Learning-based Predictive Path Following Control for Nonlinear Systems Under Uncertain Disturbances

TL;DR

This paper introduces a learning-based predictive control framework combining high-level model predictive path following with low-level Gaussian Process-based disturbance learning for nonlinear robots, enhancing accuracy under uncertain disturbances.

Contribution

It proposes a novel hierarchical control scheme integrating model predictive control with Gaussian Process learning for disturbance compensation in nonlinear systems.

Findings

Effective disturbance learning with Gaussian Processes.

Improved path following accuracy in simulations.

Probabilistic stability guarantees for control scheme.

Abstract

Accurate path following is challenging for autonomous robots operating in uncertain environments. Adaptive and predictive control strategies are crucial for a nonlinear robotic system to achieve high-performance path following control. In this paper, we propose a novel learning-based predictive control scheme that couples a high-level model predictive path following controller (MPFC) with a low-level learning-based feedback linearization controller (LB-FBLC) for nonlinear systems under uncertain disturbances. The low-level LB-FBLC utilizes Gaussian Processes to learn the uncertain environmental disturbances online and tracks the reference state accurately with a probabilistic stability guarantee. Meanwhile, the high-level MPFC exploits the linearized system model augmented with a virtual linear path dynamics model to optimize the evolution of path reference targets, and provides the reference states and controls for the low-level LB-FBLC. Simulation results illustrate the effectiveness of the proposed control strategy on a quadrotor path following task under unknown wind disturbances.