or from the vehicle of positioning data, e.g. GPS [Global Positioning System] data
-
- 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
Definitions
- the subject disclosure generally relates to a vehicle, and particularly to evaluating pedestrian collision risks and determining driver warning levels based on the evaluation.
- Pedestrians are at many times walking or standing less than one foot from a slow moving vehicle. Due to the density of the traffic within a heavy populated city, vehicles often move at very slow speeds (e.g., less than 10 mph). As a result, pedestrians do not distance themselves from the vehicles; rather, pedestrians may walk, stand, or ride bikes just inches from slow moving vehicles.
- Pedestrians are typically aware of vehicles in close proximity to them due to the sound of the running engine.
- vehicles are becoming increasingly quiet during engine-on operations, and therefore, the pedestrians are less likely to hear a vehicle in close proximity.
- the reduction in noise of the engine is due to enhanced noise suppression as well as the increasing use of electric and hybrid electric vehicles.
- the actuation of the horn by the driver although effective, is often viewed as a rude behavior and requires manual intervention by the driver of the vehicle.
- Some drivers are reluctant to use their horn to warn the pedestrians since it IS viewed as rude behavior and since they may underestimate the danger to the pedestrian.
- a method to generate a pedestrian detection warning in a vehicle includes constructing, by a vehicle controller, a pedestrian zone based on pedestrian information that is received from a traffic controller.
- the method further includes computing, by the vehicle controller, a vehicle trajectory that predicts a path for the vehicle.
- the method further includes determining, by the vehicle controller, a minimal distance between the pedestrian zone and the vehicle trajectory.
- the method further includes predicting, by the vehicle controller, a time to collision by computing a time for the vehicle to reach a location corresponding to the minimal distance along the vehicle trajectory.
- the method further includes in response to the time to collision being below a threshold, generating, by the vehicle controller, a warning for an operator of the vehicle.
- the pedestrian information comprises a trigger time corresponding to a push button associated with a pedestrian light. Further, the pedestrian information further comprises a pedestrian location. In one or more examples, the vehicle trajectory is computed based on vehicle information that comprises at least one of a vehicle speed, a vehicle location, and a vehicle yaw rate.
- the method further includes computing a time-decay risk as:
- Ref_Safe_Distance is a predetermined parameter and CV is a time decayed confidence-value indicative of a pedestrian being present in the pedestrian zone, wherein the vehicle controller predicts the time to collision in response to the time-decay risk being greater than a risk threshold.
- generating the warning further includes selecting a warning level based on a combination of a vehicle status, an environmental visibility, and an intersection familiarity. Determining the vehicle status includes computing
- Ref_Safe_Speed is a predetermined parameter
- TTC is the time to collision
- Ref_TTC is a predetermined parameter.
- the environmental visibility is determined based on a brightness value in vicinity of the vehicle, and based on whether a wiper of the vehicle is being used. Further, the intersection familiarity is computed as
- Num_Visits is a number of times the vehicle has passed the intersection in a predetermined duration
- Ref_Num_Visits is a predetermined parameter
- a system for pedestrian warning in a vehicle includes a traffic controller, and a vehicle controller.
- the vehicle controller receives pedestrian information from the traffic controller to generate a pedestrian detection warning based on evaluating the pedestrian information.
- the generation of a pedestrian detection warning in a vehicle includes constructing, by a vehicle controller, a pedestrian zone based on pedestrian information that is received from a traffic controller.
- the generation further includes computing, by the vehicle controller, a vehicle trajectory that predicts a path for the vehicle.
- the generation further includes determining, by the vehicle controller, a minimal distance between the pedestrian zone and the vehicle trajectory.
- the generation further includes predicting, by the vehicle controller, a time to collision by computing a time for the vehicle to reach a location corresponding to the minimal distance along the vehicle trajectory.
- the generation further includes in response to the time to collision being below a threshold, generating, by the vehicle controller, a warning for an operator of the vehicle.
- the pedestrian information includes a trigger time corresponding to a push button associated with a pedestrian light.
- the pedestrian information further includes a pedestrian location.
- the vehicle trajectory is computed based on vehicle information that comprises at least one of a vehicle speed, a vehicle location, and a vehicle yaw rate.
- the generation of the pedestrian warning further includes computing a time-decay risk as
- Ref_Safe_Distance is a predetermined parameter and CV is a time decayed confidence-value indicative of a pedestrian being present in the pedestrian zone, wherein the vehicle controller predicts the time to collision in response to the time-decay risk being greater than a risk threshold.
- generating the warning further includes selecting a warning level based on a combination of a vehicle status, an environmental visibility, and an intersection familiarity. Determining the vehicle status includes computing
- Ref_Safe_Speed is a predetermined parameter
- TTC is the time to collision
- Ref_TTC is a predetermined parameter.
- the environmental visibility is determined based on a brightness value in vicinity of the vehicle, and based on whether a wiper of the vehicle is being used. Further, the intersection familiarity is computed as
- Num_Visits is a number of times the vehicle has passed the intersection in a predetermined duration
- Ref_Num_Visits is a predetermined parameter
- a computer program product includes one or more computer executable instructions that when executed by a vehicle controller cause the vehicle controller to generate a pedestrian detection warning for a vehicle.
- the generation of the pedestrian detection warning includes constructing, by a vehicle controller, a pedestrian zone based on pedestrian information that is received from a traffic controller.
- the generation further includes computing, by the vehicle controller, a vehicle trajectory that predicts a path for the vehicle.
- the generation further includes determining, by the vehicle controller, a minimal distance between the pedestrian zone and the vehicle trajectory.
- the generation further includes predicting, by the vehicle controller, a time to collision by computing a time for the vehicle to reach a location corresponding to the minimal distance along the vehicle trajectory.
- the generation further includes in response to the time to collision being below a threshold, generating, by the vehicle controller, a warning for an operator of the vehicle.
- the pedestrian information includes a trigger time corresponding to a push button associated with a pedestrian light.
- the pedestrian information further includes a pedestrian location.
- the vehicle trajectory is computed based on vehicle information that comprises at least one of a vehicle speed, a vehicle location, and a vehicle yaw rate.
- the generation of the pedestrian warning further includes computing a time-decay risk as:
- Ref_Safe_Distance is a predetermined parameter and CV is a time decayed confidence-value indicative of a pedestrian being present in the pedestrian zone, wherein the vehicle controller predicts the time to collision in response to the time-decay risk being greater than a risk threshold.
- generating the warning further includes selecting a warning level based on a combination of a vehicle status, an environmental visibility, and an intersection familiarity. Determining the vehicle status includes computing
- Ref_Safe_Speed is a predetermined parameter
- TTC is the time to collision
- Ref_TTC is a predetermined parameter.
- the environmental visibility is determined based on a brightness value in vicinity of the vehicle, and based on whether a wiper of the vehicle is being used. Further, the intersection familiarity is computed as
- Num_Visits is a number of times the vehicle has passed the intersection in a predetermined duration
- Ref_Num_Visits is a predetermined parameter
- FIG. 1 is a plan view of a vehicle sensing pedestrians according to one or more embodiments
- FIG. 2 depicts a block diagram of a traffic controller according to one or more embodiments
- FIG. 3 depicts a flowchart of an example method for evaluating a risk of pedestrian collision and generating a selected warning in response according to one or more embodiments
- FIG. 4 depicts pedestrian zones according to one or more embodiments.
- FIG. 5 depicts at least two example scenarios of predicted trajectories.
- module refers to processing circuitry that may include an application specific integrated circuit (ASIC), an electronic circuit, a processor (shared, dedicated, or group) and memory that executes one or more software or firmware programs, a combinational logic circuit, and/or other suitable components that provide the described functionality.
- ASIC application specific integrated circuit
- processor shared, dedicated, or group
- memory that executes one or more software or firmware programs, a combinational logic circuit, and/or other suitable components that provide the described functionality.
