US 12,030,528 B2
Vehicle perception system with temporal tracker
Cheng-Hsin Wuu, Pittsburgh, PA (US); Subhasis Das, Menlo Park, CA (US); Po-Jen Lai, Mountain View, CA (US); Qian Song, San Mateo, CA (US); and Benjamin Isaac Zwiebel, Burlingame, 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. 17/542,352.
Prior Publication US 2023/0174110 A1, Jun. 8, 2023
Int. Cl. B60W 60/00 (2020.01); G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 20/58 (2022.01)
CPC B60W 60/0027 (2020.02) [G06N 20/00 (2019.01); G06V 10/764 (2022.01); G06V 20/58 (2022.01); 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 sensor data representing an object in an environment in which a vehicle is operating, the sensor data associated with a current time;
inputting the sensor data into a machine-learned model that is configured for use in the vehicle, the machine-learned model being configured to:
determine, based at least in part on the sensor data, object data including at least a bounding box associated with the object in the environment, the bounding box indicative of a location of the object in the environment at the current time;
determine tracking data based at least in part on additional sensor data associated with a time prior to the current time;
determine, based at least in part on the sensor data and the tracking data, an estimated location of the object in the environment at the current time; and
associate, as tracked object data, the object data with the tracking data based at least in part on the estimated location;
receiving, from the machine-learned model, an output including at least the tracked object data; and
controlling the vehicle based at least in part on the tracked object data.