Fast trajectory planning via maneuver pattern selection

Patent metadata

Field	Value
Publication number	US-10678248-B2
Application number	US-201815897368-A
Country	US
Kind code	B2
Filing date	Feb 15, 2018
Priority date	Feb 15, 2018
Publication date	Jun 9, 2020
Grant date	Jun 9, 2020

Abstract

Technical solutions are described for maneuvering a vehicle autonomously is described. An example method includes receiving, by a controller, a command to navigate the vehicle, the command based on a global route calculation. The method further includes ranking, by the controller, maneuver patterns from a list of maneuver patterns to generate a ranked list of maneuver patterns. The method further includes selecting a maneuver pattern from the ranked list, and in response to a comfort score assigned to the selected maneuver pattern being above a predetermined threshold, executing the maneuver pattern.

First claim

What is claimed is:

1. A method for maneuvering a vehicle autonomously, the method comprising:
receiving, by a controller, a command to navigate the vehicle, the command based on a global route calculation;
ranking, by the controller, maneuver patterns from a list of maneuver patterns to generate a ranked list of maneuver patterns;
selecting a maneuver pattern from the ranked list, wherein the selected maneuver pattern is the highest untried maneuver pattern from the ranked list;
in response to a comfort score assigned to the selected maneuver pattern being above a predetermined threshold, executing the maneuver pattern; and
adjusting the predetermined threshold responsive to none of the maneuver patterns from the ranked list meeting the predetermined threshold.

2. The method of claim 1 , wherein a maneuver pattern comprises a plurality of trajectories.

3. The method of claim 2 , wherein selecting the maneuver pattern comprises:
determining the comfort score of a first trajectory from the maneuver pattern based on attribute values assigned to the trajectory and local parameters.

4. The method of claim 3 , wherein the local parameters comprise parameters computed for obstacles in a predetermined vicinity surrounding the vehicle.

5. The method of claim 3 , the selection of the maneuver further comprises performing a local optimization within the plurality of trajectories to identify a trajectory that satisfies the predetermined threshold for the comfort score.

6. The method of claim 1 , wherein the global route calculation is performed based on a source and destination provided to the vehicle for autonomous navigation.

7. A trajectory planning system comprising:
a memory; and
a processor coupled with the memory, the processor configured to determine a trajectory for moving a vehicle autonomously, the determination comprising:
receiving, by a controller, a command to navigate the vehicle, the command based on a global route calculation;
ranking, by the controller, maneuver patterns from a list of maneuver patterns to generate a ranked list of maneuver patterns, wherein the list comprises and end-of-list NULL entry, which is a specific entry at an end of the list to identify the end of the list;
selecting a maneuver pattern from the ranked list, wherein the selected maneuver pattern is the highest untried maneuver pattern from the ranked list; and
in response to a comfort score assigned to the selected maneuver pattern being above a predetermined threshold, executing the maneuver pattern.

8. The system of claim 7 , wherein a maneuver pattern comprises a plurality of trajectories.

9. The system of claim 8 , wherein selecting the maneuver pattern comprises determining the comfort score of a first trajectory from the maneuver pattern based on attribute values assigned to the trajectory and local parameters.

10. The system of claim 9 , wherein the local parameters comprise parameters computed for obstacles in a predetermined vicinity surrounding the vehicle.

11. The system of claim 9 , the selection of the maneuver further comprises performing a local optimization within the plurality of trajectories to identify a trajectory that satisfies the predetermined threshold for the comfort score.

12. The system of claim 7 , wherein the determining further comprises, adjusting the predetermined threshold if none of the maneuver patterns from the ranked list meet the predetermined threshold.

13. A vehicle controller for determining a trajectory for moving a vehicle autonomously, the determination comprising:
receiving, by a controller, a command to navigate the vehicle, the command based on a global route calculation;
ranking, by the controller, maneuver patterns from a list of maneuver patterns to generate a ranked list of maneuver patterns, wherein the list comprises an end-of-list NULL entry, which is a specific entry at an end of the list to identify the end of the list;
selecting a maneuver pattern from the ranked list;
in response to a comfort score assigned to the selected maneuver pattern being above a predetermined threshold, executing the maneuver pattern;
subsequent to executing the maneuver pattern, determining whether the maneuver pattern was successful;
selecting and exrcuting a next highest maneuver pattern from the ranked list until detecting the end-of-list NULL entry; and
responsive to detecting the end-of-list NULL entry, lowering the predetermined threshold.

14. The vehicle controller of claim 13 , wherein a maneuver pattern comprises a plurality of trajectories.

15. The vehicle controller of claim 14 , wherein selecting the maneuver pattern comprises determining the comfort score of a first trajectory from the maneuver pattern based on attribute values assigned to the trajectory and local parameters, wherein the local parameters comprise parameters computed for obstacles in a predetermined vicinity surrounding the vehicle.

16. The vehicle controller of claim 15 , the selection of the maneuver further comprises performing a local optimization within the plurality of trajectories to identify a trajectory that satisfies the predetermined threshold for the comfort score.

17. The vehicle controller of claim 13 , wherein the selected maneuver pattern is the highest untried maneuver pattern from the ranked list.

18. The vehicle controller of claim 13 , wherein the determining further comprises, adjusting the predetermined threshold if none of the maneuver patterns from the ranked list meet the predetermined threshold.

Assignees

• Gm Global Tech Operations Llc

Inventors

• Ford Jordan
• Jafari Tafti Sayyed Rouhollah
• Mehdi Syed B

Classifications

• G05D1/0088

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

• G05D1/0212 Primary

  with means for defining a desired trajectory (involving a plurality of land vehicles G05D1/0287) · CPC title

• B60W60/0011

  involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles · CPC title

• B60W60/001

  Planning or execution of driving tasks · CPC title

• B60W30/095 Primary

  Predicting travel path or likelihood of collision · CPC title