Drone mapping through multi-agent reinforcement learning

In recent years, the use of drones to map environments and survey them for items of interest such as forest fires, landslides or wild animals has gained traction in various research communities. However, the need for a human pilot or a pre-planned flight path severely limits the effectiveness of the drones, especially when a whole swarm is used. In this work, we propose a model of the drone survey problem and apply three well-known reinforcement learning strategies, showing that the performance loss due to the lack of explicit optimization and pre-programmed knowledge of the system statistics is negligible in the swarm scenario.