- FIG. 1 is a plan view of a vehicle sensing pedestrians according to one or more embodiments.
- a vehicle 10 is traveling along a roadway 11 in a densely populated area where multiple pedestrians 12 travel on different sides of the vehicle 10 .
- the vehicle 10 may travel within the populated area at slow speeds due to traffic congestion caused by an excessive number of vehicles on the road and number of pedestrians crossing the roads at intersections.
- the pedestrians 12 includes walking pedestrians, jogging pedestrians, or cycling pedestrians in the roadway and on nearby sidewalks.
- Roadways may also include pedestrian lanes disposed adjacent to the curb (not shown) in the road and is used for runners and bicyclers.
- the vehicle 10 is equipped with a sensing device 14 that includes one or more sensors or like devices that are regionally disposed around the vehicle for sensing pedestrians proximate to the vehicle 10 .
- the sensors may be disposed at the front of the vehicle 16 and the front corners of the vehicle 18 in addition to the rear of the vehicle 20 and the rear corners of the vehicle 22 .
- the vehicle 10 includes a controller 15 that analyzes the information received from the one or more sensors to detect a pedestrian.
- the vehicle 10 receives pedestrian information from external devices.
- a traffic controller 25 is shown that sends pedestrian information to the controller 15 .
- the traffic controller 25 uses infrastructure sensors, along the road etc., external to the vehicle 10 , to detect pedestrians 12 . Based on the pedestrian information, the controller 15 generates one or more warnings for the operator of the vehicle 10 .
- the infrastructure sensors (such as the cameras) are mounted high over an intersection and have a broader view of an intersection and/or roadside along which the vehicle 10 is traveling. Accordingly, human drivers and the vehicle built-in sensors are limited by line-of-sight and environment visibility, for example, the driver's view is blocked by other vehicles, trees, buildings at an intersection.
- the technical solutions described herein facilitate the vehicle controller 15 to utilize the infrastructure sensors to detect the presence of pedestrians and share the information with passing vehicles 10 .
- the technical solutions described herein accordingly facilitate extending the range of sensing for the vehicle 10 and also enhance the environment visibility.
- FIG. 2 depicts a block diagram of a traffic controller according to one or more embodiments.
- the traffic controller 25 obtains pedestrian information from one or more infrastructure sensors 210 .
- the infrastructure sensors 210 include various types of sensors such as a push button 212 , an infrared sensor 214 , an ultrasound sensor 216 , a camera 218 , and the like.
- the information received from the infrared sensors 210 is used by the traffic controller 25 to detect the presence of pedestrians 12 .
- the traffic controller 25 uses a roadside unit (RSU) 220 to broadcast the pedestrian info to nearby vehicles, such as the vehicle 10 .
- nearby vehicles include vehicles within a predetermined vicinity or range in which the RSU 220 can broadcast information.
- the RSU 220 may use wireless communication protocols for broadcasting vehicle information, such as Dedicated Short Range Communications (DSRC) to transmit the pedestrian information to the vehicle controller 15 .
- DSRC Dedicated Short Range Communications
- the vehicle controller 15 evaluates a risk of collision between the vehicle 10 and one or more detected pedestrians 12 . Based on the evaluation, the vehicle controller 15 gives a driver a selected level of warning, such as image warning, voice warning, haptic warning, etc. Selecting the level of warning includes suppressing one or more warnings, and determining an appropriate level of warning for the driver according to the evaluation.
- a selected level of warning such as image warning, voice warning, haptic warning, etc. Selecting the level of warning includes suppressing one or more warnings, and determining an appropriate level of warning for the driver according to the evaluation.
- FIG. 3 depicts a flowchart of an example method for evaluating a risk of pedestrian collision and generating a selected warning in response according to one or more embodiments.
- the method may be executed by the vehicle controller 15 , in one or more examples.
- the method includes the vehicle controller 15 receiving the pedestrian information from the traffic controller 25 , at 310 .
- the pedestrian information includes pedestrian light SPaT (Signal Phase and Timing) information.
- the SPaT includes information when a pedestrian 12 activates a pedestrian crossing button.
- the SPaT includes pedestrian crossing signal information from an automated pedestrian crossing system that is activated automatically on a periodic basis or in response to detecting a pedestrian.
- the pedestrian information received may further include a timestamp that indicates push-button trigger time, or when the pedestrian crossing was activated in case of an automated crossing system.
- the pedestrian information further includes pedestrian location, for example, obtained from the camera 218 , the infrared 214 , and/or ultrasonic 216 sensors.
- the vehicle controller 15 also receives a map from the road side unit 220 , at 310 .
- the map may include a crosswalk or intersection map at which the traffic controller 25 is installed.
- the map includes dimensions of the crosswalk or intersection.
- the method further includes constructing pedestrian zones, at 320 .
- FIG. 4 depicts pedestrian zones according to one or more embodiments.
- a pedestrian zone 410 represents an area in which one or more pedestrian 12 may appear.
- the vehicle controller 15 uses the entire crosswalk that covers the entire dimension of the road as the pedestrian zone 410 .
- the vehicle controller 15 constructs a pedestrian zone 410 that represents a rectangular area a pedestrian 12 is walking toward. The dimensions of the rectangular area is of a predetermined dimension.
- the vehicle controller 15 constructs the pedestrian zone 410 using the pedestrian information that includes a location, a moving speed, a direction, an update time, a last observed location, and the like that is obtained from the one or more infrastructure sensors 210 and received from the traffic controller 25 .
- the method further includes predicting a vehicle trajectory for the vehicle 10 , at 330 .
- the vehicle controller 15 obtains vehicle information for generating the vehicle trajectory.
- the vehicle information includes speed, location (from a Global Navigation Satellite System (GNSS), for example Global Positioning System (GPS)), an orientation, whether the vehicle is in leftmost/rightmost lane, status of the turn signals, a yaw rate, steering wheel angle and the like or a combination thereof.
- GNSS Global Navigation Satellite System
- GPS Global Positioning System
- the vehicle controller 15 receives the vehicle information from the one or more subsystems in the vehicle 10 or from one or more systems external to the vehicle 10 .
- a system such as ONSTARTM may monitor the vehicle 10 and provide such vehicle information to the vehicle controller 15 periodically or when requested.
- FIG. 5 depicts at least two example scenarios of predicted trajectories 510 for the vehicle 10 .
- the predicted trajectory 510 can be substantially a straight line or a curve as illustrated. It should be noted that the predicted trajectory 510 can be any different shape in other examples.
- the vehicle controller 15 may perform the trajectory prediction using any of the one or more techniques that are known or that will be developed.
- the method further includes calculating a minimal distance and time-to-collision, at 340 .
- the minimal distance 520 is calculated at a point which is at the minimum distance between the pedestrian zone 410 and the vehicle trajectory 510 .
- the minimal distance 520 varies.
- the vehicle controller 15 can compute the time before the vehicle 10 reaches the corresponding minimal distance point to the pedestrian zone 410 .
- the computed time along the predicted trajectory 510 is the time to collision.
- the method further includes calculating a time decayed risk, at 350 .
- Calculating the risk includes computing a time decaying confidence function to represent a confidence of pedestrian presence in the pedestrian zone 410 .
- the confidence function calculation increases a confidence-value (CV) if a pedestrian 12 is detected, and decreases the confidence-value (CV) gradually since last detection of pedestrians 12 in the pedestrian zone 410 .
- CV t2 CV t1 + ⁇ (t2 ⁇ t1) where CV t2 is the confidence-value at t2 if no observation update since time t1, where the function ⁇ can be any monotonically decreasing function that is predetermined.
