On-sky demonstration of reinforcement learning for adaptive optics control

• URL: http://arxiv.org/abs/2606.10771v1
• Date: Tue, 09 Jun 2026 12:26:06 GMT
• Title: On-sky demonstration of reinforcement learning for adaptive optics control
• Abstract summary: We report the first on-sky demonstration of a reinforcement learning controller for adaptive optics, named Policy Optimization for AO (PO4AO)<n>PO4AO was implemented and deployed on the Papyrus adaptive optics system installed at the Coudé focus of the 1.52 m telescope (T152) at the OHP.<n>When properly implemented and optimized, PO4AO constitutes a robust and high-performance turnkey controller for single-conjugate adaptive optics systems.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL)-based algorithms have recently emerged as a promising approach for adaptive optics (AO) control. In simulations and laboratory experiments, they have demonstrated robustness to real-world effects such as photon and detector noise, misregistration, vibrations, and rapid variations in seeing conditions. However, their performance has not yet been validated on sky. We report the first on-sky demonstration of a reinforcement learning controller for adaptive optics, named Policy Optimization for AO (PO4AO). We further analyze its on-sky behavior and identify directions for improving the algorithm and its implementation.PO4AO was implemented and deployed on the Papyrus adaptive optics system installed at the Coudé focus of the 1.52 m telescope (T152) at the OHP. A Python-based implementation was interfaced with the existing real-time controller (DAO RTC) via shared-memory buffers. The performance of PO4AO was compared to that of a standard integrator controller over several nights, covering a range of flux levels and atmospheric conditions. PO4AO consistently outperformed the standard integrator in all tested configurations. The controller successfully learned and compensated for vibration patterns and demonstrated strong robustness to measurement noise. Once tuned for Papyrus, PO4AO operated in a turnkey fashion, using a single set of hyperparameters across varying observing conditions and science targets. These performance gains were achieved despite a non-optimized Python implementation introducing approximately $750\,μ\text{s}$ of additional latency, along with control jitter and occasional frame drops. When properly implemented and optimized, PO4AO constitutes a robust and high-performance turnkey controller for single-conjugate adaptive optics systems, paving the way for broader adoption of reinforcement learning strategies in on-sky AO operations.

