Offline Uncertainty Sampling in Data-driven Stochastic MPC

Abstract

In this work, we exploit an offline-sampling based strategy for the constrained data-driven predictive control of an unknown linear system subject to random measurement noise. The strategy uses only past measured, potentially noisy data in a non-parametric system representation and does not require any prior model identification. The approximation of chance constraints using uncertainty sampling leads to efficient constraint tightening. Under mild assumptions, robust recursive feasibility and closed-loop constraint satisfaction is shown. In a simulation example, we provide evidence for the improved control performance of the proposed control scheme in comparison to a purely robust data-driven predictive control approach.

arXiv commentThis work has been accepted for presentation at IFAC World Congress 2023

References in corpus (5)

• Data-Driven Model Predictive Control with Stability and Robustness Guarantees
• The Scenario Approach for Stochastic Model Predictive Control with Bounds on Closed-Loop Constraint Violations
• On a Stochastic Fundamental Lemma and Its Use for Data-Driven Optimal Control
• Data-driven model predictive control: closed-loop guarantees and experimental results
• Minimization of Constraint Violation Probability in Model Predictive Control

Cited by in corpus (1)

• Sampling-based Stochastic Data-driven Predictive Control under Data Uncertainty - Extended Version