US 11,809,193 B2
Data-driven control for autonomous driving
Yujia Wu, San Diego, CA (US); Zijie Xuan, San Diego, CA (US); and Arda Kurt, San Diego, CA (US)
Assigned to TUSIMPLE, INC., San Diego, CA (US)
Filed by TUSIMPLE, INC., San Diego, CA (US)
Filed on Jul. 21, 2020, as Appl. No. 16/934,989.
Prior Publication US 2022/0026912 A1, Jan. 27, 2022
Int. Cl. G05D 1/02 (2020.01)
CPC G05D 1/0221 (2013.01) [G05D 1/0219 (2013.01); G05D 1/0246 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method of obtaining a data-driven model for autonomous driving, the method comprising:
obtaining a first set of data associated with a first set of variables that characterize movements of an autonomous vehicle over time and commands provided to the autonomous vehicle over time;
determining, using a first matrix based on at least the first set of data, non-zero values and an associated second set of variables that describe a control model used to perform an autonomous driving operation of the autonomous vehicle;
calculating values for a feedback controller that describes a transfer function used to perform the autonomous driving operation of the autonomous vehicle driven on a road, wherein the values for the feedback controller are based on at least the non-zero values of the control model and a measured disturbance value that describes a driving related disturbance experienced by the autonomous vehicle;
outputting, by the feedback controller operated in the autonomous vehicle, an acceleration command and a steering command for the autonomous vehicle based on the values for the feedback controller and based on a longitudinal velocity, a lateral velocity, a yaw rate, and an angular velocity sensed by sensors on the autonomous vehicle; and
causing a steering motor and an engine of the autonomous vehicle to actuate to perform the autonomous driving operation by sending the steering command to the steering motor and the acceleration command to the engine.