Zoox, Inc.

Joseph Lorenzetti

Linjun Zhang

Timothy Caldwell

Yunpeng Pan

Xianan Huang

Ke Sun

Shahriar Sefati

Anjali Lakshmi Pemmaraju

There are provided techniques including a system, method, and computer-readable medium for autonomous vehicle control based on a probability of collision. The method may include the steps of: receiving a vehicle trajectory associated with a vehicle and an object trajectory associated with an object, determining a vehicle probability distribution associated with the vehicle at a first time along the vehicle trajectory and an object probability distribution associated with the object at the first time along the object trajectory, determining a combined probability distribution based on the vehicle and object probability distributions, determining a relative position between the vehicle and the object at the first time based on the vehicle and object positions, determining a probability value based on the combined probability distribution and the relative position, and controlling the vehicle based on the probability value.

Autonomous vehicle control based on a probability of collision

Techniques for determining a vehicle trajectory that causes a vehicle to navigate in an environment relative to one or more objects are described herein. For example, the techniques may include a computing device determining a decision tree having nodes to represent different object intents and/or nodes to represent vehicle actions at a future time. A tree search algorithm can search the decision tree to evaluate potential interactions between the vehicle and the one or more objects over a time period, and output a vehicle trajectory for the vehicle. The vehicle trajectory can be sent to a vehicle computing device for consideration during vehicle planning, which may include simulation.

Trajectory prediction based on a decision tree

Growing community of inventors

Foster City, CA, United States of America

Joseph Lorenzetti