Towards Data-driven LQR with Koopmanizing Flows

Petar Bevanda, Max Beier, Shahab Heshmati-Alamdari, Stefan Sosnowski, Sandra Hirche

Publikation: Beitrag in FachzeitschriftKonferenzartikelBegutachtung

4 Zitate (Scopus)

Abstract

We propose a novel framework for learning linear time-invariant (LTI) models for a class of continuous-time non-autonomous nonlinear dynamics based on a representation of Koopman operators. In general, the operator is infinite-dimensional but, crucially, linear. To utilize it for efficient LTI control design, we learn a finite representation of the Koopman operator that is linear in controls while concurrently learning meaningful lifting coordinates. For the latter, we rely on Koopmanizing Flows - a diffeomorphism-based representation of Koopman operators and extend it to systems with linear control entry. With such a learned model, we can replace the nonlinear optimal control problem with quadratic cost to that of a linear quadratic regulator (LQR), facilitating efficacious optimal control for nonlinear systems. The superior control performance of the proposed method is demonstrated on simulation examples.

OriginalspracheEnglisch
Seiten (von - bis)13-18
Seitenumfang6
FachzeitschriftIFAC Proceedings Volumes (IFAC-PapersOnline)
Jahrgang55
Ausgabenummer15
DOIs
PublikationsstatusVeröffentlicht - 1 Juli 2022
Veranstaltung6th IFAC Conference on Intelligent Control and Automation Sciences, ICONS 2022 - Cluj-Napoca, Rumänien
Dauer: 13 Juli 202215 Juli 2022

Fingerprint

Untersuchen Sie die Forschungsthemen von „Towards Data-driven LQR with Koopmanizing Flows“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren