AI-driven orbit determination uses normalizing flows for cislunar navigation

Researchers have developed a new method for orbit determination in the cislunar environment by applying generative modeling to angles-only measurements. This approach formulates the problem as conditional density estimation, using a normalizing flow trained on perturbed observations. The trained model can then generate statistically consistent and physics-informed state hypotheses from new measurements, which are subsequently refined by classical algorithms for improved accuracy. AI

IMPACT This research advances generative modeling applications in astrodynamics, potentially improving the accuracy and efficiency of space navigation.

RANK_REASON The cluster contains a research paper detailing a novel application of AI techniques to a specific scientific problem. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Cislunar Orbit Determination
• Generative Astrodynamics
• Near Rectilinear Halo Orbits
• Nonlinear Least-Squares Minimisation
• Normalizing Flows

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →