US 12,422,532 B1
Sensor calibration
Sreevatsan Bhaskaran, Redwood City, CA (US); and Mathew Piotrowicz, Foster City, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Nov. 19, 2021, as Appl. No. 17/531,615.
Int. Cl. G01S 7/497 (2006.01); G01S 17/931 (2020.01)
CPC G01S 7/497 (2013.01) [G01S 17/931 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more non-transitory computer readable media storing computer executable instructions that, when executed, cause the one or more processors to perform operations comprising:
predicting a calibration level of a lidar sensor prior to installation on an autonomous vehicle by:
receiving lidar data from the lidar sensor, the lidar data comprising a first lidar scan of an environment at a first time and a second lidar scan of the environment at a second time different from the first time;
determining, based at least in part on the first lidar scan, a first amount of lidar returns in a first region at a first distance range from the lidar sensor and a second amount of lidar returns in a second region at a second distance range from the lidar sensor different from the first distance range;
determining, based at least in part on the second lidar scan, a third amount of lidar returns in the first region and a fourth amount of lidar returns in the second region;
determining, by a model, a first calibration score for the first region based at least in part on the first amount of lidar returns and the third amount of lidar returns;
determining, by the model, a second calibration score for the second region based at least in part on the second amount of lidar returns and the fourth amount of lidar returns;
determining, based at least in part on the first calibration score and the second calibration score, the calibration level of the lidar sensor to indicate predicted performance of the lidar sensor after the installation on the autonomous vehicle;
causing the lidar sensor to be installed on the autonomous vehicle based at least in part on the calibration level, wherein the autonomous vehicle is configured to operate based at least in part on the lidar sensor; and
causing the autonomous vehicle to navigate in a real-world environment based on second sensor data output by the lidar sensor.