[PDF][PDF] 基于深度学习的自适应光学技术研究进展及展望

胡逸雯, 刘鑫, 匡翠方, 刘旭, 郝翔 - Chinese Journal of Lasers, 2023 - researching.cn
摘要自适应光学是一种校正波前误差的技术, 在地基望远镜, 生物成像, 人眼像差校正,
激光通信等领域中已经有了广泛的应用. 与此同时, 深度学习技术的快速发展为各个领域带来了 …

Adaptive optics control using model-based reinforcement learning

J Nousiainen, C Rajani, M Kasper, T Helin - Optics Express, 2021 - opg.optica.org
Reinforcement learning (RL) presents a new approach for controlling adaptive optics (AO)
systems for Astronomy. It promises to effectively cope with some aspects often hampering …

Adaptive optics control with multi-agent model-free reinforcement learning

B Pou, F Ferreira, E Quinones, D Gratadour… - Optics express, 2022 - opg.optica.org
We present a novel formulation of closed-loop adaptive optics (AO) control as a multi-agent
reinforcement learning (MARL) problem in which the controller is able to learn a non-linear …

Nonlinear wave front reconstruction from a pyramid sensor using neural networks

AP Wong, BRM Norris, V Deo, PG Tuthill… - Publications of the …, 2023 - iopscience.iop.org
The pyramid wave front sensor (PyWFS) has become increasingly popular to use in
adaptive optics (AO) systems due to its high sensitivity. The main drawback of the PyWFS is …

Self-optimizing adaptive optics control with reinforcement learning for high-contrast imaging

R Landman, SY Haffert… - Journal of …, 2021 - spiedigitallibrary.org
Current and future high-contrast imaging instruments require extreme adaptive optics
systems to reach contrasts necessary to directly imaged exoplanets. Telescope vibrations …

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

B Pou, J Smith, E Quinones, M Martin, D Gratadour - Optics Express, 2024 - opg.optica.org
We propose a novel control approach that combines offline supervised learning to address
the challenges posed by non-linear phase reconstruction using unmodulated pyramid …

Focal plane wavefront sensing using machine learning: performance of convolutional neural networks compared to fundamental limits

G Orban De Xivry, M Quesnel… - Monthly Notices of …, 2021 - academic.oup.com
Focal plane wavefront sensing (FPWFS) is appealing for several reasons. Notably, it offers
high sensitivity and does not suffer from non-common path aberrations (NCPAs). The price …

Using the Gerchberg–Saxton algorithm to reconstruct nonmodulated pyramid wavefront sensor measurements

V Chambouleyron, A Sengupta, M Salama… - Astronomy & …, 2024 - aanda.org
Context. Adaptive optics (AO) is a technique for improving the resolution of ground-based
telescopes by correcting optical aberrations due to atmospheric turbulence and the …

Machine learning for wavefront sensing

AP Wong, BRM Norris, V Deo, O Guyon… - … Optics Systems VIII, 2022 - spiedigitallibrary.org
Advances in the field of deep learning have motivated a flurry of research into the
application of neural networks to wavefront sensing for adaptive optics. This paper gives an …

Mitigating the nonlinearities in a pyramid wavefront sensor

F Archinuk, R Hafeez, S Fabbro… - Journal of …, 2023 - spiedigitallibrary.org
For natural guide star adaptive optics (AO) systems, pyramid wavefront sensors (PWFSs)
can provide a significant increase in sensitivity over the traditional Shack–Hartmann but at …