公开(公告)号：US20250121857A1

公开(公告)日：2025-04-17

申请号：US18913074

申请日：2024-10-11

Applicant: Waymo LLC

Inventor： Bertrand Robert Douillard ,  Aurick Qikun Zhou ,  Rami Al-Rfou ,  Kratarth Goel ,  Benjamin Sapp ,  Andre Liang Cornman ,  Cheolho Park ,  Lingyun Liu

IPC: B60W60/00 ,  B60W50/00 ,  G06F30/15

Abstract: A method performed by one or more computers, the method comprising: obtaining scene context data characterizing a scene in an environment at a current time point, wherein the scene context data includes features of the scene in a scene-centric coordinate system; generating a scene-centric encoded representation of the scene in the environment by processing the scene context data using an encoder neural network; for each target agent: obtaining agent-specific features for the target agent, processing the agent-specific features for the target agent and the scene-centric encoded representation of the scene using a fusion neural network to generate a fused scene representation for the target agent, and processing the fused scene representation for the target agent using a decoder neural network to generate a trajectory prediction output for the target agent in an agent-centric coordinate system for the target agent.

公开(公告)号：US20230406360A1

公开(公告)日：2023-12-21

申请号：US18335915

申请日：2023-06-15

Applicant: Waymo LLC

Inventor： Rami Al-Rfou ,  Nigamaa Nayakanti ,  Kratarth Goel ,  Aurick Qikun Zhou ,  Benjamin Sapp ,  Khaled Refaat

IPC: B60W60/00 ,  B60W40/06 ,  B60W40/04 ,  G06N3/0455

CPC classification number: B60W60/0027 ,  B60W40/06 ,  B60W2556/10 ,  G06N3/0455 ,  B60W40/04

Abstract: Methods, systems, and apparatus for generating trajectory predictions for one or more target agents. In one aspect, a system comprises one or more computers configured to obtain scene context data characterizing a scene in an environment at a current time point, where the scene includes multiple agents that include a target agent and one or more context agents, and the scene context data includes respective context data for each of multiple different modalities of context data. The one or more computers then generate an encoded representation of the scene in the environment that includes one or more embeddings and process the encoded representation of the scene context data using a decoder neural network to generate a trajectory prediction output for the target agent that predicts a future trajectory of the target after the current time point.