- the vehicle controller 15 after updating the confidence-value (CV) computes the risk-value using:
- Ref_Safe_Distance is a configurable parameter and CV is the time decayed confidence-value
- Minimal_Distance is the computer minimal distance 520 . If the minimal distance 520 is substantially zero, a non-zero lower bound is used instead to avoid a divide-by-zero condition.
- the method further includes comparing the risk-value with a predetermined threshold, at 360 . If the risk-value is not above the threshold, the vehicle controller 15 loops back to continue monitoring the pedestrian zone 410 and based on updated information. If the risk-value exceeds (or is equal to) the threshold value, the vehicle controller 15 compares the time to collision with another predetermined threshold, at 370 . If the time to collision is above the threshold, the vehicle controller 15 loops back to continue monitoring the pedestrian zone 410 and based on updated information. Instead, if the time to collision is less than (or equal to) the threshold, the vehicle controller 15 generates a warning for the operator of the vehicle 10 , at 380 .
- Generating the warning includes determining a warning level for generating the warning.
- the warning level is determined based on one or more parameters like the vehicle speed (S), the time to collision (C), the vehicle on-board pedestrian detection (B), as well as parameters representing environment complexity, such as visibility (V) and pedestrian detection history (P), and driver familiarity (F), among others or a combination thereof.
- the vehicle controller 15 computes a vehicle status based on the one or more parameters, at 382 .
- Computing the vehicle status includes computing the speed-parameter S as follows.
- Ref_Safe_Speed is a configurable parameter that can be predetermined and the vehicle speed is received by the vehicle controller 10 from one or more sensors in the vehicle 10 . Further, computing the vehicle status includes computing a time to collision parameter C as:
- Ref_TTC is a configurable parameter that can be predetermined.
- the vehicle status includes computing a vehicle on-board pedestrian detection parameter B, which is a binary value indicating whether the on-board pedestrian detection system of the vehicle 10 has detected a pedestrian 12 .
- Generating the warning further includes calculating an environment visibility V, at 384 .
- the visibility V can be a function of brightness, wiper movement, temperature, and other environmental parameters received from the one or more sensors of the vehicle 10 and/or from an external sources such as a computer server.
- An example function to determine V can be a look-up table, table 1.
- the visibility V is determined based on the input from a brightness (light) sensor and whether a wiper of the vehicle 10 is moving.
- the look-up table can be configured differently in other embodiments than the example above.
- the look-up table may use different, or additional parameters to determine V, such as a temperature.
- the value of V at corresponding values of brightness and wiper conditions may be different than those in the above example.
- generating the warning includes computing a driver familiarity (F) with the road/intersection at which the vehicle 10 is presently, at 385 .
- the vehicle controller 15 computes F as:
- Num_Visits is a number of visits made by the vehicle 10 to the road/intersection, which is monitored and tracked by the vehicle controller 15 .
- the vehicle controller 15 receives this number from an external system that monitors the vehicle 10 , such as a computer server.
- the number of visits may be over a predetermined duration, such as the past week, the past month, or any other predetermined duration.
- Ref_Num_Visits is a configurable parameter that can be predetermined.
- the vehicle controller 15 computes a pedestrian detection history (P) at the intersection, at 386 .
- P is based on a number of pedestrians detected at the intersection in a predetermined past time period, such as past 5 minutes, past 30 minutes, past day, and the like.
- the vehicle controller 15 computes P as:
- Ref_Pedestrian_Cnt is a configurable parameter that can be predetermined, and the Pedestrian_Cnt is the number of pedestrians detected, which may be received from the traffic controller 25 .
- the method further includes computing a warning level based on the one or more parameters computed, at 388.
- the warning level is a function of S, V, F, C, P, and B, or a combination thereof.
- the computed warning level is then used to determine a type of warning to generate, at 389 .
- the warning level is used to determine the type of warning using a look-up table, such as table 2.
- the warning types may include visual warning such as a by displaying a text/image on a vehicle display interface (VDI).
- the warning types may further include flashing the text/image on the VDI to increase an intensity of the warning, so as to attempt to attract the driver's attention.
- the warning types may further include audible warnings, such as voice, beeps, and the like.
- the warning types may further include haptic feedback, such as via a steering control, seat(s), and the like.
- the warning types may include other types of warning in other embodiments, and/or a combination of the types listed above.
- the vehicle controller 15 Once the warning type is determined, the vehicle controller 15 generates the warning for the driver, at 389 . In one or more examples, the vehicle controller 15 may adjust vehicle kinematics, such as reduce speed by applying brakes, generate an audible sound for the pedestrians 12 , for example using the horn or other audio devices of the vehicle, generate a visual indication for the pedestrians 12 , such as by flashing the lights/indicators of the vehicle, and the like, as part of the warning.
- vehicle kinematics such as reduce speed by applying brakes, generate an audible sound for the pedestrians 12 , for example using the horn or other audio devices of the vehicle, generate a visual indication for the pedestrians 12 , such as by flashing the lights/indicators of the vehicle, and the like, as part of the warning.
- the vehicle controller 15 continues to execute the method in a loop during the operation of the vehicle 10 .
- the vehicle controller 15 may be instructed to pause and/or resume the execution of the method, for example by the driver via a user-interface like a button, touch screen, and the like.
- the technical solutions described herein facilitate providing appropriate levels of warnings to the driver based on pedestrian detection.
- the technical solutions herein use time decaying function to dynamically evaluate the confidence of pedestrian detection, therefore reducing false positive alarms.
- the technical solutions herein can, hence, reduce unnecessary warnings generated for the driver.
- the technical solutions described herein improve the warning system of the vehicle, and the operation of the vehicle in general.
- the technical solutions herein calculate warning levels based on vehicle status (speed, TTC, vehicle on-board detection), environment complexity (visibility and pedestrian detection history), and driver familiarity.
- the technical solutions described herein can reduce collisions between a vehicle and pedestrians and enhance the safety of the pedestrians and/or the vehicle.
- the technical solutions described herein accordingly, evaluate risk of pedestrian collision and determine the level of warning to be provided to the driver.
- the present technical solutions may be a system, a method, and/or a computer program product at any possible technical detail level of integration
- the computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present technical solutions.
- the computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device.
- the computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Mathematical Physics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
- The subject disclosure generally relates to a vehicle, and particularly to evaluating pedestrian collision risks and determining driver warning levels based on the evaluation.
- In various environments, such as at intersections, parking places, etc., pedestrians and vehicles co-exist in a very close environment. Pedestrians are at many times walking or standing less than one foot from a slow moving vehicle. Due to the density of the traffic within a heavy populated city, vehicles often move at very slow speeds (e.g., less than 10 mph). As a result, pedestrians do not distance themselves from the vehicles; rather, pedestrians may walk, stand, or ride bikes just inches from slow moving vehicles.
- Pedestrians are typically aware of vehicles in close proximity to them due to the sound of the running engine. However, vehicles are becoming increasingly quiet during engine-on operations, and therefore, the pedestrians are less likely to hear a vehicle in close proximity. The reduction in noise of the engine is due to enhanced noise suppression as well as the increasing use of electric and hybrid electric vehicles. The actuation of the horn by the driver, although effective, is often viewed as a rude behavior and requires manual intervention by the driver of the vehicle. Some drivers are reluctant to use their horn to warn the pedestrians since it IS viewed as rude behavior and since they may underestimate the danger to the pedestrian.
- According to one or more embodiments a method to generate a pedestrian detection warning in a vehicle includes constructing, by a vehicle controller, a pedestrian zone based on pedestrian information that is received from a traffic controller. The method further includes computing, by the vehicle controller, a vehicle trajectory that predicts a path for the vehicle. The method further includes determining, by the vehicle controller, a minimal distance between the pedestrian zone and the vehicle trajectory. The method further includes predicting, by the vehicle controller, a time to collision by computing a time for the vehicle to reach a location corresponding to the minimal distance along the vehicle trajectory. The method further includes in response to the time to collision being below a threshold, generating, by the vehicle controller, a warning for an operator of the vehicle.
- In one or more examples, the pedestrian information comprises a trigger time corresponding to a push button associated with a pedestrian light. Further, the pedestrian information further comprises a pedestrian location. In one or more examples, the vehicle trajectory is computed based on vehicle information that comprises at least one of a vehicle speed, a vehicle location, and a vehicle yaw rate.
- In one or more examples, the method further includes computing a time-decay risk as:
-
- where Ref_Safe_Distance is a predetermined parameter and CV is a time decayed confidence-value indicative of a pedestrian being present in the pedestrian zone, wherein the vehicle controller predicts the time to collision in response to the time-decay risk being greater than a risk threshold. The confidence-value is computed as CV=CV+c, where c is a predetermined value, if a pedestrian is observed in the pedestrian zone, and as CVt2=CVt1+ƒ (t2−t1) wherein CVt2 is the confidence-value at time t2 if there is no updated pedestrian information since time t1, and wherein the function ƒ is a monotonically decreasing function.
- In one or more examples, generating the warning further includes selecting a warning level based on a combination of a vehicle status, an environmental visibility, and an intersection familiarity. Determining the vehicle status includes computing
-
- where Ref_Safe_Speed is a predetermined parameter, and computing
-
- where TTC is the time to collision, and Ref_TTC is a predetermined parameter. The environmental visibility is determined based on a brightness value in vicinity of the vehicle, and based on whether a wiper of the vehicle is being used. Further, the intersection familiarity is computed as
-
- where Num_Visits is a number of times the vehicle has passed the intersection in a predetermined duration, and Ref_Num_Visits is a predetermined parameter.
- According to one or more embodiments a system for pedestrian warning in a vehicle includes a traffic controller, and a vehicle controller. In one or more examples, the vehicle controller receives pedestrian information from the traffic controller to generate a pedestrian detection warning based on evaluating the pedestrian information. The generation of a pedestrian detection warning in a vehicle includes constructing, by a vehicle controller, a pedestrian zone based on pedestrian information that is received from a traffic controller. The generation further includes computing, by the vehicle controller, a vehicle trajectory that predicts a path for the vehicle. The generation further includes determining, by the vehicle controller, a minimal distance between the pedestrian zone and the vehicle trajectory. The generation further includes predicting, by the vehicle controller, a time to collision by computing a time for the vehicle to reach a location corresponding to the minimal distance along the vehicle trajectory. The generation further includes in response to the time to collision being below a threshold, generating, by the vehicle controller, a warning for an operator of the vehicle.
- In one or more examples, the pedestrian information includes a trigger time corresponding to a push button associated with a pedestrian light. The pedestrian information further includes a pedestrian location. In one or more examples, the vehicle trajectory is computed based on vehicle information that comprises at least one of a vehicle speed, a vehicle location, and a vehicle yaw rate.
- In one or more examples, the generation of the pedestrian warning further includes computing a time-decay risk as
-
- where Ref_Safe_Distance is a predetermined parameter and CV is a time decayed confidence-value indicative of a pedestrian being present in the pedestrian zone, wherein the vehicle controller predicts the time to collision in response to the time-decay risk being greater than a risk threshold. The confidence-value is computed as CV=CV+c, where c is a predetermined value, if a pedestrian is observed in the pedestrian zone, and as CVt2=CVt1+ƒ (t2−t1) wherein CVt2 is the confidence-value at time t2 if there is no updated pedestrian information since time t1, and wherein the function ƒ is a monotonically decreasing function.
- In one or more examples, generating the warning further includes selecting a warning level based on a combination of a vehicle status, an environmental visibility, and an intersection familiarity. Determining the vehicle status includes computing
-
- where Ref_Safe_Speed is a predetermined parameter, and computing
-
- where TTC is the time to collision, and Ref_TTC is a predetermined parameter. The environmental visibility is determined based on a brightness value in vicinity of the vehicle, and based on whether a wiper of the vehicle is being used. Further, the intersection familiarity is computed as
-
- where Num_Visits is a number of times the vehicle has passed the intersection in a predetermined duration, and Ref_Num_Visits is a predetermined parameter.
- According to one or more embodiments a computer program product includes one or more computer executable instructions that when executed by a vehicle controller cause the vehicle controller to generate a pedestrian detection warning for a vehicle. The generation of the pedestrian detection warning includes constructing, by a vehicle controller, a pedestrian zone based on pedestrian information that is received from a traffic controller. The generation further includes computing, by the vehicle controller, a vehicle trajectory that predicts a path for the vehicle. The generation further includes determining, by the vehicle controller, a minimal distance between the pedestrian zone and the vehicle trajectory. The generation further includes predicting, by the vehicle controller, a time to collision by computing a time for the vehicle to reach a location corresponding to the minimal distance along the vehicle trajectory. The generation further includes in response to the time to collision being below a threshold, generating, by the vehicle controller, a warning for an operator of the vehicle.
- In one or more examples, the pedestrian information includes a trigger time corresponding to a push button associated with a pedestrian light. The pedestrian information further includes a pedestrian location. In one or more examples, the vehicle trajectory is computed based on vehicle information that comprises at least one of a vehicle speed, a vehicle location, and a vehicle yaw rate.
- In one or more examples, the generation of the pedestrian warning further includes computing a time-decay risk as:
-
- where Ref_Safe_Distance is a predetermined parameter and CV is a time decayed confidence-value indicative of a pedestrian being present in the pedestrian zone, wherein the vehicle controller predicts the time to collision in response to the time-decay risk being greater than a risk threshold. The confidence-value is computed as CV=CV+c, where c is a predetermined value, if a pedestrian is observed in the pedestrian zone, and as CVt2=CVt1+ƒ (t2−t1) wherein CVt2 is the confidence-value at time t2 if there is no updated pedestrian information since time t1, and wherein the function ƒ is a monotonically decreasing function.
- In one or more examples, generating the warning further includes selecting a warning level based on a combination of a vehicle status, an environmental visibility, and an intersection familiarity. Determining the vehicle status includes computing
-
- where Ref_Safe_Speed is a predetermined parameter, and computing
-
- where TTC is the time to collision, and Ref_TTC is a predetermined parameter. The environmental visibility is determined based on a brightness value in vicinity of the vehicle, and based on whether a wiper of the vehicle is being used. Further, the intersection familiarity is computed as
-
- where Num_Visits is a number of times the vehicle has passed the intersection in a predetermined duration, and Ref_Num_Visits is a predetermined parameter.
- The above features and advantages, and other features and advantages of the disclosure are readily apparent from the following detailed description when taken in connection with the accompanying drawings.
- Other features, advantages and details appear, by way of example only, in the following detailed description, the detailed description referring to the drawings in which:
-
FIG. 1 is a plan view of a vehicle sensing pedestrians according to one or more embodiments; -
FIG. 2 depicts a block diagram of a traffic controller according to one or more embodiments; -
FIG. 3 depicts a flowchart of an example method for evaluating a risk of pedestrian collision and generating a selected warning in response according to one or more embodiments; -
FIG. 4 depicts pedestrian zones according to one or more embodiments; and -
FIG. 5 depicts at least two example scenarios of predicted trajectories. - The following description is merely exemplary in nature and is not intended to limit the present disclosure, its application or uses. It should be understood that throughout the drawings, corresponding reference numerals indicate like or corresponding parts and features. As used herein, the term module refers to processing circuitry that may include an application specific integrated circuit (ASIC), an electronic circuit, a processor (shared, dedicated, or group) and memory that executes one or more software or firmware programs, a combinational logic circuit, and/or other suitable components that provide the described functionality.
