Investigating the Fusion of Model-Based and Data-Driven Methods for Uncertainty Quantification in Cislunar Space Domain Awareness

Abstract

Space domain awareness (SDA) comprises acquiring observations and processing those observations to perform initial orbit determination for newly detected objects, correlation and catalogue updates, tracking, predictions, conjunction analysis, and probability of collisions. As new missions are being continuously studied and developed for cislunar space, there is a need for new cislunar SDA capability that goes beyond Earth orbits. Prediction of detected objects motion is not trivial due to the complex and uncertain dynamical environment. we have identified two fundamental gaps in the current state of the art that we aim to address via the proposed study- (1) The need for a high-fidelity and computationally tractable model-based approach for cislunar objects orbit prediction and uncertainty quantification; and (2) The potential of machine learning (ML) methods to combat the curse of dimensionality and provide rapid, accurate, and robust orbit predictions paving the way to real-time solutions onboard space flight hardware.

Document Details

Document Type
DoD Grant Award
Publication Date
Mar 14, 2024
Source ID
FA95502310677

Entities

People

  • Tarek Elgohary

Organizations

  • Air Force Office of Scientific Research
  • United States Air Force
  • University of Central Florida

Tags

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Aerospace Engineering.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • Space
  • Space - Orbital Debris
  • Space - Space Objects