Towards Data-driven LQR with Koopmanizing Flows

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

*Kontaktforfatter

Publikation: Bidrag til tidsskriftKonferenceartikel i tidsskriftForskningpeer review

4 Citationer (Scopus)
42 Downloads (Pure)

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.

OriginalsprogEngelsk
BogserieIFAC-PapersOnLine
Vol/bind55
Udgave nummer15
Sider (fra-til)13-18
Antal sider6
ISSN1474-6670
DOI
StatusUdgivet - 1 jul. 2022
Begivenhed6th IFAC Conference on Intelligent Control and Automation Sciences, ICONS 2022 - Cluj-Napoca, Rumænien
Varighed: 13 jul. 202215 jul. 2022

Konference

Konference6th IFAC Conference on Intelligent Control and Automation Sciences, ICONS 2022
Land/OmrådeRumænien
ByCluj-Napoca
Periode13/07/202215/07/2022
Sponsoret al., IFAC TC 1.2. Adaptive and Learning Systems, IFAC TC 3.3. Telematics: Control via Communication Networks, IFAC TC 4.3. Robotics, IFAC TC 4.5. Human Machine Systems, International Federation of Automatic Control (IFAC) - IFAC Technical Committee on Computational Intelligence in Control, TC 3.2

Bibliografisk note

Funding Information:
This work was supported by the European Union's Horizon 2020 research and innovation programme under grant agreement no. 871295 "SeaClear" (SEarch, identiflcAtion and Collection of marine Litter with Autonomous Robots).

Publisher Copyright:
Copyright © 2022 The Authors.

Fingeraftryk

Dyk ned i forskningsemnerne om 'Towards Data-driven LQR with Koopmanizing Flows'. Sammen danner de et unikt fingeraftryk.

Citationsformater