Focal plane wavefront control with model-based reinforcement learning

2026-04-01

AI Summary

This study addresses the challenge of detecting exoplanets with ground-based extremely large telescopes (ELTs) under atmospheric turbulence and non-common-path aberrations (NCPA). The authors propose PO4NCPA, a model-free reinforcement learning approach for focal-plane wavefront control that requires no prior system knowledge and relies solely on focal-plane images and sequential phase diversity to jointly correct both static and dynamic NCPA. Simulations conducted under realistic ELT apertures, vector vortex coronagraphy, and noise conditions demonstrate that PO4NCPA achieves near-optimal light suppression and high Strehl ratios for static aberrations. For dynamic aberrations, its performance rivals that of modal least-squares control combined with a delay integrator, while operating at sub-millisecond inference speeds, making it suitable for real-time correction of low-order atmospheric turbulence.

Abstract

The direct imaging of potentially habitable exoplanets is one prime science case for high-contrast imaging instruments on extremely large telescopes. Most such exoplanets orbit close to their host stars, where their observation is limited by fast-moving atmospheric speckles and quasi-static non-common-path aberrations (NCPA). Conventional NCPA correction methods often use mechanical mirror probes, which compromise performance during operation. This work presents machine-learning-based NCPA control methods that automatically detect and correct both dynamic and static NCPA errors by leveraging sequential phase diversity. We extend previous work in reinforcement learning for AO to focal plane control. A new model-based RL algorithm, Policy Optimization for NCPAs (PO4NCPA), interprets the focal-plane image as input data and, through sequential phase diversity, determines phase corrections that optimize both non-coronagraphic and post-coronagraphic PSFs without prior system knowledge. Further, we demonstrate the effectiveness of this approach by numerically simulating static NCPA errors on a ground-based telescope and an infrared imager affected by water-vapor-induced seeing (dynamic NCPAs). Simulations show that PO4NCPA robustly compensates static and dynamic NCPAs. In static cases, it achieves near-optimal focal-plane light suppression with a coronagraph and near-optimal Strehl without one. With dynamics NCPA, it matches the performance of the modal least-squares reconstruction combined with a 1-step delay integrator in these metrics. The method remains effective for the ELT pupil, vector vortex coronagraph, and under photon and background noise. PO4NCPA is model-free and can be directly applied to standard imaging as well as to any coronagraph. Its sub-millisecond inference times and performance also make it suitable for real-time low-order correction of atmospheric turbulence beyond HCI.

Problem

• non-common-path aberrations
• high-contrast imaging
• exoplanet direct imaging
• atmospheric speckles
• extremely large telescopes

Innovation

• model-based reinforcement learning
• non-common-path aberrations
• focal plane wavefront control
• phase diversity
• high-contrast imaging