Determining driving paths for autonomous driving using parallel processing

Patent metadata

Field	Value
Publication number	US-11199842-B2
Application number	US-201816019245-A
Country	US
Kind code	B2
Filing date	Jun 26, 2018
Priority date	Jun 26, 2018
Publication date	Dec 14, 2021
Grant date	Dec 14, 2021

Abstract

An autonomous driving vehicle (ADV) may determine a predicted path for a moving obstacle and speeds for different portions of the path. The ADV use multiple threads in parallel to determine the path and speeds for the different portions of the path.

First claim

What is claimed is:

1. A method of operating an autonomous driving vehicle, the method comprising:
generating multiple sets of sample points based on a first reference line representing a route from a first location to a second location, wherein the route is associated with an autonomous driving vehicle (ADV);
executing a first plurality of threads, comprising:
generating a plurality of segments simultaneously between the multiple sets of sample points to reduce an amount of time to generate the plurality of segments, wherein each thread of the first plurality of threads is configured to generate a segment of the plurality of segments; and
determining a path for the autonomous driving vehicle based on the plurality of segments, wherein the path comprises one sample point from each of the multiple sets of sample points;

controlling the autonomous driving vehicle based on the path.

2. The method of claim 1 , wherein determining the path for the autonomous driving vehicle comprises:
determining a plurality of path costs for the plurality of segments, wherein each thread of the first plurality of threads is further configured to determine a path cost of the plurality of path costs; and
determining the path further based on the plurality of path costs.

3. The method of claim 1 , further comprising:
executing a second plurality of threads configured to:
determine a plurality of speeds for a portion of the path;
determine a plurality of speed costs for the plurality of speeds, wherein each thread of the second plurality of threads is further configured to determine a speed cost of the plurality of speed costs;
determine a speed for the portion of the path; and
controlling the autonomous driving vehicle further based on the speed.

4. The method of claim 3 , wherein the plurality of speed costs are determined based on one or more of:
a plurality of velocity costs;
a plurality of acceleration costs; or
a plurality of smoothness costs.

5. The method of claim 1 , wherein generating the multiple sets of sample points comprises:
determining a distance between each of the multiple sets of sample points based on a speed of the ADV.

6. The method of claim 1 , wherein generating the plurality of segments between the multiple sets of sample points comprises:
connecting each sample point in a set of sample points to each sample point in an adjacent set of sample points.

7. The method of claim 1 , wherein generating the plurality of segments between the multiple sets of sample points comprises:
determining a plurality of polynomial functions for the plurality of segments, wherein each polynomial function represents one segment of the plurality of segments.

8. The method of claim 7 , wherein coefficients of each polynomial function are determined based on one or more of a location of the ADV, a direction of the ADV, a curvature of the ADV, or a curvature change rate of the ADV associated with a respective segment.

9. The method of claim 7 , wherein each polynomial function comprises a quintic polynomial function or a cubic polynomial function.

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:
generating multiple sets of sample points based on a first reference line representing a route from a first location to a second location, wherein the route is associated with an autonomous driving vehicle (ADV);
executing a first plurality of threads, comprising:
generating a plurality of segments simultaneously between the multiple sets of sample points to reduce an amount of time to generate the plurality of segments, wherein each thread of the first plurality of threads is configured to generate a segment of the plurality of segments; and
determining a path for the autonomous driving vehicle based on the plurality of segment, wherein the path comprises one sample point from each of the multiple sets of sample points;

controlling the autonomous driving vehicle based on the path.

11. The non-transitory machine-readable medium of claim 10 , wherein determining the path for the autonomous driving vehicle comprises:
determining a plurality of path costs for the plurality of segments, wherein each thread of the first plurality of threads is further configured to determine a path cost of the plurality of path costs; and
determining the path further based on the plurality of path costs.

12. The non-transitory machine-readable medium of claim 10 , wherein the operations further comprise:
executing a second plurality of threads configured to:
determine a plurality of speeds for a portion of the path;
determine a plurality of speed costs for the plurality of speeds, wherein each thread of the second plurality of threads is further configured to determine a speed cost of the plurality of speed costs;
determine a speed for the portion of the path; and
controlling the autonomous driving vehicle further based on the speed.

13. The non-transitory machine-readable medium of claim 12 , wherein the plurality of speed costs are determined based on one or more of:
a plurality of velocity costs;
a plurality of acceleration costs; or
a plurality of smoothness costs.

14. The non-transitory machine-readable medium of claim 10 , wherein generating the multiple sets of sample points comprises:
determining a distance between each of the multiple sets of sample points based on a speed of the ADV.

15. The non-transitory machine-readable medium of claim 10 , wherein generating the plurality of segments between the multiple sets of sample points comprises:
connecting each sample point in a set of sample points to each sample point in an adjacent set of sample points.

16. The non-transitory machine-readable medium of claim 10 , wherein generating the plurality of segments between the multiple sets of sample points comprises:
determining a plurality of polynomial functions for the plurality of segments, wherein each polynomial function represents one segment of the plurality of segments.

17. The non-transitory machine-readable medium of claim 16 , wherein coefficients of each polynomial function are determined based on one or more of a location of the ADV, a direction of the ADV, a curvature of the ADV, or a curvature change rate of the ADV associated with a respective segment.

18. The non-transitory machine-readable medium of claim 16 , wherein each polynomial function comprises a quintic polynomial function or a cubic polynomial function.

19. 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 comprising:
generating multiple sets of sample points based on a first reference line representing a route from a first location to a second location, wherein the route is associated with an autonomous driving vehicle (ADV);
executing a first plurality of threads, comprising:
generating a plurality of segments simultaneously between the multiple sets of sample points to reduce an amount of time to generate the plurality of segments, wherein each thread of the first plurality of threads is configured to generate a segment of the plurality of segments; and
determining a path for the autonomous driving vehicle based on the plurality of segment, wherein the path comprises one sample point from each of the multiple sets of sample points;

controlling the

Assignees

• Baidu Usa Llc

Inventors

• Zhang Liangliang
• Li Dong
• Hu Jiangtao
• Tao Jiaming
• Jiang Yifei
• Zhu Fan

Classifications

• B60W2420/403

  Image sensing, e.g. optical camera · CPC title

• G05D1/0278

  using satellite positioning signals, e.g. GPS · CPC title

• G05D1/027

  comprising intertial navigation means, e.g. azimuth detector (inertial navigation G01C21/16; inertial navigation combined with non-inertial navigation instruments G01C21/165) · CPC title

• G05D1/0246

  using a video camera in combination with image processing means · CPC title

• G05D1/0257

  using a radar (radar systems designed for anti-collision purposes between land vehicles or between land vehicle and fixed obstacles G01S13/931) · CPC title