湖南电力 ›› 2026, Vol. 46 ›› Issue (3): 114-120.doi: 10.3969/j.issn.1008-0198.2026.03.015

• 电力人工智能与数字化 • 上一篇    下一篇

面向密闭空间无人机巡检的安全飞行走廊快速生成方法

范翔宇1, 刘三伟1, 段肖力1, 张焜怡2,3, 孙沛一3, 王甜甜3,4   

  1. 1.国网湖南省电力有限公司电力科学研究院,湖南 长沙 410208;
    2.浙江大学机械工程学院,浙江 杭州 310030;
    3.河南省智能制造数字孪生工程研究中心,河南 郑州 451150;
    4.郑州西亚斯学院计算机与软件工程学院,河南 郑州 451150
  • 收稿日期:2025-11-24 修回日期:2025-12-25 出版日期:2026-06-25 发布日期:2026-07-07
  • 通信作者: 王甜甜,副教授,博士,主要从事无人机定位与导航、图像处理、计算机视觉和数据库理论的研究工作。
  • 作者简介:范翔宇(1999),硕士,主要从事电力设备智能化、自动化巡检技术的研究工作。
  • 基金资助:
    国网湖南省电力有限公司科技项目(5216A524000F)

Rapid Generation Method for Safe Flight Corridors in UAV Inspection Over Confined Spaces

FAN Xiangyu1, LIU Sanwei1, DUAN Xiaoli1, ZHANG Kunyi2,3, SUN Peiyi3, WANG Tiantian3,4   

  1. 1. State Grid Hunan Electric Power Company Limited Research Institute, Changsha 410208, China;
    2. School of Mechanical Engineering, Zhejiang University, Hangzhou 310030, China;
    3. Henan Provincial Engineering Research Center for Digital Twin in Intelligent Manufacturing,Zhengzhou 451150, China;
    4. School of Computer and Software Engineering, Sias University, Zhengzhou 451150, China
  • Received:2025-11-24 Revised:2025-12-25 Online:2026-06-25 Published:2026-07-07

摘要: 针对变电所、电缆隧道等密闭空间高频次无人巡检需求,提出高安全、轻算力、强实时的无人机自主飞行技术。首先,构建统计方向先验,设计约束增强A*算法,在三维实现方向级剪枝,理论保持最优性,同时将搜索节点压缩30%以上;其次,提出球形凸包安全飞行走廊框架,以四维向量(球心+半径)刻画自由空间,结合K-D Tree最近障碍查询与自适应扩大采样机制,提升无人机在密闭空间导航地图表征效率。研究成果在仿真及实际电缆隧道场景中的部署证明,该方法为资源受限无人机平台在卫星拒止环境中实现毫秒级避障提供了安全高效的技术路径。

关键词: 无人机, 室内巡检, 球形凸包, 安全飞行走廊, 卫星拒止, 实时重规划

Abstract: To address the high-frequency unmanned inspection demands in confined spaces such as substations and cable tunnels, this paper proposes a set of key autonomous drone flight technologies of high safety, low computational power and strong real-time performance. First, a statistical directional prior is constructed, and a constrained enhanced A* algorithm is designed to implement directional pruning in three dimensions. This approach theoretically maintains optimality while reducing the number of search nodes by over 30%. Second, a spherical convex hull safety corridor framework is introduced, characterizing free space via four-dimensional vectors(center+radius). Combined with K-D Tree obstacle queries and adaptive oversampling, this enhances navigation map representation efficiency for unmanned aeriol vehicle(UAV) in confined spaces. Deployed in simulations and real cable tunnel scenarios, the research delivers a safe, efficient technical pathway for resource-constrained UAV platforms to achieve millisecond-level obstacle avoidance in GPS-denied environments.

Key words: unmanned aerial vehicle(UAV), indoor inspection, spherical convex hull, safe flight corridor, GPS-denied, real-time replanning

中图分类号: