US 11,938,966 B1
Vehicle perception system validation
Clement Besson, San Francisco, CA (US); Minsu Jang, San Mateo, CA (US); Antonio Prioletti, Redwood City, CA (US); and Peng Wang, Cupertino, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Dec. 3, 2021, as Appl. No. 17/541,950.
Int. Cl. B60W 60/00 (2020.01); B60W 30/095 (2012.01); B60W 40/06 (2012.01); G06N 20/00 (2019.01)
CPC B60W 60/0015 (2020.02) [B60W 30/0953 (2013.01); B60W 30/0956 (2013.01); B60W 40/06 (2013.01); B60W 60/0013 (2020.02); G06N 20/00 (2019.01); B60W 2520/00 (2013.01); B60W 2554/404 (2020.02); B60W 2554/80 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
receiving log data associated with an autonomous vehicle, the log data representing a scenario including an environment;
identifying, based at least in part on the log data, an error associated with an output received from a perception component of an autonomous vehicle, the perception component configured to detect objects in the environment;
determining a magnitude of the error;
determining that the magnitude of the error violates a perception requirement that is associated with detecting an object in the environment, the perception requirement established based at least in part on a determination that the magnitude of the error would contribute to a collision between the autonomous vehicle and the object in alternative scenarios in which an aspect associated with the object is altered across the alternative scenarios; and
outputting at least a portion of the log data that is associated with the error for use in updating a machine-learned model associated with the perception component to meet the perception requirement.