Method for enhancing in-path obstacle detection with safety redundancy autonomous system

Patent metadata

Field	Value
Publication number	US-11225228-B2
Application number	US-202016815734-A
Country	US
Kind code	B2
Filing date	Mar 11, 2020
Priority date	Mar 11, 2020
Publication date	Jan 18, 2022
Grant date	Jan 18, 2022

Abstract

In one embodiment, a method for performing an obstacle detection for an ADV includes detecting an obstacle by a primary ADS and a secondary ADS using an obstacle detection algorithm based on sensor data provided by sensors on the ADV. In response to detecting the obstacle, a first controlled stop distance and a second controlled stop distance are calculated by the primary ADS and secondary ADS respectively based on a speed and a deceleration capability of the ADV. The first and second controlled stop distances between the primary ADS and secondary ADS are exchanged to determine a third controlled stop distance which is the maximum of the two. In response to determining that the ADV reaches within the third controlled distance between the ADV and the obstacle, a controlled stop operation is activated by the primary ADS to decelerate the ADV based on the third controlled stop distance.

First claim

What is claimed is:

1. A computer-implemented method for performing an obstacle detection for an autonomous driving vehicle (ADV), the method comprising:
detecting an obstacle by a primary autonomous driving system (ADS) and a secondary ADS using an obstacle detection algorithm based on sensor data provided by a plurality of sensors on the ADV;
calculating a first controlled stop distance and a second controlled stop distance by the primary ADS and secondary ADS respectively based on a speed and a deceleration capability of the ADV in response to detecting the obstacle;
exchanging the first and second controlled stop distances between the primary ADS and secondary ADS to determine a third controlled stop distance; and
activating a controlled stop operation by the primary ADS to decelerate the ADV based on the third controlled stop distance, in response to determining that the ADV reaches within the third controlled distance between the ADV and the obstacle.

2. The method of claim 1 , further comprising:
calculating a first emergency stop distance by the primary ADS during the controlled stop operation; and
activating an emergency stop operation when the ADV moves within the first emergency stop distance from the obstacle.

3. The method of claim 2 , further comprising:
periodically measuring by the primary ADS a current distance between the ADV and the obstacle while the ADV decelerates during the controlled stop operation;
and updating the first emergency stop distance in view of the current distance, a current speed, and the deceleration capability of the ADV.

4. The method of claim 2 , further comprising:
calculating a second emergency stop distance by the secondary ADS during the controlled stop operation; and
exchanging the first and second emergency stop distances between the primary ADS and secondary ADS to derive a third emergency stop distance based on the first and second emergency stop distances, wherein the emergency stop operation is activated based on the third emergency stop distance.

5. The method of claim 4 , further comprising selecting a longer one of the first emergency stop distance and the second emergency stop distance as the third emergency stop distance.

6. The method of claim 1 , further comprising selecting a longer one of the first controlled stop distance and the second controlled stop distance as the third controlled stop distance.

7. The method of claim 1 , further comprising:
determining whether the first controlled stop distance is different than the second controlled stop distance; and
refining the obstacle detection algorithm to reduce a possibility of a false positive or false negative detection of obstacles.

8. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations of an obstacle detection for an autonomous driving vehicle (ADV), the operations comprising:
detecting an obstacle by a primary autonomous driving system (ADS) and a secondary ADS using an obstacle detection algorithm based on sensor data provided by a plurality of sensors on the ADV;
calculating a first controlled stop distance and a second controlled stop distance by the primary ADS and secondary ADS respectively, based on a speed and a deceleration capability of the ADV in response to detecting the obstacle;
exchanging the first and second controlled stop distances between the primary ADS and secondary ADS to determine a third controlled stop distance; and
activating a controlled stop operation by the primary ADS to decelerate the ADV based on the third controlled stop distance, in response to determining that the ADV reaches within the third controlled distance between the ADV and the obstacle.

9. The machine-readable medium of claim 8 , wherein the operations further comprise:
calculating a first emergency stop distance by the primary ADS during the controlled stop operation; and
activating an emergency stop operation when the ADV moves within the first emergency stop distance from the obstacle.

10. The machine-readable medium of claim 9 , wherein the operations further comprise:
periodically measuring by the primary ADS a current distance between the ADV and the obstacle while the ADV decelerates during the controlled stop operation; and updating the first emergency stop distance in view of the current distance, a current speed, and the deceleration capability of the ADV.

11. The machine-readable medium of claim 9 , wherein the operations further comprise:
calculating a second emergency stop distance by the secondary ADS during the controlled stop operation; and
exchanging the first and second emergency stop distances between the primary ADS and secondary ADS to derive a third emergency stop distance based on the first and second emergency stop distances, wherein the emergency stop operation is activated based on the third emergency stop distance.

12. The machine-readable medium of claim 11 , wherein the operations further comprise selecting a longer one of the first emergency stop distance and the second emergency stop distance as the third emergency stop distance.

13. The machine-readable medium of claim 8 , wherein the operations further comprise selecting a longer one of the first controlled stop distance and the second controlled stop distance as the third controlled stop distance.

14. The machine-readable medium of claim 8 , wherein the operations further comprise:
determining whether the first controlled stop distance is different than the second controlled stop distance; and
refining the obstacle detection algorithm to reduce a possibility of a false positive or false negative detection of obstacles.

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 an obstacle detection for an autonomous driving vehicle (ADV), the operations including:
detecting an obstacle by a primary autonomous driving system (ADS) and a secondary ADS using an obstacle detection algorithm based on sensor data provided by a plurality of sensors on the ADV;
calculating a first controlled stop distance and a second controlled stop distance by the primary ADS and secondary ADS respectively based on a speed and a deceleration capability of the ADV in response to detecting the obstacle;
exchanging the first and second controlled stop distances between the primary ADS and secondary ADS to determine a third controlled stop distance; and
activating a controlled stop operation by the primary ADS to decelerate the ADV based on the third controlled stop distance, in response to determining that the ADV reaches within the third controlled distance between the ADV and the obstacle.

16. The system of claim 15 , wherein the operations further comprise:
calculating a first emergency stop distance by the primary ADS during the controlled stop operation; and
activating an emergency stop operation when the ADV moves within the first emergency stop distance from the obstacle.

17. The system of claim 16 , wherein the operations further comprise:
periodically measuring by the primary ADS a current distance between the ADV and the obstacle while the ADV decelerates during the controlled stop operation;
and updating the first emergency stop distance in view of the current distance, a current speed, and the deceleration capability of the ADV.

18. The system of claim 16 , wherein the operations further comprise

Assignees

• Baidu Usa Llc

Inventors

• Liu Xiaodong
• Qu Ning

Classifications

• G05D1/0223 Primary

  involving speed control of the vehicle (vehicle fittings for automatically controlling, i.e. preventing speed from exceeding an arbitrarily established velocity or maintaining speed at a particular velocity, as selected by the vehicle operator B60K31/00) · CPC title

• G05D1/0214

  in accordance with safety or protection criteria, e.g. avoiding hazardous areas (monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13) · CPC title

• G05D1/0077

  using redundant signals or controls · 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

• B60W10/18

  including control of braking systems · CPC title