arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.13610astro-ph.IM
收藏

集成监督学习与强化学习用于自适应光学中未调制金字塔波前传感器的预测控制

Integrating supervised and reinforcement learning for predictive control with an unmodulated pyramid wavefront sensor for adaptive optics

Bartomeu Pou, Jeffrey Smith, Eduardo Quinones, Mario Martin, Damien Gratadour

AI总结:

本文提出一种结合离线监督学习与在线强化学习的控制方法,利用未调制金字塔波前传感器同时驱动倾斜平台和高维镜,在暗弱恒星和差视宁度下显著优于传统控制,且对大气变化鲁棒。

摘要:

我们提出了一种新颖的控制方法,结合离线监督学习以应对使用未调制金字塔波前传感器(P-WFS)进行非线性相位重建所面临的挑战,并采用在线强化学习进行预测控制。该控制方法使用高阶P-WFS同时驱动倾斜校正平台和高维变形镜。仿真结果表明,我们的方法优于传统控制技术,在暗弱恒星和较差视宁度等挑战性条件下表现出显著的性能提升,并且对大气条件的变化具有鲁棒性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