Adaptive Management and Mitigation of Uncertainty in Fusion (AMMUF)

Missile defense takes place in an uncertain and dynamic environment, so multi-sensor fusion must be employed to aggregate and merge disparate data from the battlefield. However, the fusion process is hindered by the vast amount of uncertainty in operational contexts, such as imprecise measurements and varying environmental conditions. Various algorithms and fusion processes have been developed to manage this uncertainty so that accurate assessment of threats can still be obtained. However, little effort has been made at determining which methods and algorithms are best suited under different conditions and uncertainty models. In our Adaptive Management and Mitigation of Uncertainty in Fusion (AMMUF) project, we will use decision-theoretic probabilistic relational models (DT-PRMs) to model the fusion process and the different design and algorithmic decisions that can be made by system engineers and fusion operators. DT-PRMs can determine optimal decisions under inherent domain uncertainty in a variety of operational conditions. Our AMMUF tool will enable system engineers to determine the optimal fusion configuration in different missile defense contexts, giving battlefield operators the most accurate and efficient information about missile threats. Approved for Public Release 14-MDA-7663 (8 January 14)