Integrating supervised and reinforcement learning for predictive control with an unmodulated pyramid wavefront sensor for adaptive optics
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_ | 1866910457389907968 |
|---|---|
| author | Pou, Bartomeu Smith, Jeffrey Quinones, Eduardo Martin, Mario Gratadour, Damien |
| author_facet | Pou, Bartomeu Smith, Jeffrey Quinones, Eduardo Martin, Mario Gratadour, Damien |
| contents | We propose a novel control approach that combines offline supervised learning to address the challenges posed by non-linear phase reconstruction using unmodulated pyramid wavefront sensors (P-WFS) and online reinforcement learning for predictive control. The control approach uses a high-order P-WFS to drive a tip-tilt stage and a high-dimensional mirror concurrently. Simulation results demonstrate that our method outperforms traditional control techniques, showing significant improvements in performance under challenging conditions such as faint stars and poor seeing, and exhibits robustness against variations in atmospheric conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_13610 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Integrating supervised and reinforcement learning for predictive control with an unmodulated pyramid wavefront sensor for adaptive optics Pou, Bartomeu Smith, Jeffrey Quinones, Eduardo Martin, Mario Gratadour, Damien Instrumentation and Methods for Astrophysics We propose a novel control approach that combines offline supervised learning to address the challenges posed by non-linear phase reconstruction using unmodulated pyramid wavefront sensors (P-WFS) and online reinforcement learning for predictive control. The control approach uses a high-order P-WFS to drive a tip-tilt stage and a high-dimensional mirror concurrently. Simulation results demonstrate that our method outperforms traditional control techniques, showing significant improvements in performance under challenging conditions such as faint stars and poor seeing, and exhibits robustness against variations in atmospheric conditions. |
| title | Integrating supervised and reinforcement learning for predictive control with an unmodulated pyramid wavefront sensor for adaptive optics |
| topic | Instrumentation and Methods for Astrophysics |
| url | https://arxiv.org/abs/2405.13610 |