On-site notification from autonomous vehicle for traffic safety

• US 10,627,819 B1
• Filed: 10/11/2018
• Issued: 04/21/2020
• Est. Priority Date: 10/11/2018
• Status: Active Grant

• Current Assignee: Pony.ai, Inc.
• Original Assignee: Pony.ai, Inc.
• Inventors: Zhou, Zixuan, Yu, Xiang, Lou, Tiancheng, Peng, Jun
• Primary Examiner(s): Lieu, Julie B
• Application Number:
  US16/158,200
• Publication Number:
  US 20200117193A1
• Time in Patent Office: 558 Days
• Field of Search: None
• CPC Class Codes: B60Q 1/507 specific to autonomous vehicles
• CPC Class Codes: B60Q 1/543 for indicating other states or conditions of the vehicle indicating taxis' state of hire or fare G07B13/045
• CPC Class Codes: B60Q 5/006 indicating risk of collision between vehicles or with pedestrians
• CPC Class Codes: G05D 1/0055 with safety arrangements
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G08G 1/005 including pedestrian guidance indicator
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

A system included and a computer-implemented method performed in an autonomous-driving vehicle are described. The system performs: detecting one or more movable traffic objects; determining one or more target movable traffic objects from the one or more detected movable traffic objects; determining a type of the one or more target movable traffic objects and an traffic object that has a right of way (ROW) in a situation involving the autonomous-driving vehicle. The system further performs: determining a manner of generating a vehicle behavior notification to the target movable traffic object based on the type of the one or more target movable traffic objects and the ROW; and causing a vehicle behavior notification of the determined manner to be generated to the one or more target movable traffic objects.

Claims

1. A system for an autonomous-driving vehicle, comprising:

one or more processors; and

memory storing instructions that, when executed by the one or more processors, cause the one or more processors to;

detect one or more movable traffic objects;

determine one or more target movable traffic objects from the one or more detected movable traffic objects;

determine a type of the one or more target movable traffic objects and an traffic object that has a right of way (ROW) in a situation involving the autonomous-driving vehicle;

determine a manner of generating a vehicle behavior notification to the target movable traffic object based on the type of the one or more target movable traffic objects and the ROW, wherein the determining the manner of generating the vehicle behavior notification comprises;

determining, when it is determined that the autonomous-driving vehicle has the ROW, whether or not it is safe to proceed;

determining, when it is determined that it is safe to proceed, a first manner of generating the vehicle behavior notification, wherein the vehicle behavior notification of the first manner indicates that the autonomous-driving vehicle will proceed;

determining, when it is determined that it is not safe to proceed, a second manner of generating the vehicle behavior notification different from the first manner; and

determining, when it is determined that the autonomous-driving vehicle does not have the ROW, a third manner of generating the vehicle behavior notification different from the first and second manners; and

cause a vehicle behavior notification of the determined manner to be generated to the one or more target movable traffic objects.

2. The system of claim 1, wherein the instructions cause the one or more processors to:

determine a vehicle route of the autonomous-driving vehicle;

determine predicted moving paths of the detected one or more movable traffic objects;

determine one or more of the detected one or more movable traffic objects that are predicted to be within a predetermined distance from the autonomous-driving vehicle as one or more candidate movable traffic objects, based on the vehicle route and the predicted moving paths of the one or more movable traffic objects; and

determine the one or more target movable traffic objects from the one or more candidate movable traffic objects.

3. The system of claim 1, wherein

the vehicle behavior notification of the first manner indicates that the autonomous-driving vehicle will proceed,

the vehicle behavior notification of the second manner indicates that the autonomous-driving vehicle will operate to avoid unsafety, and

the vehicle behavior notification of the third manner indicates that the autonomous-driving vehicle will yield.

4. The system of claim 1, wherein

each of the one or more target movable traffic objects is one of a pedestrian, a person on a human-powered vehicle, and a motor vehicle driven by a human driver, and

the vehicle behavior notification of at least one of the first, second, and third manners corresponding to the pedestrian and the person on the human-powered vehicle is different from the vehicle behavior notification of the at least one of the first, second, and third manners corresponding to the motor vehicle driven by the human driver.

5. The system of claim 4, wherein

the vehicle behavior notification of at least one of the first, second, and third manners corresponding to the pedestrian and the person on the human-powered vehicle includes a first light signal, and

the vehicle behavior notification of the at least one of the first, second, and third manners corresponding to the motor vehicle driven by the human driver includes a second light signal different from the first light signal.

6. The system of claim 1, wherein at least one of the one or more target movable traffic objects is another autonomous-driving vehicle, and when the autonomous-driving vehicle is at an intersection, the instructions cause the one or more processors to:

generate a signal indicating a random number;

determine priority of the random number with respect to one or more other random numbers indicated by signals from the at least one of the one or more target movable traffic objects according to a predetermined algorithm; and

determine the traffic object that has the ROW in accordance with the determined priority.

7. The system of claim 6, wherein the generated signal indicating the random number comprises a wireless signal transmitted from the autonomous-driving vehicle.

