Group and combine obstacles for autonomous driving vehicles

Patent metadata

Field	Value
Publication number	US-11560159-B2
Application number	US-202016830090-A
Country	US
Kind code	B2
Filing date	Mar 25, 2020
Priority date	Mar 25, 2020
Publication date	Jan 24, 2023
Grant date	Jan 24, 2023

Abstract

In one embodiment, a plurality of obstacles is sensed in an environment of an automated driving vehicle (ADV). One or more representations are formed to represent corresponding groupings of the plurality of obstacles. A vehicle route is determined in view of the one or more representations, rather than each and every one of the obstacles individually.

First claim

What is claimed is:

1. A method for operating an autonomous driving vehicle, the method comprising:
sensing a plurality of obstacles in an environment of an automated driving vehicle (ADV);
forming a single representation of the plurality of obstacles based on a set of one or more rules in view of relative relationships amongst the obstacles;
predicting a plurality of potential paths of one of the plurality of obstacles;
discarding a first of the plurality of potential paths, in response to a second of the plurality of potential paths being between the ADV and the first of the plurality of potential paths;
determining a vehicle route in view of the single representation of the plurality of obstacles and the plurality of potential paths which does not include the first of the plurality of potential paths; and
generating one or more control commands to effect movement of the ADV along the vehicle route.

2. The method of claim 1 , wherein the set of one or more rules includes whether the plurality of obstacles are vehicles that are driving along a same driving lane within a threshold distance to each other.

3. The method of claim 1 , wherein the set of one or more rules includes whether the plurality of obstacles are pedestrians within a threshold distance to each other.

4. The method of claim 3 , further comprising generating a single virtual wall for the single representation of the pedestrians.

5. The method of claim 1 , wherein the set of one or more rules includes distance between each of the plurality of obstacles.

6. The method of claim 1 , wherein the set of one or more rules includes at least one of a) distance between each of the plurality of obstacles, or b) commonality of movement direction of the plurality of obstacles.

7. The method of claim 1 , wherein the set of one or more rules includes at least one of a) distance between each of the plurality of obstacles, b) commonality of movement direction of the plurality of obstacles, or c) commonality of type of the obstacle.

8. The method of claim 1 , further comprising:
sensing a different plurality of obstacles in the environment of the ADV; and
forming a second representation of the different plurality of obstacles; wherein
the second representation of the different plurality of obstacles is also used to determine the vehicle route.

9. The method of claim 1 , wherein determining a vehicle route in view of the single representation of the plurality of obstacles includes:
determining a driving decision, including at least one of a yield decision, an overtake decision, a pass decision, and a stop decision, based on the single representation of the plurality of obstacles; and
optimizing the vehicle route based on the single representation of the plurality of obstacles and the driving decision.

10. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:
sensing a plurality of obstacles in an environment of an automated driving vehicle (ADV);
forming a single representation of the plurality of obstacles based on a set of one or more rules in view of relative relationships amongst the obstacles;
predicting a plurality of potential paths of one of the plurality of obstacles;
discarding a first of the plurality of potential paths, in response to a second of the plurality of potential paths being between the ADV and the first of the plurality of potential paths;
determining a vehicle route in view of the single representation of the plurality of obstacles and the plurality of potential paths which does not include the first of the plurality of potential paths; and
generating one or more control commands to effect movement of the ADV along the vehicle route.

11. The non-transitory machine-readable medium of claim 10 , wherein the set of one or more rules includes whether the plurality of obstacles are vehicles that are driving along a same driving lane within a threshold distance to each other.

12. The non-transitory machine-readable medium of claim 10 , wherein the set of one or more rules includes whether the plurality of obstacles are pedestrians within a threshold distance to each other.

13. The non-transitory machine-readable medium of claim 12 , wherein the operations further comprise generating a single virtual wall for the single representation of the pedestrians.

14. The non-transitory machine-readable medium of claim 10 , wherein the set of one or more rules includes distance between each of the plurality of obstacles.

15. The non-transitory machine-readable medium of claim 10 , wherein the set of one or more rules includes at least one of a) distance between each of the plurality of obstacles, or b) commonality of movement direction of the plurality of obstacles.

16. A data processing system, comprising:
a processor; and
a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including;
sensing a plurality of obstacles in an environment of an automated driving vehicle (ADV);
forming a single representation of the plurality of obstacles based on a set of one or more rules in view of relative relationships amongst the obstacles;
predicting a plurality of potential paths of one of the plurality of obstacles;
discarding a first of the plurality of potential paths, in response to a second of the plurality of potential paths being between the ADV and the first of the plurality of potential paths;
determining a vehicle route in view of the single representation of the plurality of obstacles and the plurality of potential paths and not the first of the plurality of potential paths; and
generating one or more control commands to effect movement of the ADV along the vehicle route.

17. The data processing system of claim 16 , wherein the set of one or more rules includes whether the plurality of obstacles are vehicles that are driving along a same driving lane within a threshold distance to each other.

18. The data processing system of claim 16 , wherein the set of one or more rules includes whether the plurality of obstacles are pedestrians within a threshold distance to each other.

19. The data processing system of claim 18 , wherein the operations further comprise generating a single virtual wall for the single representation of the pedestrians.

20. The data processing system of claim 16 , wherein the set of one or more rules includes distance between each of the plurality of obstacles.

Assignees

• Baidu Usa Llc

Inventors

• Tao Jiaming
• Luo Qi
• Zhou Jinyun
• Xu Kecheng
• Wang Yu
• Jiang Shu
• Hu Jiangtao
• Miao Jinghao

Classifications

• 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

• B60W2554/801

  Lateral distance · CPC title

• G05D1/0088

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

• B60W60/0027 Primary

  using trajectory prediction for other traffic participants · CPC title

• B60W30/09

  Taking automatic action to avoid collision, e.g. braking and steering · CPC title