Enabling Robust C2 Systems through Evolvable Human-in-the-Loop Data Fusion

Abstract : Data fusion systems are being increasingly used to support military planning, decision making, and command and control functions in general. Typically, these systems are designed around the current capabilities of particular data collectors (e.g., sensors) and available processing algorithms. These algorithms incorporate an "ontology" that reflects the designer's perception of key concepts in the world (e.g., types of threats, classes of vehicles to be tracked) and how these can be parsed by the data fusion systems. As a consequence, these algorithms are limited in their ability to adapt to the dynamic changes that inevitably arise in the operational environment (e.g., new sensors, weapons, and enemy tactics). This frailty is representative of a more generic problem with current approaches to system design that result in rigid systems that are unable to evolve to keep pace with changing operational conditions. In this paper, we present the results of an analysis, design, and development effort intended to move towards robust C2 through evolvable human-in-the-loop data fusion systems. We discuss an evolvable semantic interface we have designed that enables the creation of new concepts within the fusion system, and provide an overview of the prototype evolvable data fusion system architecture we are developing.