Densely-Packed Target Data Fusion for Naval Mission-level Simulation Systems MP 11-10

Current Department of Navy (DON) mission-level simulators are not adequate for detection and data fusion (DFF) in target-dense environments for the support of robust determination or evaluation of COAs. This is due to inadequate handling of the ambiguities in track correlation and the subsequent effects on situational awareness (SA). Metron proposes solutions that address the difficulties inherent to all-source fusion of multi-Int data, through innovative correlation techniques, anomaly detection, ambiguity resolution, adversary action, and the treatment of low-resolution sensors. As data fusion often involves a human element, Metron shall consider agent-based modeling (ABM) techniques to effect the clustering and correlation of observations and to determine threat intent based on both historical context and the experience bias and learning curve of the agent. Metron shall consider how each layer of fusion as defined in the JDL (Joint Directors of Laboratories for the DOD) functional model contributes to the decision space and the uncertainties thereof. Furthermore, Metron shall consider optimization techniques for process refinement. The development of these DDF techniques has direct application for effective Information Operations (IO), Maritime Domain Awareness (MDA), and Maritime Interdiction Operations (MIO), as well as training applications.