-
FIG. 1 is a plan view of a vehicle sensing pedestrians according to one or more embodiments. In the illustrated example scenario, avehicle 10 is traveling along a roadway 11 in a densely populated area wheremultiple pedestrians 12 travel on different sides of thevehicle 10. Thevehicle 10 may travel within the populated area at slow speeds due to traffic congestion caused by an excessive number of vehicles on the road and number of pedestrians crossing the roads at intersections. Thepedestrians 12 includes walking pedestrians, jogging pedestrians, or cycling pedestrians in the roadway and on nearby sidewalks. Roadways may also include pedestrian lanes disposed adjacent to the curb (not shown) in the road and is used for runners and bicyclers. - The
vehicle 10 is equipped with asensing device 14 that includes one or more sensors or like devices that are regionally disposed around the vehicle for sensing pedestrians proximate to thevehicle 10. The sensors may be disposed at the front of thevehicle 16 and the front corners of thevehicle 18 in addition to the rear of thevehicle 20 and the rear corners of thevehicle 22. Thevehicle 10 includes acontroller 15 that analyzes the information received from the one or more sensors to detect a pedestrian. In addition, thevehicle 10 receives pedestrian information from external devices. For example, atraffic controller 25 is shown that sends pedestrian information to thecontroller 15. Thetraffic controller 25 uses infrastructure sensors, along the road etc., external to thevehicle 10, to detectpedestrians 12. Based on the pedestrian information, thecontroller 15 generates one or more warnings for the operator of thevehicle 10. - In one or more examples, the infrastructure sensors (such as the cameras) are mounted high over an intersection and have a broader view of an intersection and/or roadside along which the
vehicle 10 is traveling. Accordingly, human drivers and the vehicle built-in sensors are limited by line-of-sight and environment visibility, for example, the driver's view is blocked by other vehicles, trees, buildings at an intersection. Hence, the technical solutions described herein facilitate thevehicle controller 15 to utilize the infrastructure sensors to detect the presence of pedestrians and share the information with passingvehicles 10. The technical solutions described herein accordingly facilitate extending the range of sensing for thevehicle 10 and also enhance the environment visibility. -
FIG. 2 depicts a block diagram of a traffic controller according to one or more embodiments. As illustrated thetraffic controller 25 obtains pedestrian information from one ormore infrastructure sensors 210. Theinfrastructure sensors 210 include various types of sensors such as a push button 212, aninfrared sensor 214, anultrasound sensor 216, acamera 218, and the like. The information received from theinfrared sensors 210 is used by thetraffic controller 25 to detect the presence ofpedestrians 12. Thetraffic controller 25 uses a roadside unit (RSU) 220 to broadcast the pedestrian info to nearby vehicles, such as thevehicle 10. Here, nearby vehicles include vehicles within a predetermined vicinity or range in which theRSU 220 can broadcast information. For example, theRSU 220 may use wireless communication protocols for broadcasting vehicle information, such as Dedicated Short Range Communications (DSRC) to transmit the pedestrian information to thevehicle controller 15. - The vehicle controller 15 (
FIG. 1 ) evaluates a risk of collision between thevehicle 10 and one or more detectedpedestrians 12. Based on the evaluation, thevehicle controller 15 gives a driver a selected level of warning, such as image warning, voice warning, haptic warning, etc. Selecting the level of warning includes suppressing one or more warnings, and determining an appropriate level of warning for the driver according to the evaluation. -
FIG. 3 depicts a flowchart of an example method for evaluating a risk of pedestrian collision and generating a selected warning in response according to one or more embodiments. The method may be executed by thevehicle controller 15, in one or more examples. The method includes thevehicle controller 15 receiving the pedestrian information from thetraffic controller 25, at 310. The pedestrian information includes pedestrian light SPaT (Signal Phase and Timing) information. For example, the SPaT includes information when apedestrian 12 activates a pedestrian crossing button. Alternatively, or in addition, the SPaT includes pedestrian crossing signal information from an automated pedestrian crossing system that is activated automatically on a periodic basis or in response to detecting a pedestrian. The pedestrian information received may further include a timestamp that indicates push-button trigger time, or when the pedestrian crossing was activated in case of an automated crossing system. Alternatively, or in addition, the pedestrian information further includes pedestrian location, for example, obtained from thecamera 218, the infrared 214, and/or ultrasonic 216 sensors. - In one or more examples, the
vehicle controller 15 also receives a map from theroad side unit 220, at 310. The map may include a crosswalk or intersection map at which thetraffic controller 25 is installed. The map includes dimensions of the crosswalk or intersection. - The method further includes constructing pedestrian zones, at 320.
FIG. 4 depicts pedestrian zones according to one or more embodiments. Apedestrian zone 410 represents an area in which one ormore pedestrian 12 may appear. Depending on the pedestrian information received, thepedestrian zone 410 thevehicle controller 15 generatesdifferent pedestrian zones 410. For example, in case of low-resolution sensors like the push-button 212, thevehicle controller 15 uses the entire crosswalk that covers the entire dimension of the road as thepedestrian zone 410. In case of higher resolution information from theinfrastructure sensors 210, thevehicle controller 15 constructs apedestrian zone 410 that represents a rectangular area apedestrian 12 is walking toward. The dimensions of the rectangular area is of a predetermined dimension. - The
vehicle controller 15 constructs thepedestrian zone 410 using the pedestrian information that includes a location, a moving speed, a direction, an update time, a last observed location, and the like that is obtained from the one ormore infrastructure sensors 210 and received from thetraffic controller 25. - Referring back to the flowchart in
FIG. 3 , the method further includes predicting a vehicle trajectory for thevehicle 10, at 330. Thevehicle controller 15 obtains vehicle information for generating the vehicle trajectory. The vehicle information includes speed, location (from a Global Navigation Satellite System (GNSS), for example Global Positioning System (GPS)), an orientation, whether the vehicle is in leftmost/rightmost lane, status of the turn signals, a yaw rate, steering wheel angle and the like or a combination thereof. Thevehicle controller 15 receives the vehicle information from the one or more subsystems in thevehicle 10 or from one or more systems external to thevehicle 10. For example, a system such as ONSTAR™ may monitor thevehicle 10 and provide such vehicle information to thevehicle controller 15 periodically or when requested. -
FIG. 5 depicts at least two example scenarios of predictedtrajectories 510 for thevehicle 10. The predictedtrajectory 510 can be substantially a straight line or a curve as illustrated. It should be noted that the predictedtrajectory 510 can be any different shape in other examples. Thevehicle controller 15 may perform the trajectory prediction using any of the one or more techniques that are known or that will be developed. - Referring back to the flowchart of
FIG. 3 , the method further includes calculating a minimal distance and time-to-collision, at 340. Theminimal distance 520 is calculated at a point which is at the minimum distance between thepedestrian zone 410 and thevehicle trajectory 510. Depending on thepedestrian zone 410 and the predictedtrajectory 510, theminimal distance 520 varies. Further, once theminimal distance 520 and the point corresponding to theminimal distance 520 is identified, thevehicle controller 15 can compute the time before thevehicle 10 reaches the corresponding minimal distance point to thepedestrian zone 410. The computed time along the predictedtrajectory 510 is the time to collision. - The method further includes calculating a time decayed risk, at 350. Calculating the risk includes computing a time decaying confidence function to represent a confidence of pedestrian presence in the
pedestrian zone 410. The confidence function calculation increases a confidence-value (CV) if apedestrian 12 is detected, and decreases the confidence-value (CV) gradually since last detection ofpedestrians 12 in thepedestrian zone 410. For example, the confidence function computes CV=CV+c, ifpedestrians 12 are observed in thepedestrian zone 410 where c is a predetermined constant. Further, the confidence value CV is updated as CVt2=CVt1+ƒ (t2−t1) where CVt2 is the confidence-value at t2 if no observation update since time t1, where the function ƒ can be any monotonically decreasing function that is predetermined. - The
vehicle controller 15, after updating the confidence-value (CV) computes the risk-value using: -
- Here, Ref_Safe_Distance is a configurable parameter and CV is the time decayed confidence-value, and the Minimal_Distance is the computer
minimal distance 520. If theminimal distance 520 is substantially zero, a non-zero lower bound is used instead to avoid a divide-by-zero condition. - The method further includes comparing the risk-value with a predetermined threshold, at 360. If the risk-value is not above the threshold, the
vehicle controller 15 loops back to continue monitoring thepedestrian zone 410 and based on updated information. If the risk-value exceeds (or is equal to) the threshold value, thevehicle controller 15 compares the time to collision with another predetermined threshold, at 370. If the time to collision is above the threshold, thevehicle controller 15 loops back to continue monitoring thepedestrian zone 410 and based on updated information. Instead, if the time to collision is less than (or equal to) the threshold, thevehicle controller 15 generates a warning for the operator of thevehicle 10, at 380. - Generating the warning includes determining a warning level for generating the warning. The warning level is determined based on one or more parameters like the vehicle speed (S), the time to collision (C), the vehicle on-board pedestrian detection (B), as well as parameters representing environment complexity, such as visibility (V) and pedestrian detection history (P), and driver familiarity (F), among others or a combination thereof.
