US 12,296,857 B2
Path-based trajectory prediction
Sepideh Afshar, Cambridge, MA (US); Akshay Bhagat, Pittsburgh, PA (US); Lu Lu, Upton, MA (US); Balarama Raju Buddharaju, Pittsburgh, PA (US); and Henggang Cui, Allison Park, PA (US)
Assigned to Motional AD LLC, Boston, MA (US)
Filed by Motional AD LLC, Boston, MA (US)
Filed on Dec. 20, 2022, as Appl. No. 18/085,516.
Claims priority of provisional application 63/424,814, filed on Nov. 11, 2022.
Claims priority of provisional application 63/416,476, filed on Oct. 14, 2022.
Prior Publication US 2024/0132112 A1, Apr. 25, 2024
Int. Cl. B60W 60/00 (2020.01); G01C 21/32 (2006.01)
CPC B60W 60/0027 (2020.02) [G01C 21/32 (2013.01); B60W 2554/4041 (2020.02); B60W 2554/4042 (2020.02); B60W 2554/4046 (2020.02); B60W 2556/10 (2020.02); B60W 2556/40 (2020.02)] 19 Claims
OG exemplary drawing
 
1. A method, comprising:
obtaining, by at least one processor, information about one or more agents in a portion of an environment where a vehicle is operating, the information comprising data associated with locations of the one or more agents in the portion of the environment;
for at least one agent of the one or more agents,
determining, by the at least one processor, a reference path for the agent based on a location of the agent in the environment,
transforming, by the at least one processor, information corresponding to the reference path from a Cartesian coordinate system to a path relative frame that is based on the reference path,
predicting, by the at least one processor, a future trajectory of the at least one agent in the path relative frame based on the reference path, and
transforming, by the at least one processor, the future trajectory of the at least one agent from the path relative frame back to the Cartesian coordinate system; and
controlling the vehicle to operate based on one or more predicted future trajectories of the at least one agent of the one or more agents.