Multi-Uav Trajectory Planning for 3d Visual Inspection of Complex Structures

This paper presents a new trajectory planning algorithm for 3D autonomous UAV volume coverage and visual inspection. The is an extension of state-of-the-art Heat Equation Driven Area Coverage (HEDAC) multi-agent area domains. With given target exploration density field, the designs potential field directs UAVs to regions higher potential, i.e., values remaining density. Collisions between agents with domain boundaries are prevented by implementing distance correcting agent's directional vector when threshold reached. A unit cube test case considered evaluate this strategy coverage. For inspection applications, supplemented camera direction control. containing nearest from any point in structure surface designed. gradient calculated obtain orientation throughout trajectory. Three different cases varying complexities validate proposed method simplest scenario synthetic portal-like inspected using three UAVs. other two scenarios based on realistic structures where commonly utilized: wind turbine bridge. When deployed inspection, simulated traversing smooth spiral trajectories have successfully explored entire while cameras directed curved surfaces turbine's blades. In bridge efficacious complex demonstrated employing single five methodology successful, flexible applicable real-world tasks.