US 12,296,858 B2
Hybrid log simulated driving
Andres Guillermo Morales Morales, San Francisco, CA (US); Samir Parikh, Los Gatos, CA (US); and Kai Zhenyu Wang, Foster City, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Nov. 18, 2021, as Appl. No. 17/529,803.
Prior Publication US 2023/0150549 A1, May 18, 2023
Int. Cl. B60W 60/00 (2020.01)
CPC B60W 60/00272 (2020.02) [B60W 60/0016 (2020.02); B60W 60/0017 (2020.02); B60W 2420/403 (2013.01); B60W 2554/4049 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising:
receiving sensor data captured by a physical vehicle located at a first road segment in an environment, the sensor data comprising an object located at a second road segment different from the first road segment;
determining, based at least in part on a trajectory library, at least one trajectory segment associated with the object;
determining that the at least one trajectory segment is mapped to a trajectory associated with the object;
determining object data representing the object in the sensor data;
instantiating, based at least in part on the object data, a simulated environment comprising a simulated object at the second road segment, wherein a first road topology associated with the object in the environment is different than a second road topology associated with the simulated environment and the object is associated with a first orientation with respect to a road in the environment and the object is associated with a second orientation with respect to a simulated road that is different than the first orientation;
determining a location of a simulated autonomous vehicle in the simulated environment, wherein the location is associated with the second road segment and the simulated autonomous vehicle corresponds to the physical vehicle; and
determining a response of the simulated autonomous vehicle to the simulated object.