Waymo LLC

Zijian Guo

Jiyang Gao

Congcong Li

Dragomir Dimitrov Anguelov

Yu Ouyang

Yu Zhang

Vijay Vasudevan

Edward Stephen Walker, Jr

Jiquan Ngiam

Yin Zhou

Pei Sun

Yang Song

David Harrison Silver

Junhua Mao

Chi Yeung Jonathan Ng

Qichi Yang

Nichola Abdo

Andre Liang Cornman

Hsu-kuang Chiu

David Lee

Yuanfang Wang

Zhengli Zhao

Anthony Ronald Grue

Kevin Poulet

Xiaowei Li

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for open vehicle doors prediction using a neural network model. One of the methods includes: obtaining sensor data (i) that includes a portion of a point cloud generated by a laser sensor of an autonomous vehicle and (ii) that characterizes a vehicle that is in a vicinity of the autonomous vehicle in an environment; and processing the sensor data using an open door prediction neural network to generate an open door prediction that predicts a likelihood score that the vehicle has an open door.

Open vehicle doors prediction using a neural network model

Aspects of the disclosure provide for the identification of parkable areas. In one instance, observations of parked vehicles may be identified from logged data. The observations may be used to determine whether a sub-portion of an edge of a roadgraph corresponds to a parkable area. In some examples, the edge may define a drivable area in the roadgraph. In addition, map information is generated based on the determination of whether the sub-portion of the edge corresponds to the parkable area.

Identifying parkable areas for autonomous vehicles

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for searching an autonomous vehicle sensor data repository. One of the methods includes maintaining a collection of sensor samples and one or more embeddings of each sensor sample. Each sensor sample is generated from sensor data at multiple time steps and characterizes an environment at each of the multiple time steps. Each embedding corresponds to a respective portion of the sensor sample and has been generated by an embedding neural network. A query specifying a query portion of a query sensor sample is received. A query embedding corresponding to the query portion of the query sensor sample is generated through the embedding neural network. A plurality of relevant sensor samples that have embeddings that are closest to the query embedding are identified as characterizing similar scenarios to the query portion of the query sensor sample.

Searching an autonomous vehicle sensor data repository based on context embedding

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for searching an autonomous vehicle sensor data repository. One of the methods includes maintaining a collection of sensor samples and, for each sensor sample, an embedding of the sensor sample; receiving a request specifying a query sensor sample, wherein the query sensor sample characterizes a query environment region; and identifying, from the collection of sensor samples, a plurality of relevant sensor samples that characterize similar environment regions to the query environment region, comprising: processing the query sensor sample through the embedding neural network to generate a query embedding; and identifying, from sensor samples in a subset of the sensor samples in the collection, a plurality of sensor samples that have embeddings that are closest to the query embedding.

Searching an autonomous vehicle sensor data repository

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data using dynamic voxelization. When deployed within an on-board system of a vehicle, processing the point cloud data using dynamic voxelization can be used to make autonomous driving decisions for the vehicle with enhanced accuracy, for example by combining representations of point cloud data characterizing a scene from multiple views of the scene.

Processing point clouds using dynamic voxelization

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a spatio-temporal embedding of a sequence of point clouds. One of the methods includes obtaining a temporal sequence comprising a respective point cloud input corresponding to each of a plurality of time points, each point cloud input comprising point cloud data generated from sensor data captured by one or more sensors of a vehicle at the respective time point; processing each point cloud input using a first neural network to generate a respective spatial embedding that characterizes the point cloud input; and processing the spatial embeddings of the point cloud inputs using a second neural network to generate a spatio-temporal embedding that characterizes the point cloud inputs in the temporal sequence.

Spatio-temporal embeddings

Growing community of inventors

Sunnyvale, CA, United States of America

Zijian Guo