An adaptive data sampling strategy for stabilizing dynamical systems via controller inference
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908823905632256 |
|---|---|
| author | Werner, Steffen W. R. Peherstorfer, Benjamin |
| author_facet | Werner, Steffen W. R. Peherstorfer, Benjamin |
| contents | Learning stabilizing controllers from data is an important task in engineering applications; however, collecting informative data is challenging because unstable systems often lead to rapidly growing or erratic trajectories. In this work, we propose an adaptive sampling scheme that generates data while simultaneously stabilizing the system to avoid instabilities during the data collection. Under mild assumptions, the approach provably generates data sets that are informative for stabilization and have minimal size. The numerical experiments demonstrate that controller inference with the novel adaptive sampling approach learns controllers with up to one order of magnitude fewer data samples than unguided data generation. The results show that the proposed approach opens the door to stabilizing systems in edge cases and limit states where instabilities often occur and data collection is inherently difficult. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01816 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An adaptive data sampling strategy for stabilizing dynamical systems via controller inference Werner, Steffen W. R. Peherstorfer, Benjamin Optimization and Control Machine Learning Numerical Analysis Dynamical Systems 37N35, 65F55, 90C22, 90C59, 93B52 Learning stabilizing controllers from data is an important task in engineering applications; however, collecting informative data is challenging because unstable systems often lead to rapidly growing or erratic trajectories. In this work, we propose an adaptive sampling scheme that generates data while simultaneously stabilizing the system to avoid instabilities during the data collection. Under mild assumptions, the approach provably generates data sets that are informative for stabilization and have minimal size. The numerical experiments demonstrate that controller inference with the novel adaptive sampling approach learns controllers with up to one order of magnitude fewer data samples than unguided data generation. The results show that the proposed approach opens the door to stabilizing systems in edge cases and limit states where instabilities often occur and data collection is inherently difficult. |
| title | An adaptive data sampling strategy for stabilizing dynamical systems via controller inference |
| topic | Optimization and Control Machine Learning Numerical Analysis Dynamical Systems 37N35, 65F55, 90C22, 90C59, 93B52 |
| url | https://arxiv.org/abs/2506.01816 |