Autonomous UAV-based intelligent inspection framework for rail transit infrastructure:A review of technological developments
QIN Yong
MENG Fanteng
ZHANG Zicheng
MENG Tong
LIU Pengshuai
XU Liqian
CUI Jing
QIU Ninghai
YU Chongchong
WANG Zhipeng
QIN Fabo
WEN Qi
QIAN Liwen
Abstract：To address the limitations of traditional manual inspection of rail transit infrastructure,such as low efficiency,safety risks,and the dependence of existing rail-mounted detection equipment on maintenance time gaps,which leads to blind spots and limited coverage,this study develops an inte-grated"End-Edge-Cloud-Surveillance"framework for autonomous unmanned aerial vehicle(UAV)-based intelligent inspection in rail transit.At the"End"layer,multi-source perception combining vis-ible light,infrared,and LiDAR,together with visual-inertial state estimation,enables autonomous perception and task-level navigation.At the"Edge"layer,beyond-visual-line-of-sight(BVLOS)com-munication and secure,efficient data transmission mechanisms are established,alongside lightweight onboard inference for real-time defect and risk detection.At the"Cloud"and"Surveillance"layers,cross-scenario and multi-target inspection applications are conducted with global data analytics,while a low-altitude surveillance system integrating cooperative and non-cooperative surveillance is estab-lished to ensure regulatory compliance and operational safety throughout the entire process.The re-sults demonstrate that this work systematically identifies the unique challenges and characteristics of the rail transit domain and,for the first time,unifies UAV-based rail transit inspection within a full-chain"End-Edge-Cloud-Surveillance"framework.This provides a generalizable reference framework for the future deployment of autonomous UAVs in rail infrastructure inspection.
Keywords：rail transitautonomous UAVintelligent inspectionend-edge-cloud-surveillance col-laborationinfrastructure operation and maintenance
Publication Date：2025-10-30
Online Publishing Date：2025-11-06(First online date of this platform, not the publication date of the document)
Pages：31( 145-175 )