US 11,926,347 B2
Conditional agent trajectory prediction
Reza Mahjourian, Austin, TX (US); Carlton Macdonald Downey, Mountain View, CA (US); Benjamin Sapp, Marina del Rey, CA (US); Dragomir Anguelov, San Francisco, CA (US); and Ekaterina Igorevna Tolstaya, Voorhees, NJ (US)
Assigned to Waymo LLC, Mountain View, CA (US)
Filed by Waymo LLC, Mountain View, CA (US)
Filed on Oct. 29, 2021, as Appl. No. 17/514,259.
Claims priority of provisional application 63/108,249, filed on Oct. 30, 2020.
Prior Publication US 2022/0135086 A1, May 5, 2022
Int. Cl. B60W 60/00 (2020.01); G06N 3/045 (2023.01)
CPC B60W 60/00272 (2020.02) [B60W 60/00274 (2020.02); G06N 3/045 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method performed by one or more computers, the method comprising:
obtaining context data characterizing an environment, the context data comprising data characterizing a plurality of agents in the environment at a current time point, the plurality of agents comprising a query agent and a set of one or more target agents, and the context data comprising data characterizing trajectories of each of the plurality of agents up to the current time point;
obtaining data identifying a planned future trajectory for the query agent after the current time point; and
for each target agent in the set, processing the context data and the data identifying the planned future trajectory using a first neural network to generate a conditional trajectory prediction output that defines a conditional probability distribution over possible future trajectories of the target agent after the current time point given that the query agent follows the planned future trajectory for the query agent after the current time point.