US 11,703,869 B2
Latency accommodation in trajectory generation
Andrew E. Beller, San Francisco, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Nov. 26, 2019, as Appl. No. 16/696,754.
Prior Publication US 2021/0157325 A1, May 27, 2021
Int. Cl. G05D 1/02 (2020.01); G05D 1/00 (2006.01); G06V 20/58 (2022.01)
CPC G05D 1/0214 (2013.01) [G05D 1/0088 (2013.01); G05D 1/0223 (2013.01); G06V 20/58 (2022.01); G05D 2201/0213 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more computer-readable media storing instructions executable by the one or more processors, wherein the instructions, when executed, cause the system to perform operations comprising:
receiving first sensor data of an environment at a first time;
determining, at a second time and based at least in part on the first sensor data, a first location of an object in the environment;
determining, as a first latency, a difference between the first time and the second time, and averaging the first latency with one or more previously determined latencies, to obtain an average latency;
receiving second sensor data;
determining, based at least in part on the second sensor data, a predicted location of the object;
determining, based at least in part on a predetermined acceleration associated with the object and the average latency, a safety distance;
generating a trajectory for an autonomous vehicle based at least in part on the safety distance, wherein the first latency is determined based at least in part on a first predicted latency to generate the trajectory or a second predicted latency to control the autonomous vehicle to execute the trajectory; and
controlling the autonomous vehicle based at least in part on the trajectory and the predicted location of the object.