A Transferable Belief Model Approach to Combat Identification

Abstract

Combat identification (CID) is the process of accurately characterizing battlespace entities to enable high-confidence, real-time application of tactical options, such as engagement. Evidence to support CID estimates is often sparse, latent in the battlefield, or both, raising the risk of association ambiguity and potential loss of CID custody. Therefore, an automated CID estimation methodology must properly account for and convey its results’ uncertainty, ambiguity, and ignorance to the warfighter to support timely, well-informed decision-making. The automated CID estimation process presented in this article is a computationally scalable approach to achieve robust CID custody in over-the-horizon targeting applications. Novel aspects of this approach include (1) a compact representation of track histories as tracking segments (vice measurements); (2) a temporal history of kinematic ambiguities between tracks; and (3) a transferable belief model for open-world evidential reasoning under uncertainty, ambiguity, and conflict. The result is an actionable, informative CID estimation process that accounts for real-world challenges and constraints.