A Reinforcement Learning-based Method To Plan The Coverage Path And Recharging Of Unmanned Aerial Vehicles

Researchers at Technical University of Munich (TUM) and University of California Berkeley (UC Berkeley) have developed a new reinforcement learning-based tool that optimizes the trajectories of Unmanned Aerial Vehicles (UAVs) throughout an entire mission, including visits to charging stations when their battery is running low. This tool is aimed at tackling the commonly underlying research problem, known as coverage path planning (CPP). The research team has been trying to devise better solutions for CPP since 2016, and their previous works have tried to tackle simpler versions of the problem.