Waymo LLC

Meta Platforms Technologies, LLC

Uatc, LLC

Tian Lan

Dragomir Dimitrov Anguelov

Khaled Refaat

Congcong Li

Galen Clark Haynes

Chen Sun

Junhua Mao

Jiyang Gao

Benjamin Sapp

Yuning Chai

Hang Zhao

Cordelia Luise Schmid

Xinwei Shi

Alexander David Styler

Yi Shen

Yue Shen

Zhishuai Zhang

Jeonhyung Kang

Mamta Jain

Jiachen Li

Jonathan Chandler Stroud

Andrew John Hardy Liebchen

Meekal Bajaj

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

A system obtains scene context data characterizing the environment. The scene context data includes data that characterizes a trajectory of an agent in a vicinity of a vehicle up to a current time point. The system identifies a plurality of initial target locations, and generates, for each of a plurality of target locations that each corresponds to one of the initial target locations, a respective predicted likelihood score that represents a likelihood that the target location will be an intended final location for a future trajectory of the agent. For each target location in a first subset of the target locations, the system generates a predicted future trajectory for the agent given that the target location is the intended final location for the future trajectory. The system further selects, as likely future trajectories of the agent, one or more of the predicted future trajectories.

Agent trajectory prediction using target locations

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

In one embodiment, a computing system may receive, from a first electronic device associated with a first user, a first request to generate a link associated with an artificial reality application and an action to be performed by the artificial reality application. The computing system may then generate a link to instructions that are executable on an artificial reality device to cause the artificial reality device to launch the artificial reality application and perform the action. The computing system may then receive, from a second electronic device associated with a second user, an indication that the second user activated the link on the second electronic device, and send the instructions associated with the link to an artificial reality device associated with the second user to cause the artificial reality device associated with the second user to launch the artificial reality application and perform the action.

Linking to social experiences in artificial reality environments

The disclosed computer-implemented method may include creating, by an artificial reality platform, a link configured to invite an invitee user to join an inviter user in an instance of an artificial reality application at a current location of the inviter user in the instance. The method may additionally include sharing the link, by the artificial reality platform, with the invitee user, and receiving, by the artificial reality platform, an indication of an activation of the link by the invitee user. The method may further include launching, by the artificial reality platform at least partly in response to receipt of the indication, the instance in an artificial reality device of the invitee user at the current location of the inviter user. Various other methods, systems, and computer-readable media are also disclosed.

Systems and methods for assisting users of artificial reality platforms

Growing community of inventors

Mountain View, CA, United States of America

Tian Lan