Systems and methods for automatically calibrating a LIDAR using information from a secondary vehicle

• US 10,145,945 B2
• Filed: 01/11/2017
• Issued: 12/04/2018
• Est. Priority Date: 01/11/2017
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Research Institute, Inc. (Toyota Motor Corporation)
• Inventors: Harada, Masahiro
• Primary Examiner(s): Patel, Shardul D
• Application Number:
  US15/403,585
• Publication Number:
  US 20180196127A1
• Time in Patent Office: 692 Days
• Field of Search: 701 33, 701 331, 356 401
• CPC Class Codes: G01S 17/42 Simultaneous measurement of distance and other co-ordinates indirect measurement G01S17/46
• CPC Class Codes: G01S 17/93 for anti-collision purposes
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G01S 2013/9316 combined with communication equipment with other vehicles or with base stations
• CPC Class Codes: G01S 7/003 Transmission of data between radar, sonar or lidar systems and remote stations
• CPC Class Codes: G01S 7/497 Means for monitoring or calibrating
• CPC Class Codes: G01S 7/4972 Alignment of sensor
• CPC Class Codes: G08G 1/161 Decentralised systems, e.g. inter-vehicle communication

Abstract

System, methods, and other embodiments described herein relate to calibrating a sensor of a first vehicle. In one embodiment, a method includes, in response to detecting that a second vehicle is proximate to the first vehicle, acquiring perceived information from the sensor about the second vehicle. The method includes comparing the perceived information with vehicle information to generate an offset that characterizes a variance within the perceived information produced by the sensor. The vehicle information identifies known characteristics of the second vehicle. The method includes adjusting the sensor according to the offset to correct the variance of the sensor.

Claims

1. A calibration system for calibrating a sensor of a first vehicle, the sensor being a light detecting and ranging (LIDAR) sensor, the calibration system comprising:

one or more processors;

a memory communicably coupled to the one or more processors and storing;

a capture module including instructions that when executed by the one or more processors cause the one or more processors to, in response to detecting that a second vehicle is proximate to the first vehicle, acquire perceived information from the sensor about the second vehicle, and

acquire, in the first vehicle, vehicle information about the second vehicle by wirelessly communicating with the second vehicle using vehicle-to-vehicle (V2V) communications, wherein the vehicle information identifies known characteristics of the second vehicle including at least a location of the second vehicle, and an indicator of a shape of the second vehicle; and

a calibration module including instructions that when executed by the one or more processors cause the one or more processors to compare the perceived information with a reference point cloud derived from the vehicle information to generate an offset that characterizes a variance within the perceived information produced by the sensor, and

wherein the calibration module includes instructions to adjust the sensor according to the offset to correct the variance of the sensor.

2. The calibration system of claim 1, wherein the capture module further includes instructions to acquire the perceived information by controlling the LIDAR sensor to generate data about the second vehicle including at least a perceived distance from the first vehicle to the second vehicle.

3. The calibration system of claim 1, wherein the capture module further includes instructions to acquire the vehicle information about the second vehicle by querying the second vehicle for at least a portion of the vehicle information using a vehicle-to-vehicle (V2V) communication channel to receive the vehicle information from the second vehicle.

4. The calibration system of claim 1, wherein the capture module further includes instructions to acquire the vehicle information by (i) obtaining a location from a global position system (GPS) of the second vehicle and (ii) obtaining a yaw measurement from an inertial navigation system (INS) of the second vehicle, and wherein the capture module includes instructions to derive the shape of the second vehicle from an identified model of the second vehicle identified in the vehicle information.

5. The calibration system of claim 4, wherein the capture module includes instructions to generate the reference point cloud from the shape, the location, and the yaw of the second vehicle, and wherein the calibration module further includes instructions to compare the reference point cloud with a perceived point cloud from the perceived information to generate the offset, wherein the offset is a set of points that identifies a variance of points in the perceived point cloud.

6. The calibration system of claim 1, wherein the capture module further includes instructions to acquire at least a portion of the vehicle information by using at least a camera of the first vehicle to locate the second vehicle and to identify a shape of the second vehicle from a camera image when the V2V communications are unavailable.

7. The calibration system of claim 1, wherein the calibration module further includes instructions to adjust the sensor by modifying operating parameters of the sensor to alter an alignment of the sensor, and wherein the calibration module further includes instructions to modify the operating parameters by changing values of one or more registers within the sensor that store the operating parameters.

8. The calibration system of claim 1, wherein the calibration module further includes instructions to compare the perceived information and the vehicle information by comparing perceived distances of a surface of the second vehicle as identified from the perceived information with identified distances to the second vehicle determined from the vehicle information, wherein calibrating the sensor occurs as the first vehicle is operating on a roadway without intervening with operation of the first vehicle.

