Jump to content

Waymo llc (20250121857). BEHAVIOR PREDICTION USING SCENE-CENTRIC REPRESENTATIONS

From WikiPatents

BEHAVIOR PREDICTION USING SCENE-CENTRIC REPRESENTATIONS

Organization Name

waymo llc

Inventor(s)

Bertrand Robert Douillard of San Francisco CA US

Aurick Qikun Zhou of San Francisco CA US

Rami Al-rfou of Menlo Park CA US

Kratarth Goel of Fremont CA US

Benjamin Sapp of Marina del Rey CA US

Andre Liang Cornman of San Francisco CA US

Cheolho Park of Palo Alto CA US

Lingyun Liu of Sunnyvale CA US

BEHAVIOR PREDICTION USING SCENE-CENTRIC REPRESENTATIONS

This abstract first appeared for US patent application 20250121857 titled 'BEHAVIOR PREDICTION USING SCENE-CENTRIC REPRESENTATIONS

Original Abstract Submitted

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.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.