- The
vehicle controller 15 computes a vehicle status based on the one or more parameters, at 382. Computing the vehicle status includes computing the speed-parameter S as follows. -
- Here, Ref_Safe_Speed is a configurable parameter that can be predetermined and the vehicle speed is received by the
vehicle controller 10 from one or more sensors in thevehicle 10. Further, computing the vehicle status includes computing a time to collision parameter C as: -
- where Ref_TTC is a configurable parameter that can be predetermined.
- Further, the vehicle status includes computing a vehicle on-board pedestrian detection parameter B, which is a binary value indicating whether the on-board pedestrian detection system of the
vehicle 10 has detected apedestrian 12. - Generating the warning further includes calculating an environment visibility V, at 384. The visibility V can be a function of brightness, wiper movement, temperature, and other environmental parameters received from the one or more sensors of the
vehicle 10 and/or from an external sources such as a computer server. An example function to determine V can be a look-up table, table 1. -
TABLE 1 Visibility (V) Brightness Wiper 0 (good visibility) day Not moving 0.5 (medium) day Moving 0.6 (medium) Night Not moving 1.0 (low visibility) night Moving - Here, the visibility V is determined based on the input from a brightness (light) sensor and whether a wiper of the
vehicle 10 is moving. It should be noted that the look-up table can be configured differently in other embodiments than the example above. For example, the look-up table may use different, or additional parameters to determine V, such as a temperature. Alternatively, or in addition, in other embodiments, the value of V at corresponding values of brightness and wiper conditions may be different than those in the above example. - Further, generating the warning includes computing a driver familiarity (F) with the road/intersection at which the
vehicle 10 is presently, at 385. Thevehicle controller 15 computes F as: -
- Here, Num_Visits is a number of visits made by the
vehicle 10 to the road/intersection, which is monitored and tracked by thevehicle controller 15. Alternatively, or in addition, thevehicle controller 15 receives this number from an external system that monitors thevehicle 10, such as a computer server. In one or more examples, the number of visits may be over a predetermined duration, such as the past week, the past month, or any other predetermined duration. Further, Ref_Num_Visits is a configurable parameter that can be predetermined. - Further, the
vehicle controller 15 computes a pedestrian detection history (P) at the intersection, at 386. P is based on a number of pedestrians detected at the intersection in a predetermined past time period, such as past 5 minutes, past 30 minutes, past day, and the like. Thevehicle controller 15 computes P as: -
- Here, Ref_Pedestrian_Cnt is a configurable parameter that can be predetermined, and the Pedestrian_Cnt is the number of pedestrians detected, which may be received from the
traffic controller 25. - The method further includes computing a warning level based on the one or more parameters computed, at 388. In one or more examples, the warning level is a function of S, V, F, C, P, and B, or a combination thereof. For example, Warning_Level=w1S+w2V+w3F+w4C+w5P+w6B, where wi are configurable weights, i.e. Σ wi=1. The computed warning level is then used to determine a type of warning to generate, at 389. In one or more examples, the warning level is used to determine the type of warning using a look-up table, such as table 2.
-
TABLE 2 Warning Level Value Type of Warning <0.2 No Warning <0.4 Text/Image <0.8 Flashing Text/Image >0.8 Voice and Haptic - As shown in the above example, based on the warning level being within a particular range, the type of warning varies. The warning types may include visual warning such as a by displaying a text/image on a vehicle display interface (VDI). The warning types may further include flashing the text/image on the VDI to increase an intensity of the warning, so as to attempt to attract the driver's attention. The warning types may further include audible warnings, such as voice, beeps, and the like. The warning types may further include haptic feedback, such as via a steering control, seat(s), and the like. The warning types may include other types of warning in other embodiments, and/or a combination of the types listed above. It should be noted that the above look-up table, table 2, is an example, and that in other embodiments different ranges of warning levels may use different warning types than those depicted herein. Once the warning type is determined, the
vehicle controller 15 generates the warning for the driver, at 389. In one or more examples, thevehicle controller 15 may adjust vehicle kinematics, such as reduce speed by applying brakes, generate an audible sound for thepedestrians 12, for example using the horn or other audio devices of the vehicle, generate a visual indication for thepedestrians 12, such as by flashing the lights/indicators of the vehicle, and the like, as part of the warning. - The
vehicle controller 15 continues to execute the method in a loop during the operation of thevehicle 10. In one or more examples, thevehicle controller 15 may be instructed to pause and/or resume the execution of the method, for example by the driver via a user-interface like a button, touch screen, and the like. - Accordingly, the technical solutions described herein facilitate providing appropriate levels of warnings to the driver based on pedestrian detection. The technical solutions herein use time decaying function to dynamically evaluate the confidence of pedestrian detection, therefore reducing false positive alarms. The technical solutions herein can, hence, reduce unnecessary warnings generated for the driver. The technical solutions described herein improve the warning system of the vehicle, and the operation of the vehicle in general. The technical solutions herein calculate warning levels based on vehicle status (speed, TTC, vehicle on-board detection), environment complexity (visibility and pedestrian detection history), and driver familiarity. Further yet, the technical solutions described herein can reduce collisions between a vehicle and pedestrians and enhance the safety of the pedestrians and/or the vehicle. The technical solutions described herein, accordingly, evaluate risk of pedestrian collision and determine the level of warning to be provided to the driver.
- The present technical solutions may be a system, a method, and/or a computer program product at any possible technical detail level of integration. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present technical solutions.
- The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
- While the above disclosure has been described with reference to exemplary embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from its scope. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the disclosure without departing from the essential scope thereof. Therefore, it is intended that the present disclosure not be limited to the particular embodiments disclosed, but will include all embodiments falling within the scope thereof.
