Keywords: VTOL UAV, BVLOS (Beyond Visual Line of Sight), LiDAR, 3D point cloud, railway maintenance, snow cornice.

This paper evaluates the feasibility of utilising vertical take-off and landing unmanned aerial vehicles and portable vehicle-mounted light detection and ranging systems for the maintenance of railway structures in mountainous and heavy snowfall regions. Field demonstration tests were conducted to address labor shortages and infrastructure ageing. The vertical take-off and landing aircraft successfully captured high-resolution imagery over a twenty-kilometre section within twenty minutes under the newly established regulatory framework in Japan, enabling rapid digital twin construction and real-time situational streaming via cellular networks. Concurrently, the vehicle-mounted system demonstrated robust through-window data acquisition from an operating train under wintry conditions, achieving a dimensional accuracy within fifty millimetres. By employing a point cloud change-detection algorithm, the system successfully quantified snow overhang lengths at tunnel portals, providing a data-driven basis for prioritizing snow removal operations. The integration of these complementary technologies offers a highly efficient, multi-scale framework that bridges the gap between conventional ground-based inspections and aerial surveys, significantly enhancing operational safety and disaster resilience in railway infrastructure management.

download the full-text of this paper (PDF, 2210 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description