Learning Safety-Compatible Observers for Unknown Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908575573475328 |
|---|---|
| author | Bae, Juho Roh, Daegyeong Choi, Han-Lim |
| author_facet | Bae, Juho Roh, Daegyeong Choi, Han-Lim |
| contents | This paper presents a data-driven approach for jointly learning a robust full-state observer and its robustness certificate for systems with unknown dynamics. Leveraging incremental input-to-state stability (delta ISS) notions, we jointly learn a delta ISS Lyapunov function that serves as the robustness certificate and prove practical convergence of the estimation error under standard fidelity assumptions on the learned models. This renders the observer safety-compatible: they can be consumed by certificate-based safe controllers so that, when the controller tolerates bounded estimation error, the controller's certificate remains valid under output feedback. We further extend the approach to interconnected systems via the small-gain theorem, yielding a distributed observer design framework. We validate the approach on a variety of nonlinear systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03609 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Safety-Compatible Observers for Unknown Systems Bae, Juho Roh, Daegyeong Choi, Han-Lim Systems and Control This paper presents a data-driven approach for jointly learning a robust full-state observer and its robustness certificate for systems with unknown dynamics. Leveraging incremental input-to-state stability (delta ISS) notions, we jointly learn a delta ISS Lyapunov function that serves as the robustness certificate and prove practical convergence of the estimation error under standard fidelity assumptions on the learned models. This renders the observer safety-compatible: they can be consumed by certificate-based safe controllers so that, when the controller tolerates bounded estimation error, the controller's certificate remains valid under output feedback. We further extend the approach to interconnected systems via the small-gain theorem, yielding a distributed observer design framework. We validate the approach on a variety of nonlinear systems. |
| title | Learning Safety-Compatible Observers for Unknown Systems |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2510.03609 |