Real-time wildfire monitoring with a fleet of UAVs

This paper introduces a wildfire monitoring system based on fleet of Unmanned Aerial Vehicles (UAVs) to provide firefighters with precise and up-to-date information about propagating wildfire, so that they can devise efficient suppression actions. We present an approach plan trajectories for fixed-wing UAVs observe evolving over time by tailoring the Variable Neighborhood Search metaheuristic problem characteristics. Realistic models terrain, fire propagation process, are exploited, together model wind, predict spread accordingly motions. Algorithms integrated within software architecture allowing tests real simulated flying synthetic wildfires. Results mixed-reality test campaign show ability proposed effectively map propagation.