EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Distributed Koopman operator learning from sequential observations

Ali Azarbahram, Shenyu Liu, Gian Paolo Incremona

European Journal of Control · 2026-05 · 89 · 101497

DOI: 10.1016/j.ejcon.2026.101497 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Control, 2026-05. Verfasst von Ali Azarbahram und 2 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a distributed Koopman operator learning framework for modeling unknown nonlinear dynamics using sequential observations from multiple agents. Each agent estimates a local Koopman approximation based on lifted data and collaborates over a communication graph to reach exponential consensus on a consistent distributed approximation. The approach supports distributed computation under asynchronous and resource-constrained sensing. Its performance is demonstrated through simulation results, validating convergence and predictive accuracy under sensing-constrained scenarios and limited communication.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Azarbahram, A., Liu, S., & Incremona, G. P. (2026). Distributed Koopman operator learning from sequential observations. European Journal of Control, 89, 101497. https://doi.org/10.1016/j.ejcon.2026.101497

Vancouver

Azarbahram A, Liu S, Incremona GP. Distributed Koopman operator learning from sequential observations. European Journal of Control. 2026;89:101497. doi:10.1016/j.ejcon.2026.101497

BibTeX
@article{Azarbahram2026,
  author = {Azarbahram, Ali and Liu, Shenyu and Incremona, Gian Paolo},
  title = {Distributed Koopman operator learning from sequential observations},
  journal = {European Journal of Control},
  year = {2026},
  volume = {89},
  pages = {101497},
  doi = {10.1016/j.ejcon.2026.101497}
}
Kostenlos starten →