Method for correcting alignment of vehicle mounted laser scans with an elevation map for obstacle detection

• US 9,052,721 B1
• Filed: 08/28/2012
• Issued: 06/09/2015
• Est. Priority Date: 08/28/2012
• Status: Active Grant

• Current Assignee: Waymo LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Dowdall, Jonathan Baldwin, Dolgov, Dmitri, Ferguson, David Ian, Zhu, Jiajun
• Primary Examiner(s): Trammell, James
• Assistant Examiner(s): Stroud, James E
• Application Number:
  US13/597,143
• Time in Patent Office: 1,015 Days
• Field of Search: 701/23
• US Class Current: 1/1
• CPC Class Codes: B64D 45/00 Aircraft indicators or protectors not otherwise provided for camouflage F41H3/00
• CPC Class Codes: G05D 1/024 in combination with a laser lasers per se H01S
• CPC Class Codes: G05D 1/0242 using non-visible light signals, e.g. IR or UV signals
• CPC Class Codes: G05D 1/0272 comprising means for registering the travel distance, e.g. revolutions of wheels measuring distance traversed on the ground by vehicles, e.g. using odometers G01C22/00

Abstract

Methods and systems for alignment of light detection and ranging (LIDAR) data are described. In some examples, a computing device of a vehicle may be configured to compare a three-dimensional (3D) point cloud to a reference 3D point cloud to detect obstacles on a road. However, in examples, the 3D point cloud and the reference 3D point cloud may be misaligned. To align the 3D point cloud with the reference 3D point cloud, the computing device may be configured to determine a planar feature in the 3D point cloud of the road and a corresponding planar feature in the reference 3D point cloud. Further, the computing device may be configured to determine, based on comparison of the planar feature to the corresponding planar feature, a transform. The computing device may be configured to apply the transform to align the 3D point cloud with the reference 3D point cloud.

Claims

1. A method, comprising:

receiving, at a computing device configured to control a vehicle, from a light detection and ranging (LIDAR) device coupled to the vehicle, LIDAR-based information comprising a three-dimensional (3D) point cloud, wherein the 3D point cloud comprises points corresponding to light emitted from the LIDAR device and reflected from a surface of a road on which the vehicle is travelling and from one or more obstacles on the road, wherein the computing device has access to a reference 3D point cloud of the surface of the road, and wherein the reference 3D point cloud and the 3D point cloud are misaligned;

determining, using the computing device, a planar feature in the 3D point cloud, and a corresponding planar feature in the reference 3D point cloud;

determining, based on a comparison of the planar feature to the corresponding planar feature, a transform; and

applying the transform to points of the 3D point cloud or points of the reference 3D point cloud so as to align the 3D point cloud with the reference 3D point cloud.

2. The method of claim 1, wherein the vehicle is in an autonomous operation mode.

3. The method of claim 1, wherein the planar feature relates to a plane of the surface of the road.

4. The method of claim 1, wherein determining the transform comprises determining a difference in one or more of pitch angle, roll angle, or elevation of the planar feature compared to the corresponding planar feature.

5. The method of claim 1, wherein the reference 3D point cloud relates to an obstacle-free elevation map of the road.

6. The method of claim 1, further comprising detecting the one or more obstacles based on a comparison of the 3D point cloud to the reference 3D point cloud aligned with the 3D point cloud.

7. The method of claim 6, further comprising:

modifying, using the computing device, a control strategy associated with a driving behavior of the vehicle, based on the detecting of the one or more obstacles; and

controlling, using the computing device, the vehicle based on the modified control strategy.

8. The method of claim 1, wherein determining the corresponding planar feature in the reference 3D point cloud comprises determining a latitude, longitude, and yaw angle of the vehicle at a location of the vehicle on the road.

9. A non-transitory computer readable medium having stored thereon instructions executable by a computing device to cause the computing device to perform functions comprising:

receiving, from a light detection and ranging (LIDAR) device coupled to a vehicle, LIDAR-based information comprising a three-dimensional (3D) point cloud, wherein the 3D point cloud comprises points corresponding to light emitted from the LIDAR device and reflected from a surface of a road on which the vehicle is travelling and from one or more obstacles on the road;

determining a planar feature in the 3D point cloud, and a corresponding planar feature in a reference 3D point cloud of the surface of the road, wherein the reference 3D point cloud and the 3D point cloud are misaligned;

determining, based on a comparison of the planar feature to the corresponding planar feature, a transform; and

applying the transform to points of the 3D point cloud or points of the reference 3D point cloud so as to align the 3D point cloud with the reference 3D point cloud.

10. The non-transitory computer readable medium of claim 9, wherein the computing device is configured to control the vehicle in an autonomous operation mode.

11. The non-transitory computer readable medium of claim 9, wherein the function of determining the transform comprises determining a difference in one or more of pitch angle, roll angle, or elevation of the planar feature compared to the corresponding planar feature.

12. The non-transitory computer readable medium of claim 9, wherein the function of applying the transform comprises applying the transform to points in the 3D point cloud or points in the reference 3D point cloud.

13. The non-transitory computer readable medium of claim 9, wherein the reference 3D point cloud relates to an obstacle-free elevation map of the road, and wherein the instructions are further executable by the computing device to cause the computing device to perform functions comprising detecting the one or more obstacles based on a comparison of the 3D point cloud to the reference 3D point cloud aligned with the 3D point cloud.

14. The non-transitory computer readable medium of claim 9, wherein the function of determining the corresponding planar feature in the reference 3D point cloud comprises:

determining a latitude, longitude, and yaw angle of the vehicle at a location of the vehicle on the road; and

identifying a portion in the reference 3D point cloud corresponding to the location of the vehicle; and

determining the corresponding planar feature in the identified portion.

15. A control system for a vehicle, comprising:

a light detection and ranging (LIDAR) device configured to provide LIDAR-based information comprising a three-dimensional (3D) point cloud, wherein the 3D point cloud comprises points corresponding to light emitted from the LIDAR device and reflected from a surface of a road on which the vehicle is travelling and from one or more obstacles on the road; and

a computing device in communication with the LIDAR device, wherein the computing device has access to a reference 3D point cloud of the surface of the road, wherein the reference 3D point cloud and the 3D point cloud are misaligned, and wherein the computing device is configured to;

receive the LIDAR-based information;

determine a planar feature in the 3D point cloud, and a corresponding planar feature in the reference 3D point cloud;

determine, based on a comparison of the planar feature to the corresponding planar feature, a transform; and

apply the transform to points of the 3D point cloud or points of the reference 3D point cloud so as to align the 3D point cloud with the reference 3D point cloud.

16. The system of claim 15, wherein the computing device is further configured to control the vehicle in an autonomous operation mode.

17. The system of claim 15, wherein, to determine the transform, the computing device is configured to:

compare the 3D point cloud to the reference 3D point cloud; and

determine a difference in one or more of pitch angle, roll angle, or elevation of the planar feature compared to the corresponding planar feature.

18. The system of claim 15, wherein the reference 3D point cloud relates to an obstacle-free elevation map of the road, and wherein the computing device is configured to:

compare the 3D point cloud to the reference 3D point cloud aligned with the 3D point cloud; and

detect the one or more obstacles in the 3D point cloud.

19. The system of claim 15, wherein the computing device is configured to apply the transform to points in the 3D point cloud or points in the reference 3D point cloud.

20. The system of claim 15, further comprising a Global Position System (GPS) module, wherein, to determine the corresponding planar feature in the reference 3D point cloud, the computing device is configured to:

receive, from the GPS module, location information relating to a latitude, longitude, and yaw angle of the vehicle at a location of the vehicle on the road;

identify, based on the location information, a portion in the reference 3D point cloud corresponding to the location; and

determine the corresponding planar feature in the identified portion.