9. A non-transitory computer-readable medium for calibrating a sensor of a first vehicle, the sensor being a light detecting and ranging (LIDAR) sensor, and storing instructions that when executed by one or more processors cause the one or more processors to:

in response to detecting that a second vehicle is proximate to the first vehicle, acquire perceived information from the sensor about the second vehicle;

acquire, in the first vehicle, vehicle information about the second vehicle by wirelessly communicating with the second vehicle using vehicle-to-vehicle (V2V) communications, wherein the vehicle information identifies known characteristics of the second vehicle including at least a location of the second vehicle, and an indicator of a shape of the second vehicle;

compare the perceived information with a reference point cloud derived from the vehicle information to generate an offset that characterizes a variance within the perceived information produced by the sensor; and

adjust the sensor according to the offset to correct the variance of the sensor.

10. The non-transitory computer-readable medium of claim 9, wherein the instructions to acquire the perceived information include instructions to control the LIDAR sensor to generate data about the second vehicle including at least a perceived distance from the first vehicle to the second vehicle.

11. The non-transitory computer-readable medium of claim 9, wherein the instructions to acquire the vehicle information about the second vehicle include instructions to query the second vehicle for at least a portion of the vehicle information, and wherein the instructions to acquire the vehicle information include instructions to communicate with the second vehicle using a vehicle-to-vehicle (V2V) communication channel to receive the vehicle information from the second vehicle.

12. The non-transitory computer-readable medium of claim 9, wherein the instructions to acquire the vehicle information include instructions to (i) obtain a location from a global position system (GPS) of the second vehicle and (ii) obtain a yaw measurement from an inertial navigation system (INS) of the second vehicle, and wherein the instructions to acquire the vehicle information include instructions to derive the shape of the second vehicle from an identified model of the second vehicle within the vehicle information.

13. The non-transitory computer-readable medium of claim 12, wherein the instructions to acquire the vehicle information include instructions to generate the reference point cloud from the shape, the location, and the yaw measurement of the second vehicle, and wherein the instructions to compare include instructions to compare the reference point cloud with a perceived point cloud from the perceived information to generate the offset, and wherein the offset is a set of points that identifies a variance of points in the perceived point cloud.

14. A method of calibrating a sensor of a first vehicle, the sensor being a light detecting and ranging (LIDAR) sensor, comprising:

in response to detecting that a second vehicle is proximate to the first vehicle, acquiring perceived information from the sensor about the second vehicle;

acquiring, in the first vehicle, vehicle information about the second vehicle by wirelessly communicating with the second vehicle using vehicle-to-vehicle (V2V) communications, wherein the vehicle information identifies known characteristics of the second vehicle including at least a location of the second vehicle, and an indicator of a shape of the second vehicle;

comparing the perceived information with a reference point cloud derived from the vehicle information to generate an offset that characterizes a variance within the perceived information produced by the sensor; and

adjusting the sensor according to the offset to correct the variance of the sensor.

15. The method of claim 14, wherein acquiring the perceived information includes controlling the LIDAR sensor to generate data about the second vehicle including at least a perceived distance from the first vehicle to the second vehicle.

16. The method of claim 14, further comprising:

acquiring the vehicle information about the second vehicle by querying the second vehicle for at least a portion of the vehicle information, wherein acquiring the vehicle information includes communicating with the second vehicle using a vehicle-to-vehicle (V2V) communication channel to receive the vehicle information from the second vehicle when the V2V communications are unavailable.

17. The method of claim 14, further comprising:

acquiring the vehicle information by (i) obtaining a location from a global position system (GPS) of the second vehicle and (ii) obtaining a yaw measurement from an inertial navigation system (INS) of the second vehicle, and wherein the shape of the second vehicle is derived from an identified model of the second vehicle.

18. The method of claim 17, wherein acquiring the vehicle information further includes generating the reference point cloud from the shape, the location, and the yaw measurement of the second vehicle, wherein comparing the perceived information and the vehicle information includes comparing the reference point cloud with a perceived point cloud derived from the perceived information to generate the offset, and wherein the offset is a set of points that identifies a variance of points in the perceived point cloud.

19. The method of claim 14, wherein adjusting the sensor includes modifying operating parameters of the sensor to alter an alignment of the sensor, wherein modifying the operating parameters includes changing values of one or more registers within the sensor that store the operating parameters, and wherein calibrating the sensor occurs as the first vehicle is operating on a roadway without intervening with operation of the first vehicle.

20. The method of claim 14, wherein comparing the perceived information and the vehicle information includes comparing perceived distances of a surface of the second vehicle as identified from the perceived information with identified distances to the second vehicle determined from the vehicle information.