Zoox, Inc.

Julia A Wyatt

Gerrit Bagschik

Sy Kelly Olson

Kshitij Agarwal

Thomas Bernard Gacka

Pengzhi Tian

Techniques are discussed herein for generating and evaluating autonomous vehicle control systems. In examples, a driving scenario is determined and log data, e.g., generated from user-supported vehicles travelling in an environment, may be used to determine instances in which vehicles experience the driving scenario. Based on the log data, an exposure metric, a severity metric, and/or a controllability metric may be determined. A safety goal can be determined from the metric(s) and vehicle control parameters are determined to comport with the safety goal. The vehicle control parameters may be used to control an autonomous vehicle in the environment.

Safe vehicle operation using log data

Techniques for determining a safety metric associated with a vehicle controller are discussed herein. The safety metric may be reflective of one or more severity scores associated with a collision simulated by simulating performance of the vehicle controller. The techniques may include determining a simulation scenario, simulating the scenario by simulating a component of an autonomous vehicle, and determining simulation data describing a collision occurring between the simulated autonomous vehicle and an object in the scenario. The simulation data is used to determine a severity score for the collision that may be used to refine the component of the autonomous vehicle system and/or validate the component for safe operation.

Growing community of inventors

Sudbury, MA, United States of America

Julia A Wyatt