UAV Path Planning for Outdoor High-Voltage Transmission Line Inspection Based on Point Cloud Data

Abstract To address the challenges of dense obstacles and complex spatial structures in high-voltage transmission line inspection environments, as well as the difficulty of balancing search efficiency and path quality in traditional path planning algorithms, this paper proposes a Multi-source Adaptive Tornado Optimization algorithm (MA-TOC) for UAV 3D path planning. First, a 3D environment model satisfying flight safety constraints is constructed based on LiDAR point cloud data. Second, a triple-layer heterogeneous cyclone sampling mechanism, an adaptive step-size adjustment strategy, and a local stagnation escape mechanism are introduced to enhance the global exploration capability and adaptability to complex environments. Furthermore, directional continuity constraints are incorporated to optimize the quality of the generated paths. Finally, path planning experiments are conducted in real high-voltage transmission line point cloud scenarios. Comparative experiments against APF, RRT, RRT*, and A* demonstrate that MA-TOC can rapidly generate safe and smooth inspection trajectories and achieves a favorable balance among planning reliability, computational efficiency, path smoothness, and obstacle avoidance performance.