US 12,428,032 B2
Determining prediction times for a model
Ethan Miller Pronovost, Redwood City, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Nov. 30, 2022, as Appl. No. 18/072,469.
Prior Publication US 2024/0174265 A1, May 30, 2024
Int. Cl. B60W 60/00 (2020.01); B60W 50/00 (2006.01)
CPC B60W 60/0027 (2020.02) [B60W 50/0097 (2013.01); B60W 2050/0028 (2013.01); B60W 2554/4042 (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 executable by the one or more processors, wherein the instructions, when executed, cause the one or more processors to perform operations comprising:
receiving, from a sensor associated with an autonomous vehicle, sensor data associated with an environment;
determining, based at least in part on the sensor data, a number of objects in the environment within a threshold distance of the autonomous vehicle;
determining, by a planning component of the autonomous vehicle and based at least in part on the number of objects in the environment, a temporal length of a time horizon for a future predicted state of at least one object, wherein the temporal length includes a first time step and a second time step different from the first time step;
searching a decision tree using the first time step within the time horizon and the second time step within the time horizon;
determining, by the planning component and based at least in part on searching the decision tree, multiple discrete predictions associated with the autonomous vehicle and the environment;
determining, by the planning component and based at least in part on the multiple discrete predictions, an action for the autonomous vehicle; and
controlling the autonomous vehicle based at least in part on the action.