Waymo LLC

Leland Stanford Junior University

Xinwei Shi

Junhua Mao

Dragomir Dimitrov Anguelov

Yang Song

Brian A Hargreaves

Khaled Refaat

Congcong Li

Yin Zhou

Ruizhongtai Qi

Andre Liang Cornman

Zhishuai Zhang

Alexander Gorban

Jeonhyung Kang

Jingxiao Zheng

Ting Liu

Tian Lan

Jiachen Li

Jonathan Chandler Stroud

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for agent behavior prediction using keypoint data. One of the methods includes obtaining data characterizing a scene in an environment, the data comprising: (i) context data comprising data characterizing historical trajectories of a plurality of agents up to the current time point; and (ii) keypoint data for a target agent; processing the context data using a context data encoder neural network to generate a context embedding for the target agent; processing the keypoint data using a keypoint encoder neural network to generate a keypoint embedding for the target agent; generating a combined embedding for the target agent from the context embedding and the keypoint embedding; and processing the combined embedding using a decoder neural network to generate a behavior prediction output for the target agent that characterizes predicted behavior of the target agent after the current time point.

Pedestrian behavior prediction with 3D human keypoints

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for estimating a 3-D pose of an object of interest from image and point cloud data. In one aspect, a method includes obtaining an image of an environment; obtaining a point cloud of a three-dimensional region of the environment; generating a fused representation of the image and the point cloud; and processing the fused representation using a pose estimation neural network and in accordance with current values of a plurality of pose estimation network parameters to generate a pose estimation network output that specifies, for each of multiple keypoints, a respective estimated position in the three-dimensional region of the environment.

Multi-modal 3-D pose estimation

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium that determine yield behavior for an autonomous vehicle, and can include identifying an agent that is in a vicinity of an autonomous vehicle navigating through a scene at a current time point. Scene features can be obtained and can include features of (i) the agent and (ii) the autonomous vehicle. An input that can include the scene features can be processed using a first machine learning model that is configured to generate (i) a crossing intent prediction that includes a crossing intent score that represents a likelihood that the agent intends to cross a roadway in a future time window after the current time, and (ii) a crossing action prediction that includes a crossing action score that represents a likelihood that the agent will cross the roadway in the future time window after the current time.

Pedestrian crossing intent yielding

A method for magnetic resonance imaging reconstructs images that have reduced under-sampling artifacts from highly accelerated multi-spectral imaging acquisitions. The method includes performing by a magnetic resonance imaging (MRI) apparatus an accelerated multi-spectral imaging (MSI) acquisition within a field of view of the MRI apparatus, where the sampling trajectories of different spectral bins in the acquisition are different; and reconstructing bin images using neural network priors learned from training data as regularization to reduce under-sampling artifacts.

Deep learning based methods to accelerate multi-spectral imaging

A method for magnetic resonance imaging suppresses off-resonance gradient-induced image artifacts due to metal. The method includes performing by a magnetic resonance imaging (MRI) apparatus two multi-spectral imaging (MSI) acquisitions within a field of view of the MRI apparatus, where the two MSI acquisitions have alternating-sign readout gradients. The two MSI acquisitions are then processed and combined by the MRI apparatus using a weighted image combination to produce a final image.

Alternating gradients for metal-induced artifacts correction in magnetic resonance imaging

Growing community of inventors

Cupertino, CA, United States of America

Xinwei Shi