Inspection Path Planning for Aerial Vehicles via Sampling-based Sequential Optimization

Unmanned Aerial Vehicles (UAVs) commonly called drones are gaining interest for infrastructure inspection due to their ability to automize and monitor large areas more securely at a lower cost. Autonomous inspection and path planning are essential capabilities for the drone's autonomous flight. In this paper, we propose a novel inspection path planning method for achieving a complete and efficient inspection using drones. A point cloud generated from a 3D mapping service is used to represent complex inspection targets and provided as the input of the path planning method. The method is designed as a sampling-based sequential optimization to calculate and optimize an inspection path while considering the limitation of the sensors, inspection efficiency, and safety requirements of the drones. The proposed method is evaluated for both the use case of bridge inspection and power pylon inspection. A comparison between the proposed path search algorithm and TSP solver is made. Furthermore, the scalability of the method is assessed with different sizes of the inspection problem.