Zoox, Inc.

Rasmus Fonseca

Marin Kobilarov

Mark Jonathon McClelland

Timothy Caldwell

Jack Riley

Kai Zhenyu Wang

Gowtham Garimella

Jefferson Bradfield Packer

Andrew Scott Crego

Mahsa Ghafarianzadeh

Lichao Ma

Matthew Van Heukelom

Adrian Michael Costantino

Chonhyon Park

Arian Houshmand

Yunpeng Pan

Xianan Huang

Liam Gallagher

Muhammad Farooq Rama

Lingfeng Zhang

Cheng Peng

Techniques for representing sensor data and predicted behavior of various objects in an environment are described herein. For example, an autonomous vehicle can represent prediction probabilities as an uncertainty model that may be used to detect potential collisions, define a safe operational zone or drivable area, and to make operational decisions in a computationally efficient manner. The uncertainty model may represent a probability that regions within the environment are occupied using a heat map type approach in which various intensities of the heat map represent a likelihood of a corresponding physical region being occupied at a given point in time.

Object uncertainty models to assist with drivable area determinations

The techniques discussed herein may comprise an autonomous vehicle guidance system that generates a group of candidate trajectories based at least in part on sensor data. This group of candidate trajectories is clustered into two or more clusters and one or more representative trajectories may be determined for each cluster. The representative trajectory may be one of the trajectories in the cluster or a separately determined trajectory that represents the trajectories in a cluster, such as a mean or median trajectory. The representative trajectory may be used to predict how a dynamic object would react to the representative trajectory. This prediction may be used to determine potentially different costs associated with the different trajectories of the cluster with which the representative trajectory is associated. These costs may include costs to induce following behavior by the autonomous vehicle and/or cost(s) associated with conditionally available roadway portions.

Vehicle control using trajectory clustering and reactive prediction

Techniques for generating more accurate determinations of object proximity by using vectors in data structures based on vehicle sensor data are disclosed. Vectors reflecting a distance and direction to a nearest object edge from a reference point in a data structure are used to determine a distance and direction from a point of interest in an environment to a nearest surface. In some examples, a weighted average query point response vector is determined using the determined distance vectors of cells neighboring the cell in which the point of interest is located and nearest to the same object as the query point, providing a more accurate estimate of the distance to the nearest object from the point of interest.

Distance representation and encoding

Object uncertainty models

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 for modeling the probability distribution of errors in perception systems are discussed herein. For example, techniques may include modeling error distribution for attributes such as position, size, pose, and velocity of objects detected in an environment, and training a mixture model to output specific error probability distributions based on input features such as object classification, distance to the object, and occlusion. The output of the trained model may be used to control the operation of a vehicle in an environment, generate simulations, perform collision probability analyses, and to mine log data to detect collision risks.

Perception error modeling

A vehicle computing system may implement techniques to determine an action for a vehicle to take based on a cost associated therewith. The cost may be based in part on the effect of the action on an object (e.g., another vehicle, bicyclist, pedestrian, etc.) operating in the environment. The vehicle computing system may detect the object based on sensor data and determine an object trajectory based on a predicted reaction of the object to the vehicle performing the action. The vehicle computing system may determine costs associated with safety, comfort, progress, and/or operating rules for each action the vehicle could take based on the action and/or the predicted object trajectory. In some examples, the lowest cost action may be selected for the vehicle to perform.

Cost-based path determination

Growing community of inventors

Boulder Creek, CA, United States of America

Rasmus Fonseca