Nonlinear Data-Enabled Prediction and Control

Abstract

The Willems' fundamental lemma, which characterizes linear dynamics with measured trajectories, has found successful applications in controller design and signal processing, which has driven a broad research interest in its extension to nonlinear systems. In this work, we propose to apply the fundamental lemma to a reproducing kernel Hilbert space in order to extend its application to a class of nonlinear systems and we show its application in prediction and in predictive control.

arXiv commentAccepted to L4DC 2021, Zurich

References in corpus (4)

• Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control
• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
• Data-based stabilization of unknown bilinear systems with guaranteed basin of attraction
• Data-driven stabilization of nonlinear polynomial systems with noisy data

Cited by in corpus (5)

• Linear tracking MPC for nonlinear systems Part II: The data-driven case
• Koopman based data-driven predictive control
• Adaptive Robust Data-driven Building Control via Bi-level Reformulation: an Experimental Result
• Near-Optimal Design of Safe Output Feedback Controllers from Noisy Data
• From System Level Synthesis to Robust Closed-loop Data-enabled Predictive Control