US 12,291,233 B2
System and method for providing accurate trajectory following for automated vehicles in dynamic environments
Huckleberry Febbo, Los Gatos, CA (US); and David Francis Isele, Sunnyvale, CA (US)
Assigned to Honda Motor Co., Ltd., Tokyo (JP)
Filed by Honda Motor Co., Ltd., Tokyo (JP)
Filed on Jul. 15, 2020, as Appl. No. 16/929,313.
Claims priority of provisional application 62/907,328, filed on Sep. 27, 2019.
Prior Publication US 2021/0094569 A1, Apr. 1, 2021
Int. Cl. B60W 60/00 (2020.01); G01S 17/89 (2020.01); G05D 1/00 (2006.01); G05D 1/02 (2020.01); G06K 9/00 (2022.01); G06V 20/58 (2022.01)
CPC B60W 60/0011 (2020.02) [G01S 17/89 (2013.01); G05D 1/0212 (2013.01); G05D 1/024 (2013.01); G06V 20/58 (2022.01); B60W 2554/20 (2020.02); B60W 2554/40 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for providing accurate trajectory following for automated vehicles in dynamic environments comprising:
receiving image data and LiDAR data associated with a dynamic environment of a vehicle;
processing a planned trajectory of the vehicle that is based on an analysis of the image data and LiDAR data; and
communicating control signals associated with following the planned trajectory and autonomously controlling the vehicle to follow the planned trajectory to navigate within the dynamic environment to reach a goal based on the control signals, wherein a predictive optimal control problem is executed to determine the control signals that are to be communicated to autonomously control the vehicle to follow the planned trajectory, while minimizing a time to reach the goal, wherein a prediction horizon of the predictive optimal control problem is used to set a longer prediction horizon associated with processing the planned trajectory such that the longer prediction horizon associated with processing the planned trajectory is longer than the prediction horizon of the predictive optimal control problem,
wherein the predictive optimal control problem determines the control signals based on a current trajectory state and a next trajectory state of the planned trajectory and further based at least in part on an associated control trajectory state determined in conjunction with the planned trajectory prior to execution of the predictive optimal control problem,
wherein the associated control trajectory state operates as a constant reference control trajectory between trajectory states providing a fixed reference for determining the control signals that guide the vehicle from the current trajectory state to the next trajectory state, and
wherein the predictive optimal control problem determines the control signals to follow the planned trajectory within the dynamic environment based at least in part on one or more of a width of the vehicle, a height of the vehicle, a weight of the vehicle, and a current transmission gear of the vehicle.