Pavement marking map change detection, reaction, and live tile shipping

Patent metadata

Field	Value
Publication number	US-11906311-B2
Application number	US-202318118937-A
Country	US
Kind code	B2
Filing date	Mar 8, 2023
Priority date	Jun 29, 2020
Publication date	Feb 20, 2024
Grant date	Feb 20, 2024

Abstract

Systems, methods, and computer-readable media are provided for detecting a pavement marking around an autonomous vehicle, comparing the detected pavement marking with a pavement marking present in a semantic data map, determining whether a change has occurred between the detected pavement marking and the pavement marking present in the semantic data map, and updating the semantic data map based on the determining of whether the change has occurred between the detected pavement marking and the pavement marking present in the semantic data map.

First claim

What is claimed is:

1. A computer-implemented method comprising:
determining, by an autonomous vehicle, that light detection and ranging (LiDAR) sensor data captured using at least one LiDAR sensor associated with the autonomous vehicle includes a detected pavement marking;
comparing, by the autonomous vehicle, the LiDAR sensor data that includes the detected pavement marking with corresponding data map points of a pavement marking present in a semantic data map;
determining, by the autonomous vehicle and based on the comparing, that a change has occurred between the detected pavement marking and the pavement marking present in the semantic data map;
determining, by the autonomous vehicle, a severity of the change of the detected pavement marking;
in response to determining that the severity of the change of the detected pavement marking is greater than an acceptable threshold, updating, by the autonomous vehicle, the semantic data map based on the change to produce an updated semantic data map, wherein the semantic data map is updated by selecting between generating local LiDAR intensity tiles or generating colorized tiles for geospatial tiles based on a category of the detected pavement marking; and
navigating the autonomous vehicle based on the updated semantic data map.

2. The computer-implemented method of claim 1 , wherein the detected pavement marking is a lane line or a crosswalk.

3. The computer-implemented method of claim 1 , wherein the change that has occurred between the detected pavement marking and the pavement marking present in the semantic data map is a percentage of change between the detected pavement marking and the pavement marking present in the semantic data map.

4. The computer-implemented method of claim 1 , further comprising providing the updated semantic data map to an autonomous vehicle fleet server.

5. The computer-implemented method of claim 1 , further comprising:
generating geospatial tiles around the autonomous vehicle; and
designating each geospatial tile that is associated with the detected pavement marking.

6. The computer-implemented method of claim 5 , wherein the geospatial tile is a local LIDAR intensity tile or a colorized tile.

7. The computer-implemented method of claim 1 , further comprising:
in response to determining that the severity of the change of the detected pavement marking is greater than the acceptable threshold, determining an updated route for the autonomous vehicle.

8. The computer-implemented method of claim 1 , further comprising:
determining that the change of the detected pavement marking is outside of a current route of the autonomous vehicle; and
in response, proceeding along the current route of the autonomous vehicle.

9. An autonomous vehicle comprising:
one or more processors; and
at least one computer-readable storage medium having stored therein instructions which, when executed by the one or more processors, cause the autonomous vehicle to:
determine that light detection and ranging (LiDAR) sensor data captured using at least one LiDAR sensor associated with the autonomous vehicle includes a detected pavement marking;
compare the LiDAR sensor data that includes the detected pavement marking with corresponding data map points of a pavement marking present in a semantic data map;
determine, based on the comparing, that a change has occurred between the detected pavement marking and the pavement marking present in the semantic data map;
determine a severity of the change of the detected pavement marking;
in response to determining that the severity of the change of the detected pavement marking is greater than an acceptable threshold, update the semantic data map based on the change to produce an updated semantic data map, wherein the semantic data map is updated by selecting between generating local LiDAR intensity tiles or generating colorized tiles for geospatial tiles based on a category of the detected pavement marking; and
navigate the autonomous vehicle based on the updated semantic data map.

10. The autonomous vehicle of claim 9 , wherein the detected pavement marking is a lane line or a crosswalk.

11. The autonomous vehicle of claim 9 , wherein the change that has occurred between the detected pavement marking and the pavement marking present in the semantic data map is a percentage of change between the detected pavement marking and the pavement marking present in the semantic data map.

12. The autonomous vehicle of claim 9 , wherein the instructions which, when executed by the one or more processors, cause the autonomous vehicle to provide the updated semantic data map to an autonomous vehicle fleet server.

13. The autonomous vehicle of claim 9 , wherein the instructions which, when executed by the one or more processors, cause the autonomous vehicle to:
generate geospatial tiles around the autonomous vehicle; and
designate each geospatial tile that is associated with the detected pavement marking.

14. The autonomous vehicle of claim 13 , wherein the geospatial tile is a local LIDAR intensity tile or a colorized tile.

15. The autonomous vehicle of claim 9 , wherein the instructions which, when executed by the one or more processors, cause the autonomous vehicle to:
determine that the change of the detected pavement marking is outside of a current route of the autonomous vehicle; and
in response, proceed along the current route of the autonomous vehicle.

16. A non-transitory computer-readable storage medium comprising:
instructions stored on the non-transitory computer-readable storage medium, the instructions, when executed by one or more processors, cause the one or more processors to:
determine that light detection and ranging (LiDAR) sensor data captured using at least one LiDAR sensor associated with an autonomous vehicle includes a detected pavement marking;
compare the LiDAR sensor data that includes the detected pavement marking with corresponding data map points of a pavement marking present in a semantic data map;
determine, based on the comparing, that a change has occurred between the detected pavement marking and the pavement marking present in the semantic data map;
determine a severity of the change of the detected pavement marking;
in response to determining that the severity of the change of the detected pavement marking is greater than an acceptable threshold, update, the semantic data map based on the change to produce an updated semantic data map, wherein the semantic data map is updated by selecting between generating local LiDAR intensity tiles or generating colorized tiles for geospatial tiles based on a category of the detected pavement marking; and
navigate the autonomous vehicle based on the updated semantic data map.

17. The non-transitory computer-readable storage medium of claim 16 , wherein the detected pavement marking is a lane line or a crosswalk.

18. The non-transitory computer-readable storage medium of claim 16 , wherein the change that has occurred between the detected pavement marking and the pavement marking present in the semantic data map is a percentage of change between the detected pavement marking and the pavement marking present in the semantic data map.

19. The non-transitory computer-readable storage medium of claim 16 , wherein the instructions, when executed by the one or more processors, cause the one or more processors to provide the updated semantic data map to an autonomous vehicle fleet server.

20. The non-transitory computer-readable storage med

Assignees

• Gm Cruise Holdings Llc

Inventors

• Fasola Juan
• Kumar Harman
• Kushwaha Shreyans
• Zhou Xiaoyu
• Lin Yu-Cheng

Classifications

• G01C21/32 Primary

  Structuring or formatting of map data · CPC title

• G01S17/89

  for mapping or imaging · CPC title

• G05D1/0274 Primary

  using mapping information stored in a memory device (navigation using map-matching G01C21/30) · CPC title

• G05D1/0088

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title

• G05D2201/0213

  Physics · mapped topic