We present results on integrating Machine Learning (ML) methods for adaptive optics control with a real-time control library: COmmon Scalable and Modular Infrastructure for real-time Control (COSMIC). We test the integration on simulations for the instrument SAXO+. Our proposed solution’s pipeline is formed by a two-model ML system. The first model consists of a very Deep Neural Network (DNN) that maps Wavefront Sensor (WFS) images to phase and is trained offline. The second model consists of predictive control with a more compact DNN. The predictive control stage is trained online, providing an adaptive solution to changing atmospheric conditions but adding extra complexity to the pipeline. On top of implementing the solution with COSMIC, we add a set of modifications to provide faster inference and online training. Specifically, we test NVIDIA’s TensorRT to accelerate the DNNs inference, reduced precision, and just-in-time compilation for PyTorch. We show real-time capabilities by using COSMIC and improved speeds both in inference and training by using the recommendations mentioned above.
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.
A classical closed-loop adaptive optics system with a Shack-Hartmann wavefront sensor (WFS) relies on a center of gravity approach to process the WFS information and an integrator with gain to produce the commands to a Deformable Mirror (DM) to compensate wavefront perturbations. In this kind of systems, noise in the WFS images can propagate to errors in centroids computation, and thus, lead the AO system to perform poorly in closed-loop operations. In this work, we present a deep supervised learning method to denoise the WFS images based on convolutional denoising autoencoders. Our method is able to denoise the images up to a high noise level and improve the integrator performance almost to the level of a noise-free situation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.