US 12,448,006 B2
Predicting and controlling object crossings on vehicle routes
Henggang Cui, Allison Park, PA (US)
Assigned to Motional AD LLC, Boston, MA (US)
Filed by Motional AD LLC, Boston, MA (US)
Filed on Mar. 25, 2022, as Appl. No. 17/705,035.
Prior Publication US 2023/0303124 A1, Sep. 28, 2023
Int. Cl. B60W 60/00 (2020.01); B60W 50/00 (2006.01); G05B 13/02 (2006.01)
CPC B60W 60/0027 (2020.02) [B60W 50/0097 (2013.01); G05B 13/0265 (2013.01); B60W 2050/0028 (2013.01); B60W 2420/403 (2013.01); B60W 2420/408 (2024.01); B60W 2554/4041 (2020.02); B60W 2556/50 (2020.02); B60W 2720/10 (2013.01); B60W 2720/24 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving sensor information indicating at least one object surrounding a vehicle;
determining a future position of the vehicle based on at least a first trajectory of the vehicle;
determining a future position of the at least one object based on a second trajectory of the at least one object, wherein the second trajectory of the at least one object crosses the first trajectory of the vehicle or yields to the vehicle;
determining a vehicle control based on the future position of the vehicle, the future position of the at least one object, and a determination of the second trajectory of the at least one object crossing the first trajectory of the vehicle or yielding to the vehicle;
training at least one model to predict trajectories of vehicles and objects comprising a likelihood of an object trajectory crossing a vehicle trajectory, wherein the at least one model is trained based on the vehicle control, the first trajectory of the vehicle, and the second trajectory of the at least one object, wherein false object crossings are filtered from the first trajectory of the vehicle and the second trajectory of the at least one object; and
controlling an autonomous vehicle based on an output of the trained at least one model.