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.
| Original language | English |
|---|---|
| Pages (from-to) | 13-18 |
| Number of pages | 6 |
| Journal | IFAC Proceedings Volumes (IFAC-PapersOnline) |
| Volume | 55 |
| Issue number | 15 |
| DOIs | |
| State | Published - 1 Jul 2022 |
| Event | 6th IFAC Conference on Intelligent Control and Automation Sciences, ICONS 2022 - Cluj-Napoca, Romania Duration: 13 Jul 2022 → 15 Jul 2022 |
Keywords
- Koopman operators
- Learning Systems
- Learning for control
- Machine learning
- Neural networks
- Representation Learning
Fingerprint
Dive into the research topics of 'Towards Data-driven LQR with Koopmanizing Flows'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver