Ranking agents near autonomous vehicles by mutual importance

Patent metadata

Field	Value
Publication number	US-11977382-B2
Application number	US-202318197561-A
Country	US
Kind code	B2
Filing date	May 15, 2023
Priority date	Aug 7, 2020
Publication date	May 7, 2024
Grant date	May 7, 2024

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying high-priority agents in the vicinity of a vehicle. The high-priority agents can be identified based on a set of mutual importance scores in which each mutual importance score indicates an estimated mutual relevance between the vehicle and a different agent from a set of agents on planning decisions of the other. The mutual importance scores can be calculated based on importance scores assessed from the perspectives of both the vehicle and the agents.

First claim

What is claimed is:

1. A method performed by one or more data processing apparatus, the method comprising:
identifying a first agent in a vicinity of a vehicle;
determining a first importance score that indicates an importance of the first agent with respect to planning movements for the vehicle;
determining a second importance score that indicates an importance of the vehicle or a second agent with respect to planning movements for the first agent;
planning a movement for the vehicle based on the first importance score and the second importance score; and
controlling the vehicle using information about the movement that was planned based on the first importance score and the second importance score.

2. The method of claim 1 , wherein the vehicle is a fully autonomous or semi-autonomous vehicle, and wherein the first agent is another vehicle, a pedestrian, or a cyclist in the vicinity of the vehicle.

3. The method of claim 1 , wherein the second importance score indicates an importance of the vehicle with respect to planning movements for the first agent.

4. The method of claim 1 , wherein the second importance score indicates an importance of the second agent with respect to planning movements for the first agent.

5. The method of claim 1 , further comprising determining, based on the first importance score and the second importance score, a mutual importance score that indicates a mutual importance of the vehicle and the first agent with respect to planning movements of each other, wherein the movement is planned using the mutual importance score.

6. The method of claim 1 , further comprising, for each of a plurality of reference agents in the vicinity of the vehicle:
determining a first reference importance score that indicates an importance of the reference agent with respect to planning movements for the vehicle; and
determining a second reference importance score that indicates an importance of the vehicle or another agent with respect to planning movements for the reference agent.

7. The method of claim 1 , further comprising planning the movement for the vehicle using the respective first reference importance scores and the respective second reference importance scores for the plurality of reference agents in the vicinity of the vehicle.

8. The method of claim 1 , further comprising classifying the first agent into one of a plurality of priority classes based on the first importance score and the second importance score.

9. A system, comprising:
a data processing apparatus; and
a memory in communication with the data processing apparatus and storing instructions that, when executed, cause the data processing apparatus to perform operations comprising:
identifying a first agent in a vicinity of a vehicle;
determining a first importance score that indicates an importance of the first agent with respect to planning movements for the vehicle;
determining a second importance score that indicates an importance of the vehicle or a second agent with respect to planning movements for the first agent;
planning a movement for the vehicle based on the first importance score and the second importance score; and
controlling the vehicle using information about the movement that was planned based on the first importance score and the second importance score.

10. The system of claim 9 , wherein the vehicle is a fully autonomous or semi-autonomous vehicle, and wherein the first agent is another vehicle, a pedestrian, or a cyclist in the vicinity of the vehicle.

11. The system of claim 9 , wherein the second importance score indicates an importance of the vehicle with respect to planning movements for the first agent.

12. The system of claim 9 , wherein the second importance score indicates an importance of the second agent with respect to planning movements for the first agent.

13. The system of claim 9 , wherein the operations further comprise determining, based on the first importance score and the second importance score, a mutual importance score that indicates a mutual importance of the vehicle and the first agent with respect to planning movements of each other, wherein the movement is planned using the mutual importance score.

14. The system of claim 9 , wherein the operations further comprise, for each of a plurality of reference agents in the vicinity of the vehicle:
determining a first reference importance score that indicates an importance of the reference agent with respect to planning movements for the vehicle; and
determining a second reference importance score that indicates an importance of the vehicle or another agent with respect to planning movements for the reference agent.

15. The system of claim 9 , wherein the operations further comprise planning the movement for the vehicle using the respective first reference importance scores and the respective second reference importance scores for the plurality of reference agents in the vicinity of the vehicle.

16. The system of claim 9 , wherein the operations further comprise classifying the first agent into one of a plurality of priority classes based on the first importance score and the second importance score.

17. One or more non-transitory computer-readable storage media having instructions stored thereon that, when executed by data processing apparatus, cause the data processing apparatus to perform operations comprising:
identifying a first agent in a vicinity of a vehicle;
determining a first importance score that indicates an importance of the first agent with respect to planning movements for the vehicle;
determining a second importance score that indicates an importance of the vehicle or a second agent with respect to planning movements for the first agent;
planning a movement for the vehicle based on the first importance score and the second importance score; and
controlling the vehicle using information about the movement that was planned based on the first importance score and the second importance score.

18. The one or more non-transitory computer-readable storage media of claim 17 , wherein the vehicle is a fully autonomous or semi-autonomous vehicle, and wherein the first agent is another vehicle, a pedestrian, or a cyclist in the vicinity of the vehicle.

19. The one or more non-transitory computer-readable storage media of claim 17 , wherein the second importance score indicates an importance of the vehicle with respect to planning movements for the first agent.

20. The one or more non-transitory computer-readable storage media of claim 17 , wherein the second importance score indicates an importance of the second agent with respect to planning movements for the first agent.

Assignees

• Waymo Llc

Inventors

• Ding Kai
• Wang Minfa
• Chen Haoyu
• Refaat Khaled
• Ross Stephane
• Chai Wei

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G05D1/0088 Primary

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title

• G05D1/0214

  in accordance with safety or protection criteria, e.g. avoiding hazardous areas (monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13) · CPC title

• G06N3/08

  Learning methods · CPC title