← Back to NASA Technology Projects

Reinforcement Learning for High-Contrast Exoplanet Imaging with Coronagraphs

Completed TRL 3 (started at 1, targeting 3)

Description

We propose developing a Reinforcement Learning (RL) agent that will produce optical wavefront sensing and control algorithms addressing 2 application areas: (a) “digging” optimal coronagraphic dark-holes, and (b) Wavefront Sensing (WFS) based PSF calibration. The ultimate target opportunity for this work is toward the Habitable Worlds Observatory (HWO).

Benefits

The objective is to capitalize on the latest developments in machine learning (Reinforcement Learning) that uses pattern recognition algorithms to navigate a complex design environment, while maximizing a reward function to produce agents that can provide solutions to digging coronographic dark-holes and WFS-based PSF calibration. The effort constitutes the development of a new and enabling capability.

Details

Technology areaSensors and Instruments
ProgramCenter Independent Research & Development: GSFC IRAD (GSFC IRAD)
Lead organizationGoddard Space Flight Center, Greenbelt, MD
Start date2023-10-01
End date2024-09-30

Project contacts

Listed on TechPort itself — the most direct way to ask about this specific project.

How to get involved

This is early/mid-stage (TRL 3) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.