Method for optimizing three-point turn of autonomous driving vehicles

Patent metadata

Field	Value
Publication number	US-11242057-B2
Application number	US-201916693054-A
Country	US
Kind code	B2
Filing date	Nov 22, 2019
Priority date	Nov 22, 2019
Publication date	Feb 8, 2022
Grant date	Feb 8, 2022

Abstract

In one embodiment, it is determined that a speed of an autonomous driving vehicle (ADV) is below a predetermined speed threshold during a current turn section of a three-point turn, where the three-point turn includes at least three turn sections. In response, detecting an obstacle within a predetermined proximity of the ADV, determining a type of obstacle. An amount of time during which the speed of the ADV remains below the predetermined speed threshold is determined. It is determined whether the amount of time is greater than a time threshold corresponding to the type of the obstacle. If the amount of time is greater than the time threshold, the current turn section is ended and a next turn section is started.

First claim

What is claimed is:

1. A computer-implemented method of performing a three-point turn of an autonomous driving vehicle, the method comprising:
determining that a speed of an autonomous driving vehicle (ADV) is below a predetermined speed threshold during a current turn section of a three-point turn, the three-point turn having at least three turn sections;
in response to detecting an obstacle within a predetermined proximity of the ADV, determining a type of the obstacle;
calculating an amount of time during which the speed of the ADV remains below the predetermined speed threshold;
determining whether the amount of time is greater than a time threshold that is determined based on the type of the obstacle; and
terminating the current turn section and starting a next turn section of the three-point turn of the ADV, in response to determining that the amount of time is greater than a time threshold.

2. The method of claim 1 , wherein the type of obstacle includes one of a pedestrian, a vehicle, and a bike.

3. The method of claim 1 , further comprising determining the time threshold based on the type of the obstacle and a motion type of the obstacle, wherein the motion type indicates whether the obstacle is a static obstacle or a dynamic obstacle.

4. The method of claim 3 , further comprising determining a percentage of completeness of the current turn section, wherein the time threshold is determined further based on the percentage of the completeness of the current turn section.

5. The method of claim 4 , further comprising calculating an obstacle factor based on the type of the obstacle, wherein the time threshold is determined further based on the obstacle factor of the obstacle.

6. The method of claim 5 , wherein the obstacle factor is calculated further based on the motion type of the obstacle.

7. The method of claim 5 , wherein the time threshold is determined by performing a lookup operation in an obstacle curve representing a relationship between an expected time and a particular percentage of completeness of the current turn section.

8. The method of claim 7 , wherein the obstacle factor curve is one of a plurality of obstacle factor curves corresponding to a plurality of different obstacle factors.

9. A non-transitory machine-readable medium having instruction stored therein, which when executed by a processor, cause the processor to perform operations of a three-point turn of an autonomous driving vehicle, the operations comprising:
determining that a speed of an autonomous driving vehicle (ADV) is below a predetermined speed threshold during a current turn section of a three-point turn, the three-point turn having at least three turn sections;
in response to detecting an obstacle within a predetermined proximity of the ADV, determining a type of the obstacle;
calculating an amount of time during which the speed of the ADV remains below the predetermined speed threshold;
determining whether the amount of time is greater than a time threshold that is determined based on the type of the obstacle; and
terminating the current turn section and starting a next turn section of the three-point turn of the ADV, in response to determining that the amount of time is greater than a time threshold.

10. The machine-readable medium of claim 9 , wherein the type of obstacle includes one of a pedestrian, a vehicle, and a bike.

11. The machine-readable medium of claim 9 , wherein the operations further comprise determining the time threshold based on the type of the obstacle and a motion type of the obstacle, wherein the motion type indicates whether the obstacle is a static obstacle or a dynamic obstacle.

12. The machine-readable medium of claim 11 , wherein the operations further comprise determining a percentage of completeness of the current turn section, wherein the time threshold is determined further based on the percentage of the completeness of the current turn section.

13. The machine-readable medium of claim 12 , wherein the operations further comprise calculating an obstacle factor based on the type of the obstacle, wherein the time threshold is determined further based on the obstacle factor of the obstacle.

14. The machine-readable medium of claim 13 , wherein the obstacle factor is calculated further based on the motion type of the obstacle.

15. The machine-readable medium of claim 13 , wherein the time threshold is determined by performing a lookup operation in an obstacle curve representing a relationship between an expected time and a particular percentage of completeness of the current turn section.

16. The machine-readable medium of claim 15 , wherein the obstacle factor curve is one of a plurality of obstacle factor curves corresponding to a plurality of different obstacle factors.

17. 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 of a three-point turn, the operations including
determining that a speed of an autonomous driving vehicle (ADV) is below a predetermined speed threshold during a current turn section of a three-point turn, the three-point turn having at least three turn sections,
in response to detecting an obstacle within a predetermined proximity of the ADV, determining a type of the obstacle,
calculating an amount of time during which the speed of the ADV remains below the predetermined speed threshold,
determining whether the amount of time is greater than a time threshold that is determined based on the type of the obstacle, and
terminating the current turn section and starting a next turn section of the three-point turn of the ADV, in response to determining that the amount of time is greater than a time threshold.

18. The system of claim 17 , wherein the type of obstacle includes one of a pedestrian, a vehicle, and a bike.

19. The system of claim 17 , wherein the operations further comprise determining the time threshold based on the type of the obstacle and a motion type of the obstacle, wherein the motion type indicates whether the obstacle is a static obstacle or a dynamic obstacle.

20. The system of claim 19 , wherein the operations further comprise determining a percentage of completeness of the current turn section, wherein the time threshold is determined further based on the percentage of the completeness of the current turn section.

Assignees

• Baidu Usa Llc
• Baidu Com Times Tech Beijing Co Ltd

Inventors

• Yu Ning
• Zhu Fan
• Xu Xin

Classifications

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• B60W2554/402

  Type · CPC title

• B60W30/095

  Predicting travel path or likelihood of collision · CPC title

• B60W60/0025

  specially adapted for specific operations · CPC title

• B60W2554/00

  Input parameters relating to objects · CPC title