Search papers, labs, and topics across Lattice.
This paper introduces a novel UAV inspection path planning (IPP) algorithm for 3D surfaces that integrates normal vector filtering and integrated viewpoint evaluation (IVE) to improve path quality, inspection efficiency, and overall inspection quality. The algorithm generates viewpoints through uniform sampling and normal vector filtering, then employs an IVE method combined with Monte Carlo tree search for viewpoint selection, leading to optimized inspection paths. Simulation and real-world experiments demonstrate significant improvements in path length, inspection time, planning time, and defective coverage ratio compared to existing methods.
Achieve up to 80% faster UAV 3D surface inspections with a new path planning algorithm that smartly filters viewpoints and optimizes path selection.
The use of unmanned aerial vehicles (UAVs) for three‐dimensional (3D) surface inspection has become an important tool in the field of large‐scale structure maintenance. However, the commonly used UAVs inspection path planning (IPP) algorithms for 3D surface suffer from problems, such as path quality‐dependent model accuracy, path inspection efficiency, and low inspection quality. To address these issues, this paper proposes a UAV 3D surface IPP algorithm based on normal vector filtering and integrated viewpoint evaluation (IVE). Generate a safe and effective set of viewpoints through uniform sampling and normal vector viewpoint filtering, and then use an IVE method combined with Monte Carlo tree search to select viewpoints, thereby generating a safe, efficient, and complete UAV surface inspection path. Simulation results show that the proposed method reduces path length by up to 72.5%, inspection time by up to 80.6%, planning time by up to 54.3%, and defective coverage ratio by up to 55.8% compared with existing algorithms. Real‐world experiments on the sail sculpture and the Terracotta Warrior sculpture further illustrate the efficiency of the algorithm, successfully collecting high‐quality surface data and validating its practical applicability for 3D structural inspections.
