Zoox, Inc.

Brian Michael Filarsky

Joseph Funke

Mark Jonathon McClelland

Olivier Toupet

Shayan Darayan

Taylor Scott Clawson

Amirhossein Tamjidi

Collision avoidance and error determination for a component of an autonomous vehicle comprising receiving a first trajectory, such as to return a vehicle to an intended trajectory, that a vehicle is predicted to follow, based on an offset between the vehicle and a second trajectory associated with the vehicle, such as a reference trajectory. The first trajectory predicts a first movement characteristic (e.g., a position) of the vehicle at a point in time. A second movement characteristic is received, representing an actual movement characteristic of the vehicle at that point in time. A first error between the first and second movement characteristics is determined. Based at least in part on the first error, performance of a model for generating trajectories that a vehicle is predicted to follow is validated.

Tracker trajectory validation

Methods of processing trajectories, such as for autonomous vehicles, are provided. A method may comprise receiving a trajectory and identifying a first mode or a second mode as a control mode for controlling the vehicle. The first mode comprises determining a first control value based at least in part on a time and controlling the vehicle based at least in part on the first control value. The second mode comprises determining a second control value for the vehicle based at least in part on a position of the vehicle and controlling the vehicle based at least in part on the second control value. The vehicle may be controlled in accordance with the identified control mode. In some examples the vehicle may be controlled in accordance with the first mode at a first time, and the second mode at a second time.

Processing trajectories

Techniques for validating operation of vehicle safety system components are discussed herein. Vehicle log data processed by components of secondary systems of vehicles traversing an environment can be received which may include event metrics or be indicative of events (such as an implementation of a safety response). Such metrics may be defined by algorithm output continuity data, algorithm output feasibility data, and/or algorithm output tracking data. The log data can be utilized to test candidate safety systems to determine test event metrics. Validation of the candidate safety system components can be performed based on aggregated event metrics (such as aggregated over a fleet) meeting various criteria.

Safety component validation and update management

Techniques are described for determining to modify a coordinate system in response to the occurrence of a condition. As non-limiting examples, such conditions comprise distance traveled, speed of the vehicle (or system), an amount of computational resources available, a time since the last change, a number of objects present, the presence (or absence) of a particular object proximate the vehicle, a distance to a proximate object, based on a particular frequency, or the like. Such modifications may improve the operation and safety of a computing system used for path planning and trajectory generation by allowing lower precision numerical representations to be used in safety-critical situations while avoiding potential computational errors that would otherwise result from using such a representation.

Growing community of inventors

San Francisco, CA, United States of America

Brian Michael Filarsky