Hector: A Reinforcement Learning-based Scheduler for Minimizing Casualties of a Military Drone Swarm

In this paper, we consider a swarm of military drones flying over the unfriendly territory, where a drone can be shot down by an enemy with an age-based risk probability. We study the problem of scheduling surveillance image transmissions among the drones with an objective of minimizing the overall casualty. We present Hector, a reinforcement learning-based scheduling algorithm. Hector only uses the age of each detected target, the locally available information at each drone, as an input to a neural network to make scheduling decisions. Extensive simulations show that Hector significantly reduces casualties than a baseline round-robin algorithm. Further, Hector can offer comparable performance to a high-performing greedy scheduler, which assumes complete knowledge of global information.