Related papers

• Reinforcement Learning-Guided Evolutionary Policy Optimization for Preference-Adjustable Heterogeneous Agile Earth Observation Satellite Scheduling [50.176885352114674]
  Heterogeneous agile Earth observation satellite (AEOS) scheduling requires task selection, satellite assignment, and observation sequencing.<n>This paper proposes an evolutionary policy optimization framework for heterogeneous AEOS scheduling with preference-adjustable weighted objectives.
  arXiv  Detail & Related papers  (2026-08-25T12:16:28Z)
• LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning [90.86828952599147]
  We present LaST-R1, a novel reinforcement learning framework designed to harness "latent reasoning-before-acting" policies.<n>LaST-R1 achieves a near-perfect 99.9% average success rate on the LIBERO benchmark.<n>In real-world deployments, LaST-R1 yields up to a 22.5% average improvement over SOTA supervised fine-tuning approach.
  arXiv  Detail & Related papers  (2026-04-30T17:59:52Z)
• Focal plane wavefront control with model-based reinforcement learning [0.0]
  Direct imaging of potentially habitable exoplanets is one prime science case for high-contrast imaging instruments on extremely large telescopes.<n>Most such exoplanets orbit close to their host stars, where their observation is limited by quasi-static non-common-path aberrations (NCPA)<n>This work presents machine-learning-based NCPA control methods that automatically detect and correct both dynamic and static NCPA errors.
  arXiv  Detail & Related papers  (2026-04-01T14:55:15Z)
• Controlled LLM Training on Spectral Sphere [76.60985966206746]
  We introduce the textbfSpectral Sphere algorithm (SSO), which enforces strict module-wise spectral constraints on both weights and their updates.<n>We observe significant practical stability benefits, including improved MoE router load balancing, suppressed outliers, and strictly bounded activations.
  arXiv  Detail & Related papers  (2026-01-13T09:59:47Z)
• Comparison of Model Predictive Control and Proximal Policy Optimization for a 1-DOF Helicopter System [0.7499722271664147]
  This study conducts a comparative analysis of Model Predictive Control (MPC) and Proximal Policy Optimization (PPO), a Deep Reinforcement Learning (DRL) algorithm, applied to a Quanser Aero 2 system. PPO excels in rise-time and adaptability, making it a promising approach for applications requiring rapid response and adaptability.
  arXiv  Detail & Related papers  (2024-08-28T08:35:34Z)
• Laboratory Experiments of Model-based Reinforcement Learning for Adaptive Optics Control [0.565395466029518]
  We implement and adapt an RL method called Policy Optimization for AO (PO4AO) to the GHOST test bench at ESO headquarters. We study the predictive and self-calibrating aspects of the method. New implementation on GHOST running PyTorch introduces only around 700 microseconds in addition to hardware, pipeline, and Python interface latency.
  arXiv  Detail & Related papers  (2023-12-30T14:11:43Z)
• Reinforcement Learning-based Wavefront Sensorless Adaptive Optics Approaches for Satellite-to-Ground Laser Communication [1.8531813733282103]
  Optical satellite-to-ground communication (OSGC) has the potential to improve access to fast and affordable Internet in remote regions. Traditional adaptive optics (AO) systems use a wavefront sensor to improve fiber coupling. We propose the use of reinforcement learning (RL) to reduce the latency, size and cost of the system by up to $30-40%$ by learning a control policy through interactions with a low-cost quadrant photodiode rather than a wavefront phase profiling camera.
  arXiv  Detail & Related papers  (2023-03-13T23:03:17Z)
• Thompson Sampling Achieves $\tilde O(\sqrt{T})$ Regret in Linear Quadratic Control [85.22735611954694]
  We study the problem of adaptive control of stabilizable linear-quadratic regulators (LQRs) using Thompson Sampling (TS) We propose an efficient TS algorithm for the adaptive control of LQRs, TSAC, that attains $tilde O(sqrtT)$ regret, even for multidimensional systems.
  arXiv  Detail & Related papers  (2022-06-17T02:47:53Z)
• Towards on-sky adaptive optics control using reinforcement learning [0.0]
  The direct imaging of potentially habitable Exoplanets is one prime science case for the next generation of high contrast imaging instruments on ground-based extremely large telescopes. To reach this demanding science goal, the instruments are equipped with eXtreme Adaptive Optics (XAO) systems which will control thousands of actuators at a framerate of kilohertz to several kilohertz. Most of the habitable exoplanets are located at small angular separations from their host stars, where the current XAO systems' control laws leave strong residuals.
  arXiv  Detail & Related papers  (2022-05-16T10:01:06Z)
• Optimization-driven Deep Reinforcement Learning for Robust Beamforming in IRS-assisted Wireless Communications [54.610318402371185]
  Intelligent reflecting surface (IRS) is a promising technology to assist downlink information transmissions from a multi-antenna access point (AP) to a receiver. We minimize the AP's transmit power by a joint optimization of the AP's active beamforming and the IRS's passive beamforming. We propose a deep reinforcement learning (DRL) approach that can adapt the beamforming strategies from past experiences.
  arXiv  Detail & Related papers  (2020-05-25T01:42:55Z)
• Guided Constrained Policy Optimization for Dynamic Quadrupedal Robot Locomotion [78.46388769788405]
  We introduce guided constrained policy optimization (GCPO), an RL framework based upon our implementation of constrained policy optimization (CPPO) We show that guided constrained RL offers faster convergence close to the desired optimum resulting in an optimal, yet physically feasible, robotic control behavior without the need for precise reward function tuning.
  arXiv  Detail & Related papers  (2020-02-22T10:15:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.