US 12,330,689 B2
Predicting agent trajectories
Nachiket Deo, San Diego, CA (US); Oscar Olof Beijbom, Santa Monica, CA (US); and Eric Wolff, Boston, MA (US)
Assigned to Motional AD LLC, Boston, MA (US)
Filed by Motional AD LLC, Boston, MA (US)
Filed on Apr. 22, 2022, as Appl. No. 17/727,617.
Claims priority of provisional application 63/179,169, filed on Apr. 23, 2021.
Prior Publication US 2022/0355825 A1, Nov. 10, 2022
Int. Cl. B60W 60/00 (2020.01); B60W 50/00 (2006.01); G06N 3/08 (2023.01)
CPC B60W 60/0027 (2020.02) [B60W 50/0097 (2013.01); G06N 3/08 (2013.01); B60W 2050/0022 (2013.01); B60W 2556/40 (2020.02)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
generating, using at least one processor, a graph corresponding to a map of a scene by encoding map features and agent features as node encodings of the graph;
determining, using the at least one processor, a policy for application to outgoing edges at nodes of the graph;
sampling, using the at least one processor, paths for a target vehicle in the scene according to the policy;
predicting, using the at least one processor, a set of trajectories based on the sampled paths traversed by the policy and a sampled latent variable; and
operating, using the at least one processor, a vehicle based on the set of trajectories of the target vehicle,
wherein predicting the set of trajectories comprises:
outputting a context vector for the policy using a multi-head attention layer; and
combining the context vector with motion encodings and the sampled latent variable to predict the set of trajectories.