ARTIFICIAL INTELLIGENCE-ENABLED MULTI-MISSION RESOURCE ALLOCATION TACTICAL DECISION AID

Abstract

The Department of Defense supports many military platforms that execute multiple missions simultaneously. Platforms such as watercraft, aircraft, and land convoys support multiple missions over domains such as air and missile defense, anti-submarine warfare, strike operations, fires in support of ground operations, intelligence sensing and reconnaissance. However, major challenges to the human decision-maker exist in allocating these multi-mission resources such as the growth in battle-tempo, scale, and complexity of available platforms. This capstone study seeks to apply systems engineering to analyze the multi-mission resource allocation (MMRA) problem set to further enable artificial intelligence (AI) and machine learning tools to aid human decision-makers for initial and dynamic re-planning. To approach this problem, the study characterizes inputs and outputs of a potential MMRA process, then analyzes the scalability and complexity across three unique use cases: directed energy convoy protection, aviation support, and a carrier strike group. The critical findings of these diverse use cases were then assessed for similarities and differences to further understand commonalities for a joint AI-enabled MMRA tool.