Granted Patent B2

US 12,344,255 · App. 17/689,490 · Granted Jul 1, 2025

Inventors: Seyhan Ucar (Mountain View, CA); Emrah Akin Sisbot (Mountain View, CA); Kentaro Oguchi (Mountain View, CA)

B60W40/09B60W60/0017B60W2540/22

Abstract

Claims (50)

1. A system of an ego vehicle comprising:

a vehicle control system;

a non-transitory memory; and

an onboard unit communicatively coupled to the non-transitory memory and the vehicle control system, wherein the non-transitory memory stores computer readable code that is operable, when executed by the onboard unit, to cause the onboard unit to execute steps including:

sensing a remote vehicle to generate sensor data describing the remote vehicle and driving behavior of the remote vehicle;

classifying a type of the remote vehicle based on the sensor data;

retrieving a behavior profile for the type of the remote vehicle that identifies criteria for the type of the remote vehicle and classifications of abnormal driving behavior and normal driving behavior based on the criteria, wherein classifications of normality are variable based on the type of the remote vehicle;

comparing the driving behavior of the remote vehicle to the behavior profile for the type of the remote vehicle;

determining that the driving behavior of the remote vehicle is abnormal based on the comparing and a driving maneuver to execute to eliminate an origin of the abnormal driving behavior, wherein the ego vehicle is autonomous; and

autonomously executing, by the vehicle control system of the ego vehicle, the driving maneuver to eliminate the origin of the abnormal driving behavior.

2. The system of claim 1 , wherein the steps further include:

providing a notification to a driver of the ego vehicle that the remote vehicle is driving abnormally.

3. The system of claim 2 , wherein retrieving the behavior profile includes querying a behavior model for the behavior profile and the steps further include:

receiving feedback from the driver that the remote vehicle is abnormal; and

updating the behavior model with the feedback from the driver to change parameters for determining that the driving behavior of the remote vehicle is normal.

4. The system of claim 1 , wherein determining that the behavior of the remote vehicle is abnormal includes determining that the behavior of the remote vehicle satisfies a threshold similarity to the abnormal driving behavior in the behavior profile for the type of remote vehicle.

5. The system of claim 1 , wherein the sensor data includes an image of the remote vehicle and wherein classifying the type of the remote vehicle includes comparing the image of the remote vehicle to a set of reference images of different types of vehicles.

6. The system of claim 1 , wherein classifying the type of the remote vehicle is further based on information in a vehicle-to-everything (V2X) message received from the remote vehicle.

7. The system of claim 1 , wherein retrieving the behavior profile includes receiving a predefined behavior profile from an edge server or a cloud server.

8. The system of claim 1 , wherein the steps further include:

prior to the sensing, receiving a request from a driver to determine whether the driving behavior of the remote vehicle is abnormal.

9. The system of claim 1 , wherein sensing the remote vehicle occurs responsive to determining that the ego vehicle is in a driving scenario and that a driver of the ego vehicle requested a determination of whether the behavior of the remote vehicle is abnormal when the ego vehicle is in the driving scenario.

10. A method executed by a vehicle control system and an onboard unit of an ego vehicle, the method comprising:

sensing, by a sensor set of the ego vehicle, a remote vehicle to generate sensor data describing driving behavior of the remote vehicle;

classifying a type of the remote vehicle based on the sensor data;

retrieving a behavior profile for the type of the remote vehicle that identifies criteria for the type of the remote vehicle and classifications of abnormal behavior and normal behavior based on the criteria, wherein classifications of normality are variable based on the type of the remote vehicle;

comparing the behavior of the remote vehicle to the behavior profile for the type of the remote vehicle;

determining that the behavior of the remote vehicle is normal based on the comparing, wherein the ego vehicle is autonomous; and

autonomously executing, by the vehicle control system of the ego vehicle, a driving maneuver to eliminate an origin of the abnormal driving behavior.

11. The method of claim 10 , wherein retrieving the behavior profile includes querying a behavior model stored on the ego vehicle for the behavior profile and the method further comprises:

receiving feedback from a driver that the driving behavior is abnormal; and

updating the behavior model with the feedback from the driver to classify the behavior of the remote vehicle as abnormal.

12. The method of claim 10 , wherein the sensor data includes an image of the remote vehicle and wherein classifying the type of the remote vehicle includes comparing the image of the remote vehicle to a set of reference images of different types of vehicles.

13. The method of claim 10 , wherein classifying the type of the remote vehicle is further based on information in a vehicle-to-everything (V2X) message received from the remote vehicle.

14. The method of claim 10 , wherein retrieving the behavior profile includes receiving a predefined behavior profile from an edge server or a cloud server.

15. The method of claim 10 , wherein the behavior of the remote vehicle is normal for the type of vehicle when the type of the remote vehicle is not a car and is abnormal if the type of the remote vehicle is the car.

16. A computer program product including computer code stored on a non-transitory memory that is operable, when executed by an onboard unit of an ego vehicle that is communicatively coupled to a vehicle control system, to cause the onboard unit to execute operations including:

sensing, by a sensor set of the ego vehicle, a remote vehicle to generate sensor data describing the remote vehicle and driving behavior of the remote vehicle;

classifying a type of the remote vehicle based on the sensor data;

retrieving a behavior profile for the type of the remote vehicle that identifies criteria for the type of the remote vehicle and classifications of abnormal driving behavior and normal driving behavior based on the criteria, wherein classifications of normality are variable based on the type of the remote vehicle;

comparing the driving behavior of the remote vehicle to the behavior profile for the type of the remote vehicle;

determining that the driving behavior of the remote vehicle is abnormal based on the comparing, wherein the ego vehicle is autonomous; and

autonomously executing, by a vehicle control system of the ego vehicle, a driving maneuver to eliminate an origin of the abnormal driving behavior.

17. The computer-readable medium of claim 16 , wherein the operations further comprise:

providing a notification to a driver of the ego vehicle that the remote vehicle is driving abnormally.

18. The computer-readable medium of claim 17 , wherein retrieving the behavior profile includes querying a behavior model for the behavior profile and the operations further include:

receiving feedback from the driver that the remote vehicle is abnormal; and

updating the behavior model with the feedback from the driver to change parameters for determining that the driving behavior of the remote vehicle is normal.

19. The computer-readable medium of claim 16 , wherein determining that the behavior of the remote vehicle is abnormal includes determining that the behavior of the remote vehicle satisfies a threshold similarity to the abnormal driving behavior in the behavior profile for the type of remote vehicle.

20. The computer-readable medium of claim 16 , wherein the sensor data includes an image of the remote vehicle and wherein classifying the type of the remote vehicle includes comparing the image of the remote vehicle to a set of reference images of different types of vehicles.

Assignments (2)

Continuity (1)

References Cited (17)