Non-disruptive rail track geometry measurement system using an unmanned aerial vehicle and a light detection and ranging sensor

The safety of train operations largely depends on the health of rail tracks, necessitating regular and meticulous inspection and maintenance. A significant part of such inspections involves geometric measurements of the tracks to detect any potential problems. Existing commercial track geometry measurement processes typically rely on dedicated on-track inspection vehicles. These solutions usually necessitate temporary track closures during the assessment period and become increasingly time-consuming as the inspection area expands, resulting in significant disruptions to regular railroad operations and increased costs. To address this challenge, this paper proposes an aerial track geometry measurement system (TGMS) that utilizes an unmanned aerial vehicle (UAV) equipped with a light detection and ranging (LiDAR) sensor and an inertial measurement unit (IMU) sensor. Integrated with a state-of-the-art machine-learning-based computer vision algorithm and a simultaneous localization and mapping (SLAM) algorithm, this platform can conduct track geometry inspections seamlessly over a larger area without interrupting rail operations. In particular, this semi- or fully automated measurement is capable of measuring critical track geometry irregularities in gauge, curvature, and profile with a root mean square error (RMSE) of 1cm, 0.84 cm, and 0.87 cm, respectively. By eliminating operational interruptions, the proposed system can offer a more flexible, efficient, and cost-effective solution for inspecting and maintaining rail infrastructure.