Autonomous Recharging and Flight Mission Planning for Battery-Operated Autonomous Drones

Unmanned aerial vehicles (UAVs), commonly known as drones, are being increasingly deployed throughout the globe a means to streamline monitoring, inspection, mapping, and logistic routines. When dispatched on autonomous missions, drones require an intelligent decision-making system for trajectory planning tour optimization. Given limited capacity of their onboard batteries, key design challenge is ensure underlying algorithms can efficiently optimize mission objectives along with recharging operations during long-haul flights. With this in view, present work undertakes comprehensive study automated management systems energy-constrained drone: (1) We construct machine learning model that estimates energy expenditure typical multi-rotor while accounting real-world aspects extrinsic meteorological factors. (2) Leveraging model, joint program flight optimization formulated multi-criteria Asymmetric Traveling Salesman Problem (ATSP), wherein drone seeks time-optimal energy-feasible visits all target sites refuels whenever necessary. (3) devise efficient approximation algorithm provable worst-case performance guarantees implement it system, which supports real-time path tracking re-computation dynamic environments. (4) The effectiveness practicality proposed approach validated through extensive numerical simulations well experiments.