Synthesis of Stabilizing Recurrent Equilibrium Network Controllers
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909167086731264 |
|---|---|
| author | Junnarkar, Neelay Yin, He Gu, Fangda Arcak, Murat Seiler, Peter |
| author_facet | Junnarkar, Neelay Yin, He Gu, Fangda Arcak, Murat Seiler, Peter |
| contents | We propose a parameterization of a nonlinear dynamic controller based on the recurrent equilibrium network, a generalization of the recurrent neural network. We derive constraints on the parameterization under which the controller guarantees exponential stability of a partially observed dynamical system with sector bounded nonlinearities. Finally, we present a method to synthesize this controller using projected policy gradient methods to maximize a reward function with arbitrary structure. The projection step involves the solution of convex optimization problems. We demonstrate the proposed method with simulated examples of controlling nonlinear plants, including plants modeled with neural networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2204_00122 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Synthesis of Stabilizing Recurrent Equilibrium Network Controllers Junnarkar, Neelay Yin, He Gu, Fangda Arcak, Murat Seiler, Peter Systems and Control Artificial Intelligence Robotics We propose a parameterization of a nonlinear dynamic controller based on the recurrent equilibrium network, a generalization of the recurrent neural network. We derive constraints on the parameterization under which the controller guarantees exponential stability of a partially observed dynamical system with sector bounded nonlinearities. Finally, we present a method to synthesize this controller using projected policy gradient methods to maximize a reward function with arbitrary structure. The projection step involves the solution of convex optimization problems. We demonstrate the proposed method with simulated examples of controlling nonlinear plants, including plants modeled with neural networks. |
| title | Synthesis of Stabilizing Recurrent Equilibrium Network Controllers |
| topic | Systems and Control Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2204.00122 |