Image-based wavefront correction using model-free Reinforcement Learning

TL;DR

This paper introduces a novel data-driven, model-free reinforcement learning approach for wavefront correction in telescopes, eliminating reliance on physical models and improving robustness and efficiency in aberration correction.

Contribution

The study develops a reinforcement learning-based method for wavefront correction that operates without physical models, trained solely on simulated data, enhancing adaptability and robustness.

Findings

Successfully learned control strategies in simulated environments

Demonstrated robustness across various noise levels

Outperformed traditional model-based methods in accuracy

Abstract

Optical aberrations prevent telescopes from reaching their theoretical diffraction limit. Once estimated, these aberrations can be compensated for using deformable mirrors in a closed loop. Focal plane wavefront sensing enables the estimation of the aberrations on the complete optical path, directly from the images taken by the scientific sensor. However, current focal plane wavefront sensing methods rely on physical models whose inaccuracies may limit the overall performance of the correction. The aim of this study is to develop a data-driven method using model-free reinforcement learning to automatically perform the estimation and correction of the aberrations, using only phase diversity images acquired around the focal plane as inputs. We formulate the correction problem within the framework of reinforcement learning and train an agent on simulated data. We show that the method is able to reliably learn an efficient control strategy for various realistic conditions. Our method also demonstrates robustness to a wide range of noise levels.