Claims (20)
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/896,669 US10363944B1 (en) | 2018-02-14 | 2018-02-14 | Method and apparatus for evaluating pedestrian collision risks and determining driver warning levels |
CN201910109848.0A CN110155048B (en) | 2018-02-14 | 2019-02-11 | Method and apparatus for assessing pedestrian impact risk and determining driver warning level |
DE102019103354.3A DE102019103354A1 (en) | 2018-02-14 | 2019-02-11 | METHOD AND DEVICE FOR EVALUATING COLLISION RISKS OF PEDESTRIANS AND FOR DETERMINING DRIVER WARNING LEVELS |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/896,669 US10363944B1 (en) | 2018-02-14 | 2018-02-14 | Method and apparatus for evaluating pedestrian collision risks and determining driver warning levels |
Publications (2)
Publication Number | Publication Date |
---|---|
US10363944B1 US10363944B1 (en) | 2019-07-30 |
US20190248381A1 true US20190248381A1 (en) | 2019-08-15 |
Family
ID=67394259
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US15/896,669 Active US10363944B1 (en) | 2018-02-14 | 2018-02-14 | Method and apparatus for evaluating pedestrian collision risks and determining driver warning levels |
Country Status (3)
Country | Link |
---|---|
US (1) | US10363944B1 (en) |
CN (1) | CN110155048B (en) |
DE (1) | DE102019103354A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210107402A1 (en) * | 2019-10-10 | 2021-04-15 | Hyundai Mobis Co., Ltd. | Apparatus and method for giving warning about vehicle in violation of traffic signal at intersection |
CN113442830A (en) * | 2020-03-24 | 2021-09-28 | 深圳市超捷通讯有限公司 | Traffic safety control method and vehicle-mounted device |
EP3957532A1 (en) * | 2020-03-19 | 2022-02-23 | Cartica AI Ltd. | Predictive turning assistant |
EP3943355A3 (en) * | 2020-07-24 | 2022-04-13 | Tusimple, Inc. | Visibility condition determinations for autonomous driving operations |
US20220262122A1 (en) * | 2021-02-16 | 2022-08-18 | Toyota Jidosha Kabushiki Kaisha | Image collection apparatus and image collection method |
US20220397402A1 (en) * | 2019-11-11 | 2022-12-15 | Mobileye Vision Technologies Ltd. | Systems and methods for determining road safety |
US11710408B2 (en) | 2020-03-03 | 2023-07-25 | Honda Motor Co., Ltd. | Communication apparatus, vehicle, computer-readable storage medium, and communication method |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102106345B1 (en) * | 2018-04-25 | 2020-05-04 | 주식회사 만도 | Rear-side alert system and controlling method thereof |
KR20190084916A (en) * | 2019-06-28 | 2019-07-17 | 엘지전자 주식회사 | Apparatus for informing parking position and method thereof |
US11345342B2 (en) * | 2019-09-27 | 2022-05-31 | Intel Corporation | Potential collision warning system based on road user intent prediction |
CN111645676B (en) * | 2020-01-19 | 2022-08-26 | 摩登汽车有限公司 | Vehicle avoidance method, device, equipment and automobile |
CN111402632B (en) * | 2020-03-18 | 2022-06-07 | 五邑大学 | Risk prediction method for pedestrian movement track at intersection |
EP3886076A1 (en) * | 2020-03-27 | 2021-09-29 | Aptiv Technologies Limited | Warning system for a host automotive vehicle |
US11491976B2 (en) * | 2020-04-21 | 2022-11-08 | Baidu Usa Llc | Collision warning system for safety operators of autonomous vehicles |
US11682272B2 (en) * | 2020-07-07 | 2023-06-20 | Nvidia Corporation | Systems and methods for pedestrian crossing risk assessment and directional warning |
CN112533174B (en) * | 2020-11-24 | 2021-11-09 | 东风汽车集团有限公司 | Early warning and communication redundancy method and system for red light running scene based on C-V2X |
CN112440986B (en) * | 2020-11-30 | 2022-08-09 | 重庆长安汽车股份有限公司 | Driving control method, pedestrian AEB system, intelligent driving automobile, controller and computer readable storage medium |
JP7250070B2 (en) * | 2021-06-18 | 2023-03-31 | 本田技研工業株式会社 | WARNING CONTROL DEVICE, MOBILE, WARNING CONTROL METHOD, AND PROGRAM |
CN113656893B (en) * | 2021-08-19 | 2024-03-26 | 奇瑞汽车股份有限公司 | Pedestrian protection checking method and device and computer storage medium |
CN114312836A (en) * | 2021-12-24 | 2022-04-12 | 阿波罗智联(北京)科技有限公司 | Method, device, equipment and storage medium for automatically driving vehicle to give way to pedestrians |
CN115116268B (en) * | 2022-06-13 | 2023-11-17 | 武汉理工大学 | Rural traffic early warning method and system |
CN115139999B (en) * | 2022-06-28 | 2023-09-15 | 重庆长安汽车股份有限公司 | Vehicle and pedestrian anti-collision control method and device, electronic equipment and storage medium |
CN115083208B (en) * | 2022-07-20 | 2023-02-03 | 深圳市城市交通规划设计研究中心股份有限公司 | Human-vehicle conflict early warning method, early warning analysis method, electronic device and storage medium |
CN115240429B (en) * | 2022-08-11 | 2023-02-14 | 深圳市城市交通规划设计研究中心股份有限公司 | Pedestrian and vehicle flow statistical method, electronic equipment and storage medium |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050073438A1 (en) * | 2003-09-23 | 2005-04-07 | Rodgers Charles E. | System and method for providing pedestrian alerts |
US20120025964A1 (en) * | 2010-07-27 | 2012-02-02 | Beggs Ryan P | Methods and apparatus to detect and warn proximate entities of interest |
US20120223843A1 (en) * | 2008-03-25 | 2012-09-06 | Wall Richard W | Advanced accessible pedestrian control system for the physically disabled |
US8849494B1 (en) * | 2013-03-15 | 2014-09-30 | Google Inc. | Data selection by an autonomous vehicle for trajectory modification |
US20150032288A1 (en) * | 2013-07-25 | 2015-01-29 | GM Global Technology Operations LLC | System and method for warning of a possible collision of a motor vehicle with an object |
US20150035685A1 (en) * | 2013-08-02 | 2015-02-05 | Honda Patent & Technologies North America, LLC | Vehicle to pedestrian communication system and method |
US8996224B1 (en) * | 2013-03-15 | 2015-03-31 | Google Inc. | Detecting that an autonomous vehicle is in a stuck condition |
US9008890B1 (en) * | 2013-03-15 | 2015-04-14 | Google Inc. | Augmented trajectories for autonomous vehicles |
US9381916B1 (en) * | 2012-02-06 | 2016-07-05 | Google Inc. | System and method for predicting behaviors of detected objects through environment representation |
US20170169703A1 (en) * | 2014-07-25 | 2017-06-15 | Transoft Solutions Inc. | Onboard traffic and pedestrian warning systems and methods having optical and audio signal feedback and control |
US9786178B1 (en) * | 2013-08-02 | 2017-10-10 | Honda Motor Co., Ltd. | Vehicle pedestrian safety system and methods of use and manufacture thereof |
US20170291602A1 (en) * | 2016-04-11 | 2017-10-12 | David E. Newman | Systems and methods for hazard mitigation |
US9805474B1 (en) * | 2016-05-09 | 2017-10-31 | Iteris, Inc. | Pedestrian tracking at a traffic intersection to identify vulnerable roadway users for traffic signal timing, pedestrian safety, and traffic intersection control |
US9884585B1 (en) * | 2016-09-19 | 2018-02-06 | Faraday & Future Inc. | Exterior vehicle alerting system |
US9908470B1 (en) * | 2015-03-23 | 2018-03-06 | Rosco, Inc. | Collision avoidance and/or pedestrian detection system |
US20180118106A1 (en) * | 2016-11-01 | 2018-05-03 | Hyundai Motor Company | Vehicle and control method thereof |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9250324B2 (en) * | 2013-05-23 | 2016-02-02 | GM Global Technology Operations LLC | Probabilistic target selection and threat assessment method and application to intersection collision alert system |
KR102338554B1 (en) * | 2015-03-16 | 2021-12-15 | 주식회사 만도모빌리티솔루션즈 | Autonomous emergency braking system and control method thereof |
-
2018
