Aug 12 – 16, 2024
Von-Melle-Park 8
Europe/Berlin timezone

Data-driven predictive control with stability guarantees

Aug 12, 2024, 2:00 PM
30m
Seminarraum 205 (Von-Melle-Park 8)

Seminarraum 205

Von-Melle-Park 8

Minisymposium Contribution MS 01: Optimal Control and Machine Learning MS 01: Optimal Control and Machine Learning

Speaker

Manuel Schaller

Description

Extended Dynamic Mode Decomposition is a popular data-driven method to approximate the flow of a dynamical control system through the lens of observable functions. In this talk, we discuss how this framework and corresponding finite-data error bounds may be used in data-driven Model Predictive Control to establish (practical) asymptotic stability. The key ingredient are proportional error bounds vanishing at the origin, which may be utilized to show that important system-theoretic properties, such as cost controllability, carry over to the data-driven model, if a sufficient amount of samples is chosen.

Author

Manuel Schaller

Co-authors

Prof. Karl Worthmann (Technische Universität Ilmenau) Prof. Lars Grüne (University of Bayreuth) Lea Bold (Technische Universität Ilmenau)

Presentation materials

There are no materials yet.