Zoox, Inc.

Arian Houshmand

Ravi Verma Gogna

Marin Kobilarov

Timothy Caldwell

Paul Orecchio

Mark Jonathon McClelland

Lichao Ma

Matthew Van Heukelom

Rasmus Fonseca

Chonhyon Park

Xianan Huang

Cheng Peng

Techniques for validating and correcting teleoperation signals for an autonomous vehicle are described herein. In some examples, a system may receive, from a remote computing device, an instruction to stop movement of an autonomous. The system may determine, based at least in part on map data, that the instruction is associated with stopping the autonomous vehicle in a non-stopping area. In response to determining that the instruction is associated with stopping the autonomous vehicle in the non-stopping area, the system may determine to continue movement of the autonomous vehicle beyond the no-stopping area. The system may further identify a stopping location that is at least partially outside of the no-stopping area and control the autonomous vehicle to instead stop at the stopping location.

Validating stopping behaviors of a vehicle

A teleoperations system that collaboratively works with an autonomous vehicle planning component to generate a path for controlling the autonomous vehicle to pass a situation where the vehicle is unable to identify a vehicle option to proceed and may comprise presenting one or more paths to a teleoperator (e.g., a human user, machine-learned model, and/or artificial intelligence component), such paths being generated either at the vehicle or remote system. The teleoperations system may receive input from the teleoperator indicating a vehicle option to select for the vehicle to proceed in the environment. The teleoperations system may generate a guidance path based on the vehicle options and the input and transmit the guidance path to the autonomous vehicle. Based at least in part on the guidance path, the autonomous vehicle may generate a control trajectory to use to navigate around the obstacle.

Collaborative action ambiguity resolution for autonomous vehicles

Trajectory generation for controlling motion or other behavior of an autonomous vehicle may include alternately determining a candidate action and predicting a future state based on that candidate action. The technique may include determining a cost associated with the candidate action that may include an estimation of a transition cost from a current or former state to a next state of the vehicle. This cost estimate may be a lower bound cost or an upper bound cost and the tree search may alternately apply the lower bound cost or upper bound cost exclusively or according to a ratio or changing ratio. The prediction of the future state may be based at least in part on a machine-learned model's classification of a dynamic object as being a reactive object or a passive object, which may change how the dynamic object is modeled for the prediction.

Vehicle trajectory control using a tree search

A teleoperations system that collaboratively works with an autonomous vehicle guidance system to generate a path for controlling the autonomous vehicle may comprise generating one or more trajectories at the teleoperations system based at least in part on environment data received from the autonomous vehicle and presenting the one or more trajectories to a teleoperator (e.g., a human user, machine-learned model, or artificial intelligence component). A selection of one of the trajectories may be received at the teleoperations system and transmitted to the autonomous vehicle. The one or more trajectories may be generated at the teleoperations system and/or received from the autonomous vehicle. Regardless, the autonomous vehicle may generate a control trajectory based on the trajectory received from teleoperations, instead of merely implementing the trajectory from the teleoperations system.

Collaborative vehicle path generation

Growing community of inventors

Mountain View, CA, United States of America

Arian Houshmand