US 12,304,530 B1
Autonomous vehicle control based on a probability of collision
Joseph Lorenzetti, Foster City, CA (US); Anjali Lakshmi Pemmaraju, San Francisco, CA (US); and Shahriar Sefati, San Francisco, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Dec. 14, 2022, as Appl. No. 18/080,978.
Int. Cl. B60W 60/00 (2020.01); B60W 30/095 (2012.01); B60W 50/14 (2020.01)
CPC B60W 60/0027 (2020.02) [B60W 30/0956 (2013.01); B60W 50/14 (2013.01); B60W 60/0015 (2020.02); B60W 2554/4041 (2020.02); B60W 2756/10 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
non-transitory memory storing processor-executable instructions that, when executed by the one or more processors, cause the system to perform actions including:
receiving, from a planning component of an autonomous vehicle, a planned trajectory for the autonomous vehicle to traverse an environment;
receiving, from a prediction component of the autonomous vehicle, a predicted trajectory for an object in the environment;
determining a planned position for the autonomous vehicle along the planned trajectory at a future time;
determining a vehicle probability function for the autonomous vehicle at the future time, the vehicle probability function representing a positional uncertainty associated with the planned position;
determining a predicted position for the object along the predicted trajectory at the future time;
determining an object probability function for the object at the future time, the object probability function representing a positional uncertainty associated with the predicted position;
combining the vehicle probability function and the object probability function into a combined probability function, the combined probability function representing a total positional uncertainty between the planned position and the predicted position;
determining a relative position based at least in part on the planned position and the predicted position;
determining a value from the combined probability function based at least in part on the relative position, the value representing a probability of collision between the autonomous vehicle and the object at the at least one future time;
determining a further value based at least in part on a further planned position for the autonomous vehicle along the planned trajectory, the further value representing a probability of collision associated with the further planned position;
determining a cost value based at least in part on the value and the further value; and
controlling the autonomous vehicle based at least in part on the cost value.