Monte Carlo Tree Search and Convex Optimization for Decision Support in Beyond-Visual-Range Air Combat

Air combat is a high-risk activity where pilots must be aware of the surrounding situation to outperform the opposing team. The chances of beating the opposing team improve when the pilots have superior situation awareness, thus allowing them to act before the opposing team can do counteractions. In a highly dynamic environment, such as air combat, it can be difficult for pilots to track all adversarial units and their capabilities. In this work, we propose a combination of Monte Carlo Tree Search (MCTS) and Convex optimization to help pilots analyze the situation and be aware of any potential risks associated with missile guidance in Beyond Visual Range air combat. Our process uses MCTS to assess the best action from an opposing aircraft perspective. At the same time, the convex optimization problem searches available aircraft trajectories that enable missile guidance in relation to the opponent's potential actions. The proposed system is intended to support human decisions made by a pilot inside the aircraft or by a remote pilot operating an unmanned aerial system (UAS).