Online Learning-Based Control with Guaranteed Error Bounds for a Class of Nonlinear Systems

TL;DR

This paper introduces a learning-based control method for nonlinear systems that guarantees stability and bounded errors using Gaussian Process models and error rate limiting, validated through simulations and experiments.

Contribution

It develops a control framework combining GPSOL and DERL algorithms with stability analysis via LMIs, providing guaranteed error bounds for nonlinear system control.

Findings

Successfully verified error bounds through simulation.

Validated control scheme on a pneumatic test rig.

Demonstrated stability and bounded errors for first-order SISO systems.

Abstract

In this paper, we present a learning-based control for a class of nonlinear systems that guarantees exponential stability as well as bounded output errors. The control is based on the Gaussian Process Submodel Online Learning (GPSOL) algorithm and the Disturbance Error Rate Limiting (DERL) algorithm, both of which were developed in previous work. The GPSOL algorithm provides a method to learn Gaussian Process (GP) models for subsystems online, whereas the DERL algorithm allows to limit the rate of the prediction error of these GP models. The focus of this paper is the utilization of the GP model within an adaptive controller and the derivation of corresponding stability conditions and system peak-to-peak gains by means of linear matrix inequalities (LMIs). These peak-to-peak gains are then used to prescribe a desired prediction error rate for the DERL algorithm to achieve user-defined output error bounds. The gains and the related bounds were successfully verified using a simulation model. Furthermore, results form a successful experimental validation of the bounds and the overall control structure on a pneumatic test rig are presented. While the control scheme and error bounds proposed in this paper are limited to first-order single-input-single-output systems, an extension to certain classes of higher-order and multiple-input-multiple-output systems is expected to be forthcoming.