Applications of multi-objective evolutionary algorithms to air operations mission planning

Abstract

Air operations mission planning is a complex task, growing ever more complex as the number, variety, and interactivity of air assets increases. Mission planners are responsible for generating as close to optimal taskings of air assets to missions under severe time constraints. This function can be aided by decision-support tools to help ease the search process through automation. This paper presents several applications of multi-objective evolutionary algorithms for discovering suitable plans in the air operations domain, including dynamic targeting for air strike assets, intelligence, surveillance, and reconnaissance (ISR) asset mission planning, and unmanned aerial systems (UAS) planning. Lessons learned from these studies are described and an exploration of potential future directions is discussed.