Zoox, Inc.

Matthew Van Heukelom

Marin Kobilarov

Timothy Caldwell

Lichao Ma

Chonhyon Park

William Anthony Silva

Kai Zhenyu Wang

Jefferson Bradfield Packer

Rasmus Fonseca

Tencia Lee

Arian Houshmand

Xianan Huang

Cheng Peng

Alexander Ivanov Ivanov

A vehicle with a planning system may generate a set of candidate trajectories for controlling the vehicle. The planning system may receive sensor data from sensors. The planning system may determine, based at least in part on the sensor data, environmental data, and/or the vehicle data. The planning system may determine, based at least in part on the environmental data and/or the vehicle data, a set of candidate trajectories corresponding to a set of contemporaneous candidate actions for the vehicle to follow. An individual candidate trajectory in the set is determined by dynamically shifting the individual candidate trajectory by a lateral distance relative to the vehicle or a lane in the environment. A candidate action may indicate a position, orientation, velocity, acceleration, or the like for the vehicle to track to by a certain time or distance.

Dynamic, diverse, and computationally efficient vehicle candidate action generation

Techniques for accurately predicting and avoiding collisions with objects detected in an environment of a vehicle are discussed herein. A vehicle computing device can implement a model to output data indicating costs for potential intersection points between the object and the vehicle in the future. The model may employ a control policy and a time-step integrator to determine whether an object may intersect with the vehicle, in which case the techniques may include predicting vehicle actions by the vehicle computing device to control the vehicle.

Active prediction based on object trajectories

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

Techniques described herein are directed to classifying lanes in an environment of a vehicle for, for example, performing lane handling. In an example, system(s) of a vehicle can determine a signal indicative of a presence of the vehicle in a lane of a drivable surface in an environment within which the vehicle is located. The system(s) can determine, based at least in part on the signal, a classification of the lane as at least one of occupied (an object is at least partially in the lane), unoccupied (no object in the lane), and/or established (e.g., where an object has established a priority in the lane). The system(s) can control the vehicle based at least in part on the classification of the lane to improve safety in scenarios, for example, including merging.

Lane classification for improved vehicle handling

Techniques for determining an uncertainty metric associated with an object in an environment can include determining the object in the environment and a set of candidate trajectories associated with the object. Further, a vehicle, such as an autonomous vehicle, can be controlled based at least in part on the uncertainty metric. The vehicle can determine a traversed trajectory associated with the object and determine a difference between the traversed trajectory and the set of candidate trajectories. Based on the difference, the vehicle can determine an uncertainty metric associated with the object. In some instances, the vehicle can input the traversed trajectory and the set of candidate trajectories to a machine-learned model that can output the uncertainty metric.

Object uncertainty detection

Techniques described herein relate to lane handling, for instance to enable vehicles to perform turns without colliding into oncoming vehicles and/or bicycles in other lanes. System(s) associated with a vehicle can access sensor data and/or map data associated with an environment within which the vehicle is positioned in a first lane. The system(s) can determine that the vehicle is to perform a turn and a start of a second lane associated with the turn or a merging zone associated with the second lane. The system(s) can determine a location of the vehicle relative to the start of the second lane or the merging zone associated with the second lane and, based partly on the location, can cause the vehicle to merge into the second lane prior to performing the turn.

Lane handling for merge prior to turn

Techniques are discussed for evaluating trajectories based on risk associated with the trajectories with respect to predicted locations of objects in an environment. A vehicle can capture sensor data of an environment, which may include object(s) separate from the vehicle, such as another vehicle or a pedestrian. A prediction system can output a discretized probability distribution comprising prediction probabilities associated with possible locations of the object in the future. Heat maps, as an example discretized probability distribution, can represent one or more objects. Trajectories can be generated for the vehicle to follow in the environment. An overlap between a region of the vehicle along a trajectory and the heat map can be determined, and a probability associated with the overlap can represent a risk associated with a trajectory navigating through the environment. The vehicle can be controlled based on risks associated with the various trajectories.

Growing community of inventors

San Francisco, CA, United States of America

Matthew Van Heukelom