Increasing Automation on First Responders Reaction When Deploying Heterogeneous Fleet of Drones in Emergency Scenarios

Drones are becoming a very frequent and useful tool for emergency responders in supporting disaster management actions, but most emergency responders' fleets end-up in a plethora of drones with heterogeneous performances. In case of a major disaster all available resources are welcome. The allocation of task to each drone must be done taking into account the characteristics of the vehicle and of the payload, and must be done fast. In this work we present a methodology for the planning of drone trajectories for the surveillance of an area, using each available asset according to its potential and with the objective to obtain the full area scanned in the fastest possible time. This methodology accounts for no-fly zones that drones must completely avoid. Results show that, in less than 2 minutes, the trajectories of all the drones of an heterogeneous fleet can be generated to efficiently cover the area with a uniform precision, and less flight distance compared to the best state-of-the-art methods. The comparison of different area partition algorithms shows that it may be better to simplify the area for a better split despite the increase of area to cover.