Model-free reinforcement learning with a non-linear reconstructor for closed-loop adaptive optics control with a pyramid wavefront sensor

B. Pou; J. Smith; E. Quinones; M. Martin; D. Gratadour

doi:10.1117/12.2627849

29 August 2022 Model-free reinforcement learning with a non-linear reconstructor for closed-loop adaptive optics control with a pyramid wavefront sensor

B. Pou, J. Smith, E. Quinones, M. Martin, D. Gratadour

Author Affiliations +

Proceedings Volume 12185, Adaptive Optics Systems VIII; 121852U (2022) https://doi.org/10.1117/12.2627849
Event: SPIE Astronomical Telescopes + Instrumentation, 2022, Montréal, Québec, Canada

Abstract

We present a model-free reinforcement learning (RL) predictive model with a supervised learning non-linear reconstructor for adaptive optics (AO) control with a pyramid wavefront sensor (P-WFS). First, we analyse the additional problems of training an RL control method with a P-WFS compared to the Shack-Hartmann WFS. From those observations, we propose our solution: a combination of model-free RL for prediction with a non-linear reconstructor based on neural networks with a U-net architecture. We test the proposed method in simulation of closed-loop AO for an 8m telescope equipped with a 32x32 P-WFS and observe that both the predictive and non-linear reconstruction add additional benefits over an optimised integrator.

Conference Presentation

Citation Download Citation

B. Pou, J. Smith, E. Quinones, M. Martin, and D. Gratadour "Model-free reinforcement learning with a non-linear reconstructor for closed-loop adaptive optics control with a pyramid wavefront sensor", Proc. SPIE 12185, Adaptive Optics Systems VIII, 121852U (29 August 2022); https://doi.org/10.1117/12.2627849

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
14 PAGES + PRESENTATION

DOWNLOAD PAPER SAVE TO MY LIBRARY

WATCH
PRESENTATION

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Adaptive optics

Wavefront sensors

Neural networks

Telescopes

Machine learning

RELATED CONTENT

Machine learning techniques for piston sensing
Proceedings of SPIE (August 29 2022)

Tempestas ex machina a review of machine learning methods...
Proceedings of SPIE (October 05 2023)

Demonstration of linear and neural net closed loop control with...
Proceedings of SPIE (January 01 1900)

High precision femtosecond laser processing with aberration compensation based on...
Proceedings of SPIE (January 01 1900)

Self-optimizing adaptive optics control with reinforcement learning
Proceedings of SPIE (December 13 2020)

Neural network for modal compensation of atmospheric turbulence
Proceedings of SPIE (September 30 1994)

Recovery of atmospheric phase distortion from stellar images using an...
Proceedings of SPIE (January 13 1992)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years