Policy Learning for Nonlinear Model Predictive Control with Application to USVs

TL;DR

This paper introduces a deep neural network-based policy learning approach for nonlinear model predictive control (NMPC) to enable high-speed, real-time control of unmanned surface vehicles (USVs), overcoming traditional computational limitations.

Contribution

It develops a novel policy learning MPC method using deep neural networks, ensuring stability and practical feasibility for high-frequency USV motion control.

Findings

Achieved control at up to 5 Hz sampling rate with high precision.

Proved asymptotic stability of the closed-loop system.

Successfully applied to USV motion control in real experiments.

Abstract

The unaffordable computation load of nonlinear model predictive control (NMPC) has prevented it for being used in robots with high sampling rates for decades. This paper is concerned with the policy learning problem for nonlinear MPC with system constraints, and its applications to unmanned surface vehicles (USVs), where the nonlinear MPC policy is learned offline and deployed online to resolve the computational complexity issue. A deep neural networks (DNN) based policy learning MPC (PL-MPC) method is proposed to avoid solving nonlinear optimal control problems online. The detailed policy learning method is developed and the PL-MPC algorithm is designed. The strategy to ensure the practical feasibility of policy implementation is proposed, and it is theoretically proved that the closed-loop system under the proposed method is asymptotically stable in probability. In addition, we apply the PL-MPC algorithm successfully to the motion control of USVs. It is shown that the proposed algorithm can be implemented at a sampling rate up to $5 Hz$ with high-precision motion control. The experiment video is available via:\url{https://v.youku.com/v_show/id_XNTkwMTM0NzM5Ng==.html