Results of using Machine Learning Algorithms for the Alignment Verification of the Roman Space Telescope (Invited Paper)

The Nancy Grace Roman Telescope is a NASA observatory designed to unravel the secrets of dark energy and dark matter, search for and image exoplanets, and explore many topics in infrared optics. Scheduled to launch no earlier than October 2026, this 2.4 meter aperture telescope has a field of view 100 times greater than the Hubble Space Telescope. The mission is currently in its final integration and testing phase, where the telescope and its two instruments were aligned together to ensure proper pupil matching. To verify this alignment, multiple point sources above the entrance pupil of the telescope illuminated the optical path through the telescope-instrument system, and shadows of various obstructions in the system were analyzed using machine learning algorithms to determine the pupil matching error. This presentation reviews the test results and the machine learning algorithms employed, and compares them to our uncertainty predictions based on a modeled Monte-Carlo analysis of the test.