Interpreting High-Dimensional Earth-Moon Space Mission Design with Supervised Learning and Augmented Reality

View at publisher Summarise with VIRAT
Authors: Justin X. Schmitt, Seur Gi Jo, Marc Torrente, Henry Arnold, Michelle Aros, Barbara S. Chaparro, Kathleen Connor Howell, David Canales
Cited by: 0
References: 23

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Analyzing spacecraft motion in the Earth-Moon system requires interpreting high-dimensional, highly sensitive dynamical data, which is expensive to compute and difficult to visualize on 2D displays. This Work-in-Progress paper introduces a supervised learning surrogate that rapidly predicts key dynamical structures across energy levels, along with an augmented reality interface that places these structures in an interactive 3D environment to improve spatial understanding. Guided by human-centered design principles, a heuristic evaluation identifies initial usability needs. Together, these components offer a faster and more intuitive approach for exploring complex cislunar trajectory behavior.

Fields of Study & Subjects

Spacecraft Dynamics and Control Data Visualization and Analytics Space Exploration and Technology

Publication details

Journal / source
IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)
Pages
231–235
Publication date
26 January 2026
Language
EN