arXiv Open Access 2025

Kernel-based error bounds of bilinear Koopman surrogate models for nonlinear data-driven control

Robin Strässer Manuel Schaller Julian Berberich Karl Worthmann Frank Allgöwer
Lihat Sumber

Abstrak

We derive novel deterministic bounds on the approximation error of data-based bilinear surrogate models for unknown nonlinear systems. The surrogate models are constructed using kernel-based extended dynamic mode decomposition to approximate the Koopman operator in a reproducing kernel Hilbert space. Unlike previous methods that require restrictive assumptions on the invariance of the dictionary, our approach leverages kernel-based dictionaries that allow us to control the projection error via pointwise error bounds, overcoming a significant limitation of existing theoretical guarantees. The derived state- and input-dependent error bounds allow for direct integration into Koopman-based robust controller designs with closed-loop guarantees for the unknown nonlinear system. Numerical examples illustrate the effectiveness of the proposed framework.

Topik & Kata Kunci

Penulis (5)

R

Robin Strässer

M

Manuel Schaller

J

Julian Berberich

K

Karl Worthmann

F

Frank Allgöwer

Format Sitasi

Strässer, R., Schaller, M., Berberich, J., Worthmann, K., Allgöwer, F. (2025). Kernel-based error bounds of bilinear Koopman surrogate models for nonlinear data-driven control. https://arxiv.org/abs/2503.13407

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