Intercepting Unmanned Aerial Vehicle Swarms with Neural-Network-Aided Game-Theoretic Target Assignment
This paper examines the use of neural networks to perform low-level control calculations within a larger game-theoretic framework for drone swarm interception. As unmanned aerial vehicles (UAVs) become more capable and less expensive, their malicious use becomes a greater public threat. This paper examines the problem of intercepting rogue UAV swarms by exploiting the underlying game-theoretic nature of large-scale pursuit-evasion games to develop locally optimal profiles for target assignment. It paper also examines computationally efficient means to streamline this process.