Space Object Tracking Uncertainty Analysis with the URREF Ontology

Abstract

Accurate and rapid space object behavioral tracking enables space protection and space domain awareness (SDA). Recent methods of artificial intelligence and machine learning (AI/ML) enhance space object behavior classification of evasive satellite behaviors detection within the Adaptive Markov Inference Game Optimization (AMIGO) tool. AMIGO integrates data fusion, stochastic modeling and, and AI/ML pattern classification. Numerical simulations demonstrate the advantage of using the Uncertainty Representation and Reasoning Evaluation Framework (URREF) for space ontological pattern of life assessment of veracity, precision, and recall when a resident space objects conducts a maneuver.