Determining driving paths for autonomous driving vehicles based on map data

Patent metadata

Field	Value
Publication number	US-11520335-B2
Application number	US-201815952083-A
Country	US
Kind code	B2
Filing date	Apr 12, 2018
Priority date	Apr 12, 2018
Publication date	Dec 6, 2022
Grant date	Dec 6, 2022

Abstract

An ADV may determine whether there is preexisting map data for an environment or geographical area/location where the ADV is located/travelling. If there is no preexisting data, the ADV may generate map data based on sensor data obtained from one or more sensors of the ADV. The ADV may determine a path for the ADV based on the generated map data. If there is preexisting map data, the ADV may determine a path for the ADV based on the preexisting map data.

First claim

What is claimed is:

1. A computer-implemented method for operating an autonomous driving vehicle, the method comprising:
obtaining sensor data, wherein the sensor data indicates information about an environment through which the autonomous driving vehicle is currently traveling based on a selected route for the autonomous driving vehicle;
determining that preexisting map data of the environment is not available for determining a path of the autonomous driving vehicle through the environment;
in response to determining that preexisting map data of the environment is not available, adjusting operation of the autonomous driving vehicle from using preexisting map data to determine the path of the autonomous driving vehicle to generating and using locally generated map data to determine the path of the autonomous driving vehicle, wherein generating the locally generated map data comprises:
determining an area of the environment around the autonomous driving vehicle to map including determining a size of the area based on one or more factors, the one or more factors comprising at least a speed of the autonomous driving vehicle;
identifying a location, range, angle, and velocity of one or more objects within the area based on the sensor data, wherein the one or more objects comprise roads, road lines, sidewalks, buildings, and obstacles; and
generating, by a processing device of the autonomous driving vehicle, current map data of the area of the environment around the autonomous driving vehicle based on the sensor data and the one or more objects as the autonomous driving vehicle travels through the environment, the current map data to be used in place of the preexisting map data for determining a path of the autonomous driving vehicle through the environment;

determining a reference line, sample points, and segments for a path of the autonomous driving vehicle based on the current map data generated locally by the processing device of the autonomous driving vehicle and the selected route for the autonomous driving vehicle;
and
controlling the autonomous driving vehicle based on the reference line, sample points, and segments for the path of the autonomous driving vehicle.

2. The method of claim 1 , further comprising:
determining whether there is existing map data for the environment.

3. The method of claim 2 , wherein the current map data is generated in response to determining that there is no existing map data.

4. The method of claim 2 , further comprising:
determining a path for the autonomous driving vehicle based on the existing map data in response to determining that there is existing map data.

5. The method of claim 1 , further comprising:
obtaining path data indicative of a previous path used by the autonomous driving vehicle when the autonomous driving vehicle previously traveled through the environment.

6. The method of claim 5 , wherein the path for the autonomous driving vehicle is determined further based on the previous path.

7. The method of claim 1 , wherein the sensor data is generated by one or more sensors of the autonomous driving vehicle.

8. The method of claim 7 , wherein the sensor data comprises video data and wherein the one or more sensors comprise a camera.

9. The method of claim 7 , wherein the sensor data comprises radar data and wherein the one or more sensors comprise a radar unit.

10. The method of claim 7 , wherein the sensor data comprises light detection and range (LIDAR) data and wherein the one or more sensors comprises a light detection and range unit.

11. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:
obtaining sensor data, wherein the sensor data indicates information about an environment through which an autonomous driving vehicle is currently traveling based on a selected route for the autonomous driving vehicle;
determining that preexisting map data of the environment is not available for determining a path of the autonomous driving vehicle through the environment;
in response to determining that preexisting map data of the environment is not available, adjusting operation of the autonomous driving vehicle from using preexisting map data to determine the path of the autonomous driving vehicle to generating and using locally generated map data to determine the path of the autonomous driving vehicle, wherein generating the locally generated map data comprises:
determining an area of the environment around the autonomous driving vehicle to map including determining a size of the area based on one or more factors, the one or more factors comprising at least a speed of the autonomous driving vehicle;
identifying a location, range, angle, and velocity of one or more objects within the area based on the sensor data, wherein the one or more objects comprise roads, road lines, sidewalks, buildings, and obstacles; and
generating current map data of the area of the environment around the autonomous driving vehicle based on the sensor data and the one or more objects as the autonomous driving vehicle travels through the environment, the current map data to be used in place of the preexisting map data for determining a path of the autonomous driving vehicle;

determining a reference line, sample points, and segments for a path of the autonomous driving vehicle based on the current map data generated locally by a processing device of the autonomous driving vehicle and the selected route for the autonomous driving vehicle; and
controlling the autonomous driving vehicle based on the reference line, sample points, and segments for the path of the autonomous vehicle.

12. The non-transitory machine-readable medium of claim 11 , wherein the operations further comprise:
determining whether there is existing map data for the environment.

13. The non-transitory machine-readable medium of claim 12 , wherein the current map data is generated in response to determining that there is no existing map data.

14. The non-transitory machine-readable medium of claim 12 , wherein the operations further comprise:
determining a path for the autonomous driving vehicle based on the existing map data in response to determining that there is existing map data.

15. The non-transitory machine-readable medium of claim 11 , wherein the operations further comprise:
obtaining a previous path used by the autonomous driving vehicle when the autonomous driving vehicle previously traveled through the environment.

16. The non-transitory machine-readable medium of claim 15 , wherein the path for the autonomous driving vehicle is determined further based on the previous path.

17. The non-transitory machine-readable medium of claim 11 , wherein the sensor data is generated by one or more sensors of the autonomous driving vehicle.

18. 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, the operations comprising:
obtaining sensor data, wherein the sensor data indicates information about an environment through which an autonomous driving vehicle is currently traveling based on a selected route for the autonomous driving vehicle;
determining that preexisting map data of the environment is not available for determining a path of the autonomous driving vehicle through the environment;
in response to determining that preexisting map data of the environment is not available,

Assignees

• Baidu Usa Llc

Inventors

• Li Dong
• Jiang Yifei
• Zhang Liangliang
• Tao Jiaming
• Luo Qi
• Hu Jiangtao

Classifications

• G01C21/3837

  Data obtained from a single source · CPC title

• G01C21/34

  Route searching; Route guidance · CPC title

• G01C21/3848 Primary

  Data obtained from both position sensors and additional sensors · CPC title

• G01C21/3602

  Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera · CPC title

• G01C21/3407

  specially adapted for specific applications · CPC title