Planning under prediction with confidence region for an autonomous driving vehicle

Patent metadata

Field	Value
Publication number	US-12134402-B2
Application number	US-202117564933-A
Country	US
Kind code	B2
Filing date	Dec 29, 2021
Priority date	Dec 29, 2021
Publication date	Nov 5, 2024
Grant date	Nov 5, 2024

Abstract

An obstacle is detected based on sensor data obtained from a plurality of sensors of the ADV. A distribution of a plurality of positions of the obstacle at a point of time may be predicted. A range of positions of the plurality of positions of the obstacle may be determined based on a confidence level of the range. A modified shape with a modified length of the obstacle may be determined based on the range of positions of the obstacle. A trajectory of the ADV based on the modified shape with the modified length of the obstacle may be planned. The ADV may be controlled to drive according to the planned trajectory to drive safely to avoid a collision with the obstacle.

First claim

What is claimed is:

1. A computer-implemented method for operating an autonomous driving vehicle (ADV), the method comprising:
detecting an obstacle based on sensor data obtained from a plurality of sensors of the ADV;
predicting a distribution of a plurality of positions of the obstacle at a point of time;
determining a range of positions of the plurality of positions of the obstacle based on a confidence level of the range;
determining a modified shape with a modified length of the obstacle based on the range of positions of the obstacle;
planning a trajectory of the ADV based on the modified shape with the modified length of the obstacle; and
controlling the ADV to drive according to the planned trajectory to drive safely to avoid a collision with the obstacle.

2. The method of claim 1 , wherein the modified shape with the modified length of the obstacle includes an elongated shape longer than an actual length of the obstacle.

3. The method of claim 1 , wherein the determining a predicted range of positions of the plurality of positions of the obstacle includes determining the predicted range of positions of the plurality of positions of the obstacle according to a history of velocity and acceleration of the obstacle.

4. The method of claim 1 , wherein the confidence level of the range corresponds to a probability of the obstacle will be within the range.

5. The method of claim 1 , wherein the predicting a distribution of a plurality of positions of the obstacle in a point of time further includes predicting multiple distributions of a plurality of positions of the obstacle at multiple points of time, each distribution of the plurality of positions of the obstacle corresponding to a distribution of a plurality of positions of the obstacle at one point of time.

6. The method of claim 1 , wherein the obstacle is a leading obstacle, and wherein the planning a trajectory of the ADV based on the modified shape with the modified length of the obstacle including planning to stop the ADV before a lower bound of the modified shape with the modified length of the obstacle.

7. The method of claim 1 , wherein the obstacle is a leading obstacle, and wherein the planning a trajectory of the ADV based on the modified shape with the modified length of the obstacle including planning to pass the obstacle on a side based on an upper bound of the modified shape with the modified length of the obstacle.

8. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations of operating an autonomous driving vehicle (ADV), the operations comprising:
detecting an obstacle based on sensor data obtained from a plurality of sensors of the ADV;
predicting a distribution of a plurality of positions of the obstacle at a point of time;
determining a range of positions of the plurality of positions of the obstacle based on a confidence level of the range;
determining a modified shape with a modified length of the obstacle based on the range of positions of the obstacle;
planning a trajectory of the ADV based on the modified shape with the modified length of the obstacle; and
controlling the ADV to drive according to the planned trajectory to drive safely to avoid a collision with the obstacle.

9. The non-transitory machine-readable medium of claim 8 , wherein the modified shape with the modified length of the obstacle includes an elongated shape longer than an actual length of the obstacle.

10. The non-transitory machine-readable medium of claim 8 , wherein the operations further comprise determining the predicted range of positions of the plurality of positions of the obstacle according to a history of velocity and acceleration of the obstacle.

11. The non-transitory machine-readable medium of claim 8 , wherein the confidence level of the range corresponds to a probability of the obstacle will be within the range.

12. The non-transitory machine-readable medium of claim 8 , wherein the operations further comprise predicting multiple distributions of a plurality of positions of the obstacle at multiple points of time, each distribution of the plurality of positions of the obstacle corresponding to a distribution of a plurality of positions of the obstacle at one point of time.

13. The non-transitory machine-readable medium of claim 8 , wherein the obstacle is a leading obstacle, and wherein the operations further comprise planning to stop the ADV before a lower bound of the modified shape with the modified length of the obstacle.

14. The non-transitory machine-readable medium of claim 8 , wherein the obstacle is a leading obstacle, and wherein the operations further comprise planning to pass the obstacle on a side based on an upper bound of the modified shape with the modified length of the obstacle.

15. 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 operating an autonomous driving vehicle (ADV), the operations including
detecting an obstacle based on sensor data obtained from a plurality of sensors of the ADV;
predicting a distribution of a plurality of positions of the obstacle at a point of time;
determining a range of positions of the plurality of positions of the obstacle based on a confidence level of the range;
determining a modified shape with a modified length of the obstacle based on the range of positions of the obstacle;
planning a trajectory of the ADV based on the modified shape with the modified length of the obstacle; and
controlling the ADV to drive according to the planned trajectory to drive safely to avoid a collision with the obstacle.

16. The data processing system of claim 15 , wherein the modified shape with the modified length of the obstacle includes an elongated shape longer than an actual length of the obstacle.

17. The data processing system of claim 15 , wherein the operations further comprise determining the predicted range of positions of the plurality of positions of the obstacle according to a history of velocity and acceleration of the obstacle.

18. The data processing system of claim 15 , wherein the confidence level of the range corresponds to a probability of the obstacle will be within the range.

19. The data processing system of claim 15 , wherein the operations further comprise predicting multiple distributions of a plurality of positions of the obstacle at multiple points of time, each distribution of the plurality of positions of the obstacle corresponding to a distribution of a plurality of positions of the obstacle at one point of time.

20. The data processing system of claim 15 , wherein the obstacle is a leading obstacle, and wherein the operations further comprise planning to stop the ADV before a lower bound of the modified shape with the modified length of the obstacle.

21. The data processing system of claim 15 , wherein the obstacle is a leading obstacle, and wherein the operations further comprise planning to pass the obstacle on a side based on an upper bound of the modified shape with the modified length of the obstacle.

Assignees

• Baidu Usa Llc

Inventors

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

Classifications

• B60W50/0097

  Predicting future conditions · CPC title

• B60W40/04

  Traffic conditions · CPC title

• B60W30/0956

  the prediction being responsive to traffic or environmental parameters · CPC title

• B60W30/09

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