US 12,217,168 B2
Agent trajectory prediction using vectorized inputs
Jiyang Gao, San Jose, CA (US); Yi Shen, Sunnyvale, CA (US); Hang Zhao, Sunnyvale, CA (US); and Chen Sun, San Francisco, CA (US)
Assigned to Waymo LLC, Mountain View, CA (US)
Filed by Waymo LLC, Mountain View, CA (US)
Filed on Nov. 16, 2020, as Appl. No. 17/099,656.
Claims priority of provisional application 62/936,320, filed on Nov. 15, 2019.
Prior Publication US 2021/0150350 A1, May 20, 2021
Int. Cl. G06N 3/00 (2023.01); G01C 21/00 (2006.01); G06N 3/08 (2023.01); G05D 1/00 (2006.01)
CPC G06N 3/08 (2013.01) [G01C 21/3848 (2020.08); G05D 1/0088 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method performed by one or more computers, the method comprising:
receiving an input including (i) data characterizing observed trajectories for each of one or more agents in an environment and (ii) map features of a map of the environment;
generating a respective polyline of each of the observed trajectories that represents the observed trajectory as a sequence of one or more vectors, comprising generating a respective vector for each of one or more time intervals during the observed trajectory, wherein each respective vector includes features of the observed trajectory during the corresponding time interval;
generating a respective polyline of each of the features of the map that represents the feature as a sequence of one or more vectors;
processing a network input comprising the (i) respective polylines of the observed trajectories and (ii) the respective polylines of each of the features of the map using an encoder neural network to generate polyline features for each of the one or more agents;
for one or more of the agents, generating a predicted trajectory for the agent from the polyline features for the agent; and
controlling a movement of a vehicle based on the trajectories predicted for the one or more agents.