Inverse Learning-Based Output Feedback Control of Nonlinear Systems with Verifiable Guarantees

TL;DR

This paper introduces a data-driven output feedback control method for nonlinear systems that guarantees practical output regulation using kernel interpolation and a reference selection framework, with verifiable dataset conditions and robustness assessments.

Contribution

It develops a novel inverse learning-based controller with verifiable guarantees for nonlinear systems using noise-free data and a data-driven reference selection process.

Findings

Successfully achieves practical output regulation in simulations.

Provides verifiable dataset conditions for controller guarantees.

Demonstrates robustness with noisy output measurements.

Abstract

In this paper, we present a data-driven output feedback controller for nonlinear systems that achieves practical output regulation, using noise-free input/output measurement data. The proposed controller is based on (i) an inverse model of the system identified via kernel interpolation, which maps a desired output and the current state to the corresponding desired control input; and (ii) a data-driven reference selection framework that actively chooses a suitable desired output from the dataset which has been used for the identification. We establish a verifiable sufficient condition on the dataset under which the proposed controller guarantees practical output regulation. Numerical simulations demonstrate the effectiveness of the proposed controller, with additional evaluations in the presence of output measurement noise to assess its robustness empirically.