Method and system for determining correctness of Lidar sensor data used for localizing autonomous vehicle

Patent metadata

Field	Value
Publication number	US-11474203-B2
Application number	US-201916695381-A
Country	US
Kind code	B2
Filing date	Nov 26, 2019
Priority date	Sep 27, 2019
Publication date	Oct 18, 2022
Grant date	Oct 18, 2022

Abstract

Disclosed herein is method and system for determining correctness of Lidar sensor data used for localizing autonomous vehicle. The system identifies one or more Region of Interests (ROIs) in Field of View (FOV) of Lidar sensors of autonomous vehicle along a navigation path. Each ROI includes one or more objects. Further, for each ROI, system obtains Lidar sensor data comprising one or more reflection points corresponding to the one or more objects. The system forms one or more clusters in each ROI. The system identifies a distance value between, one or more clusters projected on 2D map of environment and corresponding navigation map obstacle points, for each ROI. The system compares distance value between one or more clusters and obstacle points based on which correctness of Lidar sensor data is determined. In this manner, present disclosure provides a mechanism to detect correctness of Lidar sensor data for navigation in real-time.

First claim

What is claimed is:

1. A method of determining correctness of Lidar sensor data used for localizing an autonomous vehicle, the method comprising:
identifying, by a detection system, one or more Region of Interests (ROIs) in Field of View (FOV) of Lidar sensors of an autonomous vehicle along a navigation path;
obtaining, by the detection system, Lidar sensor data comprising one or more reflection points, in each of the one or more ROIs, wherein the one or more reflection points correspond to one or more objects in each of the one or more ROIs;
forming, by the detection system, one or more clusters of one or more reflection points in each of the one or more ROIs;
identifying, by the detection system, a distance value between the one or more clusters projected on a 2D map of an environment and corresponding navigation map obstacle points, for each of the one or more ROIs; and
determining, by the detection system, correctness of the Lidar sensor data based on the distance value.

2. The method as claimed in claim 1 , wherein the one or more clusters is of a pattern comprising at least one of straight line, arc, L-shape, or multiple bend shape.

3. The method as claimed in claim 2 , wherein each of the one or more clusters are formed by joining the one or more reflection points until the pattern is formed which is of a predefined length.

4. The method as claimed in claim 1 , wherein the Lidar sensor data is detected as correct when the distance value is less than a predefined threshold value for a predetermined percentage value of each of the identified clusters.

5. The method as claimed in claim 1 further comprising providing information to a navigation module of the autonomous vehicle to discontinue navigation when the Lidar sensor data is incorrect.

6. The method as claimed in claim 1 , wherein identifying the one or more ROIs comprises:
obtaining a reference navigation path from a current autonomous vehicle position to a destination position, wherein the reference navigation path comprises one or more path points;
obtaining the one or more path points in a predefined distance range in the reference navigation path;
identifying one or more tangents by forming a straight line of predefined number of path points; and
identifying the one or more ROIs in a direction of a perpendicular line from each of the one or more tangents.

7. A detection system for determining correctness of Lidar sensor data used for localizing an autonomous vehicle, the detection system comprising:
a processor; and
a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which, on execution, causes the processor to:
identify one or more Region of Interests (ROIs) in Field of View (FOV) of Lidar sensors of an autonomous vehicle along a navigation path;
obtain Lidar sensor data comprising one or more reflection points, in each of the one or more ROIs, wherein the one or more reflection points correspond to one or more objects in each of the one or more ROIs;
form one or more clusters of one or more reflection points in each of the one or more ROIs;
identify a distance value between the one or more clusters projected on a 2D map of an environment and corresponding navigation map obstacle points, for each of the one or more ROIs; and
determine correctness of the Lidar sensor data based on the distance value.

8. The detection system as claimed in claim 7 , wherein the one or more clusters is of a pattern comprising at least one of straight line, arc, L-shape, or multiple bend shape.

9. The detection system as claimed in claim 8 , wherein the processor forms each of the one or more clusters by joining the one or more reflection points until the pattern is formed which is of a predefined length.

10. The detection system as claimed in claim 7 , wherein the processor detects the Lidar sensor data as correct when the distance value is less than a predefined threshold value for a predetermined percentage value of each of the identified clusters.

11. The detection system as claimed in claim 7 , wherein the processor further provides information to a navigation module of the autonomous vehicle to discontinue navigation when the Lidar sensor data is incorrect.

12. The detection system as claimed in claim 7 , wherein the processor identifies the one or more ROIs by performing steps of:
obtaining a reference navigation path from a current autonomous vehicle position to a destination position, wherein the reference navigation path comprises one or more path points;
obtaining the one or more path points in a predefined distance range in the reference navigation path;
identifying one or more tangents by forming a straight line of predefined number of path points; and
identifying the one or more ROIs in a direction of a perpendicular line from each of the one or more tangents.

13. A non-transitory computer readable medium including instructions stored thereon that when processed by at least one processor causes detection system to determine correctness of Lidar sensor data used for localizing an autonomous vehicle by performing operations comprising:
identifying one or more Region of Interests (ROIs) in Field of View (FOV) of Lidar sensors of an autonomous vehicle along a navigation path;
obtaining Lidar sensor data comprising one or more reflection points, in each of the one or more ROIs, wherein the one or more reflection points correspond to one or more objects in each of the one or more ROIs;
forming one or more clusters of one or more reflection points in each of the one or more ROIs;
identifying a distance value between the one or more clusters projected on a 2D map of an environment and corresponding navigation map obstacle points, for each of the one or more ROIs; and
determining correctness of the Lidar sensor data based on the distance value.

Assignees

• Wipro Ltd

Inventors

• Kumar R Balaji Sunil
• Sarkar Manas

Classifications

• G01S7/497

  Means for monitoring or calibrating · CPC title

• G01S7/4808 Primary

  Evaluating distance, position or velocity data · CPC title

• G01S17/006

  Theoretical aspects · CPC title

• G01S17/931

  of land vehicles · CPC title