Safety guaranteed control when planning with uncertainty

Patent metadata

Field	Value
Publication number	US-12116010-B2
Application number	US-202117645857-A
Country	US
Kind code	B2
Filing date	Dec 23, 2021
Priority date	Dec 23, 2021
Publication date	Oct 15, 2024
Grant date	Oct 15, 2024

Abstract

According to some embodiments, described herein is a method and a system for guaranteeing safety at a control level of an ADV when at least a portion of a planned path generated by a planning module of the ADV is uncertain due to traffics and/or road condition changes. The planning module, when generating a path, also generate a confidence level of each segment of the path based on one or more of perception data, map information, or traffic rules. The confidence levels are decreasing further away from the ADV. When the control module of the ADV obtains the path and the associated confidence levels, the control module issue control commands to track only one or two segments whose confidence levels exceeds a threshold hold, and issue default control commands for the rest of the path.

First claim

What is claimed is:

1. A computer-implemented method for operating an autonomous driving vehicle (ADV), comprising:
generating, by the ADV, a path that includes a plurality of segments, each segment having a different confidence level, wherein the confidence level of each segment of the plurality of segments of the path is generated using a set of rules based on perception data, map information, and traffic rules;
generating, by the ADV, a first sequence of sets of control commands to drive the ADV to track one or more segments of the plurality segments, each of the one or more segments with a confidence level exceeding a predetermined threshold;
adjusting, by the ADV, each segment of the remaining segments of the path, including modifying one or more parameters of the segment; and
generating, by the ADV, a second sequence of sets of control commands to drive the ADV to track each adjusted segment of the path.

2. The computer-implemented method of claim 1 , wherein the one or more parameters that are modified include one or more of a speed, heading, or acceleration of the ADV at each point on that adjusted segment.

3. The computer-implemented method of claim 2 , wherein each of the one or more parameters is modified to be a predetermined constant value.

4. The computer-implemented method of claim 1 , wherein the confidence level of each segment of the plurality of segments of the path is generated using a trained neural network model.

5. The computer-implemented method of claim 1 , wherein the neural network model is to generate a confidence level for only a first segment of the path, and wherein a planning module provides a default confidence level for the rest of the path.

6. The computer-implemented method of claim 1 , wherein the path and a confidence level for each segment of the path is passed from a planning module of the ADV to a control module of the ADV.

7. A non-transitory machine-readable medium having instructions stored therein for operating an autonomous driving vehicle (ADV), wherein the instructions, when executed by a processor, cause the processor to perform operations, the operations comprising:
generating, by the ADV, a path that includes a plurality of segments, each segment having a different confidence level, wherein the confidence level of each segment of the plurality of segments of the path is generated using a set of rules based on perception data, map information, and traffic rules;
generating, by the ADV, a first sequence of sets of control commands to drive the ADV to track one or more segments of the plurality segments, each of the one or more segments with a confidence level exceeding a predetermined threshold;
adjusting, by the ADV, each segment of the remaining segments of the path, including modifying one or more parameters of the segment; and
generating, by the ADV, a second sequence of sets of control commands to drive the ADV to track each adjusted segment of the path.

8. The non-transitory machine-readable medium of claim 7 , wherein the one or more parameters that are modified include one or more of a speed, heading, or acceleration of the ADV at each point on that adjusted segment.

9. The non-transitory machine-readable medium of claim 8 , wherein each of the one or more parameters is modified to be a predetermined constant value.

10. The non-transitory machine-readable medium of claim 7 , wherein the confidence level of each segment of the plurality of segments of the path is generated using a trained neural network model.

11. The non-transitory machine-readable medium of claim 7 , wherein the neural network model is to generate a confidence level for only a first segment of the path, and wherein a planning module provides a default confidence level for the rest of the path.

12. The non-transitory machine-readable medium of claim 7 , wherein the path and a confidence level for each segment of the path is passed from a planning module of the ADV to a control module of the ADV.

13. A data processing system, comprising:
a processor; and
a memory coupled to the processor to store instructions for operating an autonomous driving vehicle (ADV), which when executed by the processor, cause the processor to perform operations, the operations comprising:
generating a path that includes a plurality of segments, each segment having a different confidence level, wherein the confidence level of each segment of the plurality of segments of the path is generated using a set of rules based on perception data, map information, and traffic rules,
generating a first sequence of sets of control commands to drive the ADV to track one or more segments of the plurality segments, each of the one or more segments with a confidence level exceeding a predetermined threshold,
adjusting each segment of the remaining segments of the path, including modifying one or more parameters of the segment, and
generating a second sequence of sets of control commands to drive the ADV to track each adjusted segment of the path.

14. The data processing system of claim 13 , wherein the one or more parameters that are modified include one or more of a speed, heading, or acceleration of the ADV at each point on that adjusted segment.

15. The data processing system of claim 14 , wherein each of the one or more parameters is modified to be a predetermined constant value.

16. The data processing system of claim 13 , wherein the confidence level of each segment of the plurality of segments of the path is generated using a trained neural network model.

17. The data processing system of claim 13 , wherein the neural network model is to generate a confidence level for only a first segment of the path, and wherein a planning module provides a default confidence level for the rest of the path.

Assignees

• Baidu Usa Llc

Inventors

• Jiang Shu
• Lin Weiman
• Cao Yu
• Hu Jiangtao
• Miao Jinghao

Classifications

• G06N3/02

  Neural networks · CPC title

• B60W40/02

  related to ambient conditions · CPC title

• B60W30/143

  Speed control (B60W30/16 takes precedence) · CPC title

• 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

• B60W2555/60

  Traffic rules, e.g. speed limits or right of way · CPC title