US 12,253,607 B1
Mirror object detection based on clustering of sensor data
Nehemia Girma Terefe, Foster City, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Aug. 31, 2022, as Appl. No. 17/899,963.
Int. Cl. G01S 17/931 (2020.01); G01S 17/86 (2020.01)
CPC G01S 17/931 (2020.01) [G01S 17/86 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising:
receiving, from a first lidar device, first lidar data associated with a vehicle operating in an environment;
receiving, from a second lidar device, second lidar data associated with the vehicle, wherein the first lidar device and the second lidar device are mounted at different locations of the vehicle;
determining a region of overlap between the first lidar data and the second lidar data;
determining, based at least in part on the first lidar data and the second lidar data and the region of overlap, third lidar data;
determining, based at least in part on elevation data of the third lidar data and azimuth data of the third lidar data, a subset of the third lidar data, wherein the subset includes a set of lidar points;
determining a first lidar point of the subset of the third lidar data and a second lidar point of the subset of the third lidar data;
determining, based at least in part on a first range of the first lidar point and a second range of the second lidar point, a range difference;
determining that the range difference of the first range and the second range meets or exceeds a threshold range;
determining, based at least in part on the range difference meeting or exceeding the threshold range, a modified subset of lidar points; and
controlling, based at least in part on the modified subset of lidar points, operation of the vehicle including modifying a trajectory of the vehicle.