Automated Reasoning Across Tactical Stories to Derive Lessons Learned

Abstract

The Military Analogical Reasoning System (MARS) is a performance support system and decision aid for commanders in Tactical Operations Centers. MARS enhances and supports the innate human ability for using stories to reason about tactical goals, plans, situations, and outcomes. The system operates by comparing many instances of stored tactical stories, determining which have analogous situations and lessons learned, and then returning a description of the lessons learned. The description of the lessons learned is at a level of abstraction that can be generalized to an appropriate range of tactical situations. The machine-understandable story representation is based on a military operations data model and associated tactical situation ontology. Thus each story can be thought of, and reasoned about, as an instance of an unfolding tactical situation. The analogical reasoning algorithm is based on Gentner's Structure Mapping Theory. Consider the following two stories. In the first, a U.S. platoon in Viet Nam diverts around a minefield and subsequently comes under ambush from a large hill overlooking their new position. In the second, a U.S. task force in Iraq diverts around a biochemical hazard and subsequently comes under ambush from the roof of an abandoned building. MARS recognizes these stories as analogical, and derives the following abstraction: When enemy-placed obstacles force us into an unplanned route, beware of ambush from elevation or concealment. In this paper we describe the MARS interface, military operations data model, tactical situation ontology, and analogical reasoning algorithm.