公开(公告)号：US20220383076A1

公开(公告)日：2022-12-01

申请号：US17828778

申请日：2022-05-31

Applicant: Google LLC

Inventor： Jonathon Shlens ,  Vijay Vasudevan ,  Jiquan Ngiam ,  Benjamin James Caine ,  Zhengdong Zhang ,  Zhifeng Chen ,  Hao-Tien Chiang ,  David Joseph Weiss ,  Jeffrey Ling ,  Ashish Venugopal

IPC: G06N3/04

Abstract: A method for performing one or more tasks, wherein each of the one or more tasks includes predicting behavior of one or more agents in an environment, the method comprising: obtaining a three-dimensional (3D) input tensor representing behaviors of the one or more agents in the environment across a plurality of time steps; generating an encoded representation of the 3D input tensor by processing the 3D input tensor using an encoder neural network, wherein 3D input tensor comprises a plurality of observed cells and a plurality of masked cells; and processing the encoded representation of the 3D input tensor using a decoder neural network to generate a 4D output tensor.