Multi-UAV trajectory planning for 3D visual inspection of complex structures

This paper presents a new trajectory planning algorithm for three-dimensional autonomous UAV volume coverage and visual inspection. The algorithm is an extension of a state-of-the-art Heat Equation Driven Area Coverage (HEDAC) multi-agent area coverage algorithm for three-dimensional domains. Given a target coverage density field, the algorithm designs a potential field to minimize the remaining density and generate trajectories using potential gradients to direct UAVs to the regions with higher potential. Collisions between agents and agents with domain boundaries are prevented by implementing the distance field and correcting the agent's direction vector when the distance threshold is reached. For visual inspection applications, the algorithm is supplemented with the camera direction control. A field containing the distance from any point in the domain to the structure surface is designed. The gradient of the distance field is calculated to obtain the camera orientation throughout the trajectory. Three different test cases of varying complexities are considered to validate the proposed method for visual inspection. The simplest scenario is a synthetic portal-like structure inspected using three UAVs. The other two inspection scenarios are based on realistic structures where UAVs are commonly used: a wind turbine and a bridge. In the inspection of a wind turbine, two simulated UAVs traversing rather smooth spiral trajectories successfully explore the entire turbine structure. The bridge test case demonstrates effective visual inspection of the complex structure and srves for comparison with the state-of-the-art in trajectory planning where the HEDAC algorithm allowed more surface area to be inspected under the same conditions. The limitations of the method are analyzed, focusing on computational efficiency and adequacy of spatial coverage to approximate the surface coverage.