A Time-Reversal Control Synthesis for Steering the State of Stochastic 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_ | 1866908528350855168 |
|---|---|
| author | Mei, Yuhang Taghvaei, Amirhossein Pakniyat, Ali |
| author_facet | Mei, Yuhang Taghvaei, Amirhossein Pakniyat, Ali |
| contents | This paper presents a novel approach for steering the state of a stochastic control-affine system to a desired target within a finite time horizon. Our method leverages the time-reversal of diffusion processes to construct the required feedback control law. Specifically, the control law is the so-called score function associated with the time-reversal of random state trajectories that are initialized at the target state and are simulated backwards in time. A neural network is trained to approximate the score function, enabling applicability to both linear and nonlinear stochastic systems. Numerical experiments demonstrate the effectiveness of the proposed method across several benchmark examples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00238 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Time-Reversal Control Synthesis for Steering the State of Stochastic Systems Mei, Yuhang Taghvaei, Amirhossein Pakniyat, Ali Optimization and Control This paper presents a novel approach for steering the state of a stochastic control-affine system to a desired target within a finite time horizon. Our method leverages the time-reversal of diffusion processes to construct the required feedback control law. Specifically, the control law is the so-called score function associated with the time-reversal of random state trajectories that are initialized at the target state and are simulated backwards in time. A neural network is trained to approximate the score function, enabling applicability to both linear and nonlinear stochastic systems. Numerical experiments demonstrate the effectiveness of the proposed method across several benchmark examples. |
| title | A Time-Reversal Control Synthesis for Steering the State of Stochastic Systems |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2504.00238 |