- 2018-02-14 US US15/896,669 patent/US10363944B1/en active Active
-
2019
- 2019-02-11 CN CN201910109848.0A patent/CN110155048B/en active Active
- 2019-02-11 DE DE102019103354.3A patent/DE102019103354A1/en active Pending
Patent Citations (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050073438A1 (en) * | 2003-09-23 | 2005-04-07 | Rodgers Charles E. | System and method for providing pedestrian alerts |
US20120223843A1 (en) * | 2008-03-25 | 2012-09-06 | Wall Richard W | Advanced accessible pedestrian control system for the physically disabled |
US20120025964A1 (en) * | 2010-07-27 | 2012-02-02 | Beggs Ryan P | Methods and apparatus to detect and warn proximate entities of interest |
US9381916B1 (en) * | 2012-02-06 | 2016-07-05 | Google Inc. | System and method for predicting behaviors of detected objects through environment representation |
US9766626B1 (en) * | 2012-02-06 | 2017-09-19 | Waymo Llc | System and method for predicting behaviors of detected objects through environment representation |
US8996224B1 (en) * | 2013-03-15 | 2015-03-31 | Google Inc. | Detecting that an autonomous vehicle is in a stuck condition |
US9008890B1 (en) * | 2013-03-15 | 2015-04-14 | Google Inc. | Augmented trajectories for autonomous vehicles |
US9541410B1 (en) * | 2013-03-15 | 2017-01-10 | Google Inc. | Augmented trajectories for autonomous vehicles |
US8849494B1 (en) * | 2013-03-15 | 2014-09-30 | Google Inc. | Data selection by an autonomous vehicle for trajectory modification |
US9933784B1 (en) * | 2013-03-15 | 2018-04-03 | Waymo Llc | Augmented trajectories for autonomous vehicles |
US20150032288A1 (en) * | 2013-07-25 | 2015-01-29 | GM Global Technology Operations LLC | System and method for warning of a possible collision of a motor vehicle with an object |
US20170372612A1 (en) * | 2013-08-02 | 2017-12-28 | Honda Motor Co., Ltd. | Vehicle pedestrian safety system and methods of use and manufacture thereof |
US20150035685A1 (en) * | 2013-08-02 | 2015-02-05 | Honda Patent & Technologies North America, LLC | Vehicle to pedestrian communication system and method |
US9786178B1 (en) * | 2013-08-02 | 2017-10-10 | Honda Motor Co., Ltd. | Vehicle pedestrian safety system and methods of use and manufacture thereof |
US20180096605A1 (en) * | 2013-08-02 | 2018-04-05 | Honda Motor Co., Ltd. | Vehicle pedestrian safety system and methods of use and manufacture thereof |
US20170169703A1 (en) * | 2014-07-25 | 2017-06-15 | Transoft Solutions Inc. | Onboard traffic and pedestrian warning systems and methods having optical and audio signal feedback and control |
US9908470B1 (en) * | 2015-03-23 | 2018-03-06 | Rosco, Inc. | Collision avoidance and/or pedestrian detection system |
US20170291602A1 (en) * | 2016-04-11 | 2017-10-12 | David E. Newman | Systems and methods for hazard mitigation |
US20170323448A1 (en) * | 2016-05-09 | 2017-11-09 | Iteris, Inc. | Pedestrian tracking at a traffic intersection to identify vulnerable roadway users for traffic signal timing, pedestrian safety, and traffic intersection control |
US9805474B1 (en) * | 2016-05-09 | 2017-10-31 | Iteris, Inc. | Pedestrian tracking at a traffic intersection to identify vulnerable roadway users for traffic signal timing, pedestrian safety, and traffic intersection control |
US9884585B1 (en) * | 2016-09-19 | 2018-02-06 | Faraday & Future Inc. | Exterior vehicle alerting system |
US20180118106A1 (en) * | 2016-11-01 | 2018-05-03 | Hyundai Motor Company | Vehicle and control method thereof |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210107402A1 (en) * | 2019-10-10 | 2021-04-15 | Hyundai Mobis Co., Ltd. | Apparatus and method for giving warning about vehicle in violation of traffic signal at intersection |
US11794645B2 (en) * | 2019-10-10 | 2023-10-24 | Hyundai Mobis Co., Ltd. | Apparatus and method for giving warning about vehicle in violation of traffic signal at intersection |
US20220397402A1 (en) * | 2019-11-11 | 2022-12-15 | Mobileye Vision Technologies Ltd. | Systems and methods for determining road safety |
US11710408B2 (en) | 2020-03-03 | 2023-07-25 | Honda Motor Co., Ltd. | Communication apparatus, vehicle, computer-readable storage medium, and communication method |
EP3957532A1 (en) * | 2020-03-19 | 2022-02-23 | Cartica AI Ltd. | Predictive turning assistant |
CN113442830A (en) * | 2020-03-24 | 2021-09-28 | 深圳市超捷通讯有限公司 | Traffic safety control method and vehicle-mounted device |
US11465625B2 (en) * | 2020-03-24 | 2022-10-11 | Mobile Drive Netherlands B.V. | Traffic safety control method, vehicle-mounted device and readable storage medium |
EP3943355A3 (en) * | 2020-07-24 | 2022-04-13 | Tusimple, Inc. | Visibility condition determinations for autonomous driving operations |
US11505213B2 (en) | 2020-07-24 | 2022-11-22 | Tusimple, Inc. | Visibility condition determinations for autonomous driving operations |
US20220262122A1 (en) * | 2021-02-16 | 2022-08-18 | Toyota Jidosha Kabushiki Kaisha | Image collection apparatus and image collection method |
Also Published As
Publication number | Publication date |
---|---|
US10363944B1 (en) | 2019-07-30 |
CN110155048B (en) | 2022-08-09 |
CN110155048A (en) | 2019-08-23 |
DE102019103354A1 (en) | 2019-08-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10363944B1 (en) | Method and apparatus for evaluating pedestrian collision risks and determining driver warning levels | |
US10800455B2 (en) | Vehicle turn signal detection | |
KR102072188B1 (en) | Methods, control units and systems for avoiding collisions with vulnerable road users | |
US9751506B2 (en) | Algorithms for avoiding automotive crashes at left and right turn intersections | |
US9983591B2 (en) | Autonomous driving at intersections based on perception data | |
US20170113683A1 (en) | Methods of improving performance of automotive intersection turn assist features | |
JP5573418B2 (en) | Alarm device | |
JP5360076B2 (en) | Obstacle notification device | |
EP3078515A1 (en) | Collision avoidance based on front wheel off tracking during reverse operation | |
EP3573035A1 (en) | Vehicle behavior prediction method and vehicle behavior prediction apparatus | |
US10068472B2 (en) | Automotive lane discipline system, method, and apparatus | |
US20130058116A1 (en) | Method and device for changing a light emission of at least one headlight of a vehicle | |
KR20180060860A (en) | Collision avoidance apparatus and method preventing collision between objects | |
JP4604691B2 (en) | Alarm device for vehicle, alarm method of vehicle surrounding situation | |
JP2018024291A (en) | Vehicle external display processing apparatus and vehicle external display system | |
US20200353863A1 (en) | Method and system to avoid vehicle collision | |
US11279352B2 (en) | Vehicle control device | |
JP2021175630A (en) | Driving support device | |
US10948303B2 (en) | Vehicle control device | |
JP2009140145A (en) | Vehicle travel-supporting device | |
CN114620035A (en) | Wrong-way driving detection and collision mitigation | |
RU2712732C2 (en) | Method, system and computer-readable media for identifying device for receiving barrier | |
EP4372715A1 (en) | Vehicle collision threat assessment | |
JP2023104628A (en) | Vehicle control device | |
JP2024030868A (en) | Vehicle control device, vehicle control method, and vehicle control computer program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
AS | Assignment |
Owner name: GM GLOBAL TECHNOLOGY OPERATIONS LLC, MICHIGAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:YU, BO;BORDO, ROBERT A.;VIJAYA KUMAR, VIVEK;AND OTHERS;SIGNING DATES FROM 20180326 TO 20180327;REEL/FRAME:045374/0504 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 4 |