US 12,441,363 B2
Encoding homotopy constraints in spatio-temporal grids
Thomas Koelbaek Jespersen, Singapore (SG); Juraj Kabzan, Singapore (SG); Marc Dominik Heim, Singapore (SG); and Boaz Cornelis Floor, Singapore (SG)
Assigned to Motional AD LLC, Boston, MA (US)
Filed by Motional AD LLC, Boston, MA (US)
Filed on Nov. 24, 2021, as Appl. No. 17/535,542.
Prior Publication US 2023/0159054 A1, May 25, 2023
Int. Cl. B60W 60/00 (2020.01); B60W 40/10 (2012.01)
CPC B60W 60/0011 (2020.02) [B60W 40/10 (2013.01); B60W 60/0013 (2020.02); B60W 60/0015 (2020.02); B60W 60/0027 (2020.02)] 29 Claims
OG exemplary drawing
 
1. A method comprising:
determining, with at least one processor, a plurality of dynamic homotopy constraints associated with a scenario involving a vehicle in an environment;
embedding, with the at least one processor, the plurality of dynamic homotopy constraints in a plurality of continuously-differentiable, spatio-temporal grids a plurality of times for each timestep of a prediction horizon, where each spatio-temporal grid includes individual grids for each timestep of a prediction horizon;
generating, with the at least one processor, a plurality of trajectories based on the plurality of dynamic homotopy constraints embedded in the plurality of spatio-temporal grids;
selecting, with the at least one processor, a particular trajectory from among the plurality of trajectories generated; and
controlling, with a control circuit of the vehicle, the vehicle in the environment based on the particular trajectory selected from among the plurality of trajectories.