Robust constrained nonlinear Model Predictive Control with Gated Recurrent Unit model -- Extended version

TL;DR

This paper introduces a robust nonlinear Model Predictive Control framework utilizing a Gated Recurrent Unit network model to handle uncertainties, ensure constraint satisfaction, and guarantee stability in controlled systems.

Contribution

It presents a novel MPC approach with a Gated Recurrent Unit model, incorporating constraint tightening, new terminal cost, and set for stability under uncertainties.

Findings

Ensures robust constraint satisfaction under model uncertainties.

Guarantees Input-to-State Stability of the closed-loop system.

Demonstrates effectiveness through theoretical analysis and simulations.

Abstract

In this paper we propose a robust Model Predictive Control where a Gated Recurrent Unit network model is used to learn the input-output dynamic of the system under control. Robust satisfaction of input and output constraints and recursive feasibility in presence of model uncertainties are achieved using a constraint tightening approach. Moreover, new terminal cost and terminal set are introduced in the Model Predictive Control formulation to guarantee Input-to-State Stability of the closed loop system with respect to the uncertainty term.