Distributed Koopman Learning using Partial Trajectories for Control
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915854707326976 |
|---|---|
| author | Hao, Wenjian Lu, Zehui Upadhyay, Devesh Mou, Shaoshuai |
| author_facet | Hao, Wenjian Lu, Zehui Upadhyay, Devesh Mou, Shaoshuai |
| contents | This paper proposes a distributed data-driven framework for dynamics learning, termed distributed deep Koopman learning using partial trajectories (DDKL-PT). In this framework, each agent in a multi-agent system is assigned a partial trajectory offline and locally approximates the unknown dynamics using a deep neural network within the Koopman operator framework. By exchanging local estimated dynamics rather than training data, agents achieve consensus on a global dynamics model without sharing their private training trajectories. Simulation studies on a surface vehicle demonstrate that DDKL-PT achieves consensus on the learned dynamics, and each agent attains reasonably small approximation errors on the testing dataset. Furthermore, a model predictive control scheme is developed by integrating the learned Koopman dynamics with known kinematic relations. Results on a reference-tracking task indicate that the distributedly learned dynamics are sufficiently accurate for model-based optimal control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07212 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Distributed Koopman Learning using Partial Trajectories for Control Hao, Wenjian Lu, Zehui Upadhyay, Devesh Mou, Shaoshuai Systems and Control This paper proposes a distributed data-driven framework for dynamics learning, termed distributed deep Koopman learning using partial trajectories (DDKL-PT). In this framework, each agent in a multi-agent system is assigned a partial trajectory offline and locally approximates the unknown dynamics using a deep neural network within the Koopman operator framework. By exchanging local estimated dynamics rather than training data, agents achieve consensus on a global dynamics model without sharing their private training trajectories. Simulation studies on a surface vehicle demonstrate that DDKL-PT achieves consensus on the learned dynamics, and each agent attains reasonably small approximation errors on the testing dataset. Furthermore, a model predictive control scheme is developed by integrating the learned Koopman dynamics with known kinematic relations. Results on a reference-tracking task indicate that the distributedly learned dynamics are sufficiently accurate for model-based optimal control. |
| title | Distributed Koopman Learning using Partial Trajectories for Control |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2412.07212 |