US 11,654,934 B2
Methods and systems for diversity-aware vehicle motion prediction via latent semantic sampling
Xin Huang, Cambridge, MA (US); Stephen G. McGill, Broomall, PA (US); Jonathan A. DeCastro, Arlington, MA (US); Brian C. Williams, Cambridge, MA (US); Luke S. Fletcher, Cambridge, MA (US); John J. Leonard, Newton, MA (US); and Guy Rosman, Newton, PA (US)
Assigned to TOYOTA RESEARCH INSTITUTE, INC., Los Altos, CA (US); and MASSACHUSETTS INSTITUTE OF TECHNOLOGY, Cambridge, MA (US)
Filed by Toyota Research Institute, Inc., Los Altos, CA (US); and Massachusetts Institute of Technology, Cambridge, MA (US)
Filed on Nov. 25, 2020, as Appl. No. 17/104,355.
Claims priority of provisional application 62/941,214, filed on Nov. 27, 2019.
Prior Publication US 2021/0163038 A1, Jun. 3, 2021
Int. Cl. G06N 3/08 (2023.01); G06V 20/58 (2022.01); G06V 10/82 (2022.01); G06V 20/52 (2022.01); B60W 60/00 (2020.01); G06V 20/40 (2022.01); G06F 18/214 (2023.01)
CPC B60W 60/0011 (2020.02) [B60W 60/001 (2020.02); G06F 18/2148 (2023.01); G06N 3/08 (2013.01); G06V 10/82 (2022.01); G06V 20/41 (2022.01); G06V 20/52 (2022.01); G06V 20/58 (2022.01); B60W 2420/403 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating a predicted vehicle trajectory comprising:
receiving a trajectory vector of a target vehicle;
generating a set of latent state vectors using the received trajectory vector and an artificial neural network, wherein the latent state vectors each comprise a high-level representation, ZH, correlated to an annotation coding representing semantic categories of vehicle trajectories;
selecting a subset, from the set of latent state vectors, using farthest point sampling;
generating a predicted vehicle trajectory based on the subset of latent state vectors; and
controlling a vehicle based on the predicted vehicle trajectory.