Safety enhancement for nonlinear systems via learning-based model predictive control with Gaussian process regression

Min Lin

doi:10.1016/j.neucom.2024.127706

Safety enhancement for nonlinear systems via learning-based model predictive control with Gaussian process regression

2024-07-01

1

PRE

AI

DOI：10.1016/j.neucom.2024.127706

Original

Original request for help

Save

Abstract

En 中文

This paper proposes a novel safe Gaussian process model predictive control scheme for discrete -time nonlinear systems subject to additive uncertainties. The scheme is implemented using an online learning framework that provides safety guarantees based on a nominal model, and employs Gaussian process regression (GPR) to learn the uncertainties to improve the control performance. The advantage of this framework lies in the ability to decouple safety and performance in the robust controller design. Furthermore, the inaccuracy measure given by GPR can be used to adaptively tighten the constraints, leading to the less conservative behaviors. A rigorous analysis of the constraint satisfaction, recursive feasibility and closed -loop stability is also presented. Two simulation examples, including a regulation problem of a nominally linear system and a tracking problem of a car whose model is nonlinear, are performed to verify the effectiveness of the proposed scheme.

Keywords:

Nonlinear model predictive control

Gaussian process regression

Safety-critical systems

Learning-based control

Safety enhancement for nonlinear systems via learning-based model predictive control with Gaussian process regression

Abstract

Journal

Organization