US 12,291,193 B1
Trajectory determination based on heuristic grid data
Steven Cheng Qian, San Francisco, CA (US); and Zheyuan Xie, Foster City, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Feb. 23, 2023, as Appl. No. 18/113,149.
Int. Cl. B60W 30/06 (2006.01); B60W 50/00 (2006.01); G01C 21/34 (2006.01)
CPC B60W 30/06 (2013.01) [B60W 50/00 (2013.01); G01C 21/3453 (2013.01); B60W 2050/0022 (2013.01)] 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 one or more processors to perform operations comprising:
determining a location of an autonomous vehicle in an environment;
receiving, based at least in part on the location being within a threshold distance of a destination, a parking space associated with a target pose indicating one or more of a target position or target orientation for the autonomous vehicle;
generating a trajectory associated with navigating the autonomous vehicle to the parking space;
determining, as a pose, one or more of a position or orientation of the autonomous vehicle within the environment;
determining, based at least in part on the pose of the autonomous vehicle and the target pose of the parking space, a relative heading associated with the autonomous vehicle;
determining a relative lateral offset associated with the autonomous vehicle and a relative longitudinal offset associated with the autonomous vehicle;
accessing, based at least in part on the relative heading, a layer of a three-dimensional grid, the three-dimensional grid comprising a plurality of layers that are organized by relative heading angles;
determining, based at least in part on the relative lateral offset and the relative longitudinal offset, a region within the layer;
receiving, based at least in part on the region, a cost associated with parking in the parking space;
determining, based at least in part on the cost, to follow the trajectory; and
controlling the autonomous vehicle based at least in part on the trajectory.