Distributed Koopman Learning with Incomplete Measurements
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915531322294272 |
|---|---|
| author | Hao, Wenjian Wang, Lili Rai, Ayush Mou, Shaoshuai |
| author_facet | Hao, Wenjian Wang, Lili Rai, Ayush Mou, Shaoshuai |
| contents | Koopman operator theory has emerged as a powerful tool for system identification, particularly for approximating nonlinear time-invariant systems (NTIS). This paper considers a network of agents with limited observation capabilities that collaboratively estimate the dynamics of an NTIS. A distributed deep Koopman learning algorithm is developed by integrating Koopman operator theory, deep neural networks, and consensus-based coordination. In the proposed framework, each agent approximates the system dynamics using its partial measurements and lifted states exchanged with its neighbors. This cooperative scheme enables accurate reconstruction of the global dynamics despite the absence of full-state information at individual agents. Simulation results on the Lunar Lander environment from OpenAI Gym demonstrate that the proposed method achieves performance comparable to the centralized deep Koopman learning with full-state access. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_11586 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Distributed Koopman Learning with Incomplete Measurements Hao, Wenjian Wang, Lili Rai, Ayush Mou, Shaoshuai Systems and Control Koopman operator theory has emerged as a powerful tool for system identification, particularly for approximating nonlinear time-invariant systems (NTIS). This paper considers a network of agents with limited observation capabilities that collaboratively estimate the dynamics of an NTIS. A distributed deep Koopman learning algorithm is developed by integrating Koopman operator theory, deep neural networks, and consensus-based coordination. In the proposed framework, each agent approximates the system dynamics using its partial measurements and lifted states exchanged with its neighbors. This cooperative scheme enables accurate reconstruction of the global dynamics despite the absence of full-state information at individual agents. Simulation results on the Lunar Lander environment from OpenAI Gym demonstrate that the proposed method achieves performance comparable to the centralized deep Koopman learning with full-state access. |
| title | Distributed Koopman Learning with Incomplete Measurements |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2409.11586 |