8. The system of claim 1, wherein the instructions cause the one or more processors to:

determine whether or not at least one of the one or more target movable traffic objects is an emergency vehicle based on siren signals generated thereby; and

determine that the emergency vehicle has the ROW.

9. The system of claim 1, wherein the instructions cause the one or more processors to determine the manner of generating the vehicle behavior notification also based on a distance from the autonomous-driving vehicle to the one or more target movable traffic objects.

10. A computer-implemented method performed in an autonomous-driving vehicle comprising:

detecting one or more movable traffic objects;

determining one or more target movable traffic objects from the one or more detected movable traffic objects;

determining a type of the one or more target movable traffic objects and an traffic object that has a right of way (ROW) in a situation involving the autonomous-driving vehicle, wherein at least one of the one or more target movable traffic objects is another autonomous-driving vehicle, and the determining the traffic object that has the ROW comprises;

when the autonomous-driving vehicle is at an intersection, generating a signal indicating a random number;

determining priority of the random number with respect to one or more other random numbers indicated by signals from the at least one of the one or more target movable traffic objects according to a predetermined algorithm; and

determining the traffic object that has the ROW in accordance with the determined priority;

determining a manner of generating a vehicle behavior notification to the target movable traffic object based on the type of the one or more target movable traffic objects and the ROW; and

causing a vehicle behavior notification of the determined manner to be generated to the one or more target movable traffic objects.

11. The computer-implemented method of claim 10, wherein the determining the one or more target movable traffic objects comprises:

determining a vehicle route of the autonomous-driving vehicle;

determining predicted moving paths of the detected one or more movable traffic objects;

determining one or more of the detected one or more movable traffic objects that are predicted to be within a predetermined distance from the autonomous-driving vehicle as one or more candidate movable traffic objects, based on the vehicle route and the predicted moving paths of the one or more movable traffic objects; and

determining the one or more target movable traffic objects from the one or more candidate movable traffic objects.

12. The computer-implemented method of claim 10, wherein the determining the manner of generating the vehicle behavior notification comprises:

when it is determined that the autonomous-driving vehicle has the ROW, determining whether or not it is safe to proceed;

when it is determined that it is safe to proceed, determining a first manner of generation the vehicle behavior notification;

when it is determined that it is not safe to proceed, determining a second manner of generating the vehicle behavior notification different from the first manner; and

when it is determined that the autonomous-driving vehicle does not have the ROW, determining a third manner of generating the vehicle behavior notification different from the first and second manners.

13. The computer-implemented method of claim 12, wherein

the vehicle behavior notification of the first manner indicates that the autonomous-driving vehicle will proceed,

the vehicle behavior notification of the second manner indicates that the autonomous-driving vehicle will operate to avoid unsafety, and

the vehicle behavior notification of the third manner indicates that the autonomous-driving vehicle will yield.

14. The computer-implemented method of claim 12, wherein

each of the one or more target movable traffic objects is one of a pedestrian, a person on a human-powered vehicle, and a motor vehicle driven by a human driver, and

the vehicle behavior notification of at least one of the first, second, and third manners corresponding to the pedestrian and the person on the human-powered vehicle is different from the vehicle behavior notification of the at least one of the first, second, and third manners corresponding to the motor vehicle driven by the human driver.

15. The computer-implemented method of claim 14 wherein

the vehicle behavior notification of at least one of the first, second, and third manners corresponding to the pedestrian and the person on the human-powered vehicle includes a first light signal, and

the vehicle behavior notification of the at least one of the first, second, and third manners corresponding to the motor vehicle driven by the human driver includes a second light signal different from the first light signal.

16. The computer-implemented method of claim 10, wherein the generated signal indicating the random number comprises a wireless signal transmitted from the autonomous-driving vehicle.

17. The computer-implemented method of claim 10, wherein the determining the traffic object that has the ROW comprises:

determining whether or not at least one of the one or more target movable traffic objects is an emergency vehicle based on siren signals generated thereby; and

determining that the emergency vehicle has the ROW.

18. The computer-implemented method of claim 10, wherein the manner of generating the vehicle behavior notification is determined also based on a distance from the autonomous-driving vehicle to the one or more target movable traffic objects.

19. A system for an autonomous-driving vehicle, comprising:

one or more processors; and

memory storing instructions that, when executed by the one or more processors, cause the one or more processors to;

detect one or more movable traffic objects;

determine one or more target movable traffic objects from the one or more detected movable traffic objects;

determine a type of the one or more target movable traffic objects and an traffic object that has a right of way (ROW) in a situation involving the autonomous-driving vehicle, wherein at least one of the one or more target movable traffic objects is another autonomous-driving vehicle, and the determining the traffic object that has the ROW comprises;

when the autonomous-driving vehicle is at an intersection, generating a signal indicating a random number;

determining priority of the random number with respect to one or more other random numbers indicated by signals from the at least one of the one or more target movable traffic objects according to a predetermined algorithm; and

determining the traffic object that has the ROW in accordance with the determined priority;

determine a manner of generating a vehicle behavior notification to the target movable traffic object based on the type of the one or more target movable traffic objects and the ROW; and

cause a vehicle behavior notification of the determined manner to be generated to the one or more target movable traffic objects.