Abstract:Commander's Learning Agent

From MilcordWiki

• Caglayan, A., Burke, D. and Eaton, G. (2008) Commander's Learning Agent, Technical Report.

AFRL-RI-NY-IF- 2007-4638. AFRL, Rome, NY.

Netcentric warfare is based on the premise that integrated information networks, connecting weapon systems and warfighters, are needed to achieve information and battlespace dominance. Underlying these initiatives are the notions of complexity, agility, interoperability, and intelligence. In essence, the battlespace is increasingly complex, complexity requires agile systems, and agility requires interoperable information infrastructures and intelligent software that learns and anticipates user (human and machines) needs in dynamic environments. In this project, entitled Commander’s Learning Agent (CLearn), we researched and developed a software prototype that learns a user’s mission model and intent using a combination of passive and active techniques. While CLearn is relevant to many applications, including information security management, we describe our approach in the context of how it can be used to provide IPB (Intelligence Preparation of the Battlespace) support for planning, operations, and assessment missions in Air and Space Operation Centers (AOCs). Capturing commander’s intent manually is impractical as it requires an excessive amount of time to learn the various facets of the commander’s job. Using our approach, we demonstrate the capability to automatically capture the commander’s current mission, augment with contextual knowledge, and assign priorities to resources supporting the commander’s mission.