US 12,485,882 B1
Collision avoidance and mitigation in autonomous vehicles using predicted trajectories
Chuang Wang, Woodside, CA (US); Cooper Stokes Sloan, San Francisco, CA (US); Noureldin Ehab Hendy, Foster City, CA (US); William Harland Montgomery, IV, Burlingame, CA (US); and Yi Xu, Pasadena, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Oct. 29, 2021, as Appl. No. 17/514,542.
Int. Cl. B60W 30/09 (2012.01)
CPC B60W 30/09 (2013.01) [B60W 2420/408 (2024.01); B60W 2540/049 (2020.02); B60W 2540/227 (2020.02); B60W 2554/00 (2020.02); B60W 2554/801 (2020.02); B60W 2554/802 (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 computer-executable instructions that, when executed, cause the system to perform operations comprising: receiving sensor data captured by a sensor associated with an autonomous vehicle within an environment;
receiving a trajectory and a contingent vehicle trajectory for the autonomous vehicle to follow;
determining, based at least in part on the trajectory and the sensor data, a likelihood of a potential collision between the autonomous vehicle and a dynamic object;
determining, based at least in part on the likelihood of the potential collision meeting or exceeding a threshold, a predicted first velocity vector for the autonomous vehicle and a predicted second velocity vector for the dynamic object; determining, based at least in part on comparing the predicted first velocity vector with the predicted second velocity vector, a first predicted relative angle of impact associated with the potential collision,
determining, based at least in part on the contingent vehicle trajectory and the sensor data, an additional likelihood of a second potential collision between the autonomous vehicle and the dynamic object;
determining, based at least in part on the additional likelihood of the second potential collision meeting or exceeding the threshold, a predicted third velocity vector for the autonomous vehicle and a predicted fourth velocity vector for the dynamic object;
determining, based at least in part on comparing the predicted third velocity vector with the predicted fourth velocity vector, a second predicted relative angle of impact associated with the second potential collision;
determining, based at least in part on comparing the first predicted relative angle of impact and the second predicted relative angle of impact and as a determined trajectory, the trajectory or contingent vehicle trajectory;
and controlling the autonomous vehicle by following the determined trajectory.