SYSTEM AND METHOD FOR LIDAR-BASED VEHICULAR LOCALIZATION RELATING TO AUTONOMOUS NAVIGATION

• US 20190323844A1
• Filed: 04/18/2018
• Published: 10/24/2019
• Est. Priority Date: 04/18/2018
• Status: Active Grant

• Current Assignee: Faraday & Future Inc.
• Original Assignee: Faraday & Future Inc.
• Inventors: YENDLURI, Daedeepya, GADE, Sowmya, KURUVILLA, Anupama, BATUR, Aziz Umit
• Granted Patent: US 11,294,060 B2
• Time in Patent Office: Days
• CPC Class Codes: G01C 21/1652 with ranging devices, e.g. LIDAR or RADAR
• CPC Class Codes: G01C 21/1654 with electromagnetic compass
• CPC Class Codes: G01C 21/1656 with passive imaging devices, e.g. cameras
• CPC Class Codes: G01C 21/28 with correlation of data from several navigational instruments
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G01S 17/86 Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
• CPC Class Codes: G01S 17/89 for mapping or imaging
• CPC Class Codes: G01S 7/4808 Evaluating distance, position or velocity data
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06T 17/05 Geographic models
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2210/56 Particle system, point based geometry or rendering

Abstract

A system for use in a vehicle, the system comprising one or more sensors, one or more processors operatively coupled to the one or more sensors, and a memory including instructions, which when executed by the one or more processors, cause the one or more processors to perform a method. The method comprising capturing a current point cloud with the one or more sensors, determining an estimated location and an estimated heading of the vehicle, selecting one or more point clouds based on the estimated location and heading of the vehicle, simplifying the current point cloud and the one or more point clouds, correlating the current point cloud to the one or more point clouds, and determining an updated estimate of the location of the vehicle based on correlation between the current point cloud and the one or more point clouds.

Claims

1. A system for use in a vehicle, the system comprising:

one or more sensors;

one or more processors operatively coupled to the one or more sensors; and

a memory including instructions, which when executed by the one or more processors, cause the one or more processors to perform a method comprising the steps of;

capturing a current point cloud with the one or more sensors;

determining an estimated location and an estimated heading of the vehicle;

selecting one or more point clouds based on the estimated location and heading of the vehicle;

simplifying the current point cloud and the one or more point clouds;

correlating the current point cloud to the one or more point clouds; and

determining an updated estimate of the location of the vehicle based on correlation between the current point cloud and the one or more point clouds.

2. The system of claim 1, wherein the one or more sensors comprises a LIDAR sensor.

3. The system of claim 1, wherein the estimated location of the vehicle comprises an error bounds defining an area in which the vehicle is likely located.

4. The system of claim 3, wherein selecting the one or more point clouds based on the estimated location and heading of the vehicle comprises retrieving the one or more point clouds containing data about the area defined by the error bounds.

5. The system of claim 4, wherein selecting the one or more point clouds based on the estimated location and heading of the vehicle further comprises:

for each of the one or more point clouds containing data about the area defined by the error bounds;

determining a distance score for a respective point cloud;

determining whether the distance score is less than a search radius;

in accordance with a determination that the distance score is less than the search radius, selecting the respective point cloud; and

in accordance with a determination that the distance score is not less than the search radius, forgoing selecting the respective point cloud.

6. The system of claim 5, wherein the distance score is based on the estimated location and heading of the vehicle.

7. The system of claim 4, wherein selecting the one or more point clouds based on the estimated location and heading of the vehicle further comprises:

for each of the one or more point clouds containing data about the area defined by the error bounds, determining a distance score for a respective point cloud;

selecting the respective point cloud with the lowest distance score.

8. The system of claim 4, wherein selecting the one or more point clouds based on the estimated location and heading of the vehicle further comprises:

for each of the one or more point clouds containing data about the area defined by the error bounds, determining a distance score for a respective point cloud;

selecting up to ten of the one or more point clouds with the lowest distance score.

9. The system of claim 4, wherein the one or more point clouds containing data about the area defined by the error bounds are retrieved from the memory.

10. The system of claim 9, wherein the one or more point clouds were previously captured by the vehicle.

11. The system of claim 4, wherein the one or more point clouds containing data about the area defined by the error bounds are retrieved from a remote server.

12. The system of claim 11, wherein the one or more point clouds were previously captured by the vehicle or another vehicle.

13. The system of claim 1, wherein simplifying the current point cloud and the one or more point clouds comprises one or more of:

removing data points due to ground and the vehicle from the current point cloud and the one or more point clouds;

down-sampling the current point cloud and the one or more point clouds; and

removing outlier data points from the current point cloud and the one or more point clouds.

14. The system of claim 13, wherein removing outlier data points from the current point cloud and the one or more point clouds comprises:

calculating a distance from a first data point in the current point cloud to a corresponding data point in the one or more point clouds; and

in accordance with a determination that the distance is greater than a threshold, removing the first data point and the corresponding data point from the current point cloud and the one or more point clouds.

15. The system of claim 14, wherein the threshold is three meters.

16. The system of claim 1, wherein correlating the current point cloud to the one or more point clouds comprises translating and rotating the one or more point clouds and the current point cloud with an Interactive Closest Point (ICP) technique.

17. The system of claim 16, wherein the ICP technique is performed multiple times with different starting points.

18. The system of claim 1, wherein correlating the current point cloud to the one or more point clouds further comprises:

calculating a distance from a first data point in the current point cloud to a corresponding data point in the one or more point clouds; and

in accordance with a determination that the distance is equal to or greater than a threshold, forgoing correlating the first data point in the current point cloud to the corresponding data point in the one or more point clouds.

19. A non-transitory computer-readable medium including instructions, which when executed by one or more processors, cause the one or more processors to perform a method comprising:

capturing a current point cloud with one or more sensors;

determining an estimated location and an estimated heading of a vehicle;

selecting one or more point clouds based on the estimated location and heading of the vehicle;

simplifying the current point cloud and the one or more point clouds;

correlating the current point cloud to the one or more point clouds; and

determining an updated estimate of the location of the vehicle based on correlation between the current point cloud and the one or more point clouds.

20. A method comprising:

capturing a current point cloud with one or more sensors;

determining an estimated location and an estimated heading of a vehicle;

selecting one or more point clouds based on the estimated location and heading of the vehicle;

simplifying the current point cloud and the one or more point clouds;

correlating the current point cloud to the one or more point clouds; and

determining an updated estimate of the location of the vehicle based on correlation between the current point cloud and the one or more point clouds.