You are here

Adaptive Markov Inference Game Optimization (AMIGO) for Rapid Discovery of Evasive Satellite Behaviors

Award Information
Agency: Department of Defense
Branch: Air Force
Contract: FA8750-18-C-0106
Agency Tracking Number: F17C-T02-0039
Amount: $150,000.00
Phase: Phase I
Program: STTR
Solicitation Topic Code: AF17-CT02
Solicitation Number: 2017.0
Timeline
Solicitation Year: 2017
Award Year: 2018
Award Start Date (Proposal Award Date): 2018-04-24
Award End Date (Contract End Date): 2019-04-24
Small Business Information
20271 Goldenrod Lane
Germantown, MD 20876
United States
DUNS: 967349668
HUBZone Owned: No
Woman Owned: Yes
Socially and Economically Disadvantaged: Yes
Principal Investigator
 Dan Shen
 (301) 515-7261
 dshen@intfusiontech.com
Business Contact
 Yingli Wu
Phone: (301) 515-7261
Email: yingliwu@intfusiontech.com
Research Institution
 Texas A&M University
 746000531
 
Office of Research and Sponsored Programs
College Station, TX 77843
United States

 (979) 862-2914
 Nonprofit college or university
Abstract

Space superiority requires space protection and space situational awareness (SSA), which rely on rapid and accurate space object behavioral and operational intent discovery. The focus of this project is to develop a stochastic approach for rapid discovery of evasive satellite behaviors. Designing the innovative decision support tool has numerous challenges: (i) partial observable actions; (ii) evasive resident space objects; (iii) uncertainties modeling and propagation; (iv) real-time requirement and computational intractable algorithms.We propose a solution called Adaptive Markov Inference Game Optimization (AMIGO) for rapid discovery of evasive satellite behaviors. AMIGO is an adaptive feedback game theoretic approach. It gets information through sensors about the relations between the RSOs and ground/space surveillance assets (SAs). The relations are determined by both the RSOs and SAs. Therefore, it is a game instead of control problem. The game reasoning interacts with data level fusion, the uncertainty modeling/propagation, and RSO detection/tracking to predict the future RSOs-SAs relations. The game engine also supports optional space pattern dictionary/semantic rules for adaptive transition matrices in our Markov game. The outputs of our game reasoning include two kinds of controls: one for SAs and the other for RSOs. The two sets form a game equilibrium.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government