US 11,718,315 B2
Periodically mapping calibration scene for calibrating autonomous vehicle sensors
Daniel Chou, Sunnyvale, CA (US); Nigel Rodrigues, San Francisco, CA (US); and Jordan Michael Croom, Los Angeles, CA (US)
Assigned to GM CRUISE HOLDINGS LLC, San Francisco, CA (US)
Filed by GM Cruise Holdings LLC, San Francisco, CA (US)
Filed on Dec. 28, 2021, as Appl. No. 17/563,617.
Application 17/563,617 is a continuation of application No. 17/550,239, filed on Dec. 14, 2021.
Prior Publication US 2023/0182766 A1, Jun. 15, 2023
Int. Cl. B60W 60/00 (2020.01); G06V 20/56 (2022.01); G01C 21/00 (2006.01); G06V 40/10 (2022.01); B60W 50/00 (2006.01)
CPC B60W 60/00 (2020.02) [G01C 21/3804 (2020.08); G01C 21/3885 (2020.08); G06V 20/56 (2022.01); G06V 40/10 (2022.01); B60W 2050/0083 (2013.01); B60W 2420/00 (2013.01); B60W 2556/40 (2020.02); B60W 2556/45 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A method for calibrating a sensor of an autonomous vehicle, the method comprising:
receiving, by the autonomous vehicle, a version of a calibration map, wherein the calibration map is a virtual representation of a calibration scene and includes a ground truth feature of a calibration target in the calibration scene, the calibration map is generated based on scene data from a detector in the calibration scene and is periodically updated so that a new version of the calibration map is generated based on new scene data from the detector;
determining, by the autonomous vehicle based on the version, whether the calibration scene has an error that would interfere with calibrating the sensor;
in response to determining that the calibration scene does not have the error, navigating in the calibration scene to allow the sensor to capture one or more features of the calibration target; and
calibrating the sensor based on the one or more features captured by the sensor and the ground truth feature.