Research pick: Digging deep to spot obstacles - "Identification of intrusion obstacles for underground locomotives based on the fusion of LiDAR and wireless positioning technology"

Research in the International Journal of Vehicle Performance discusses a new integrated sensing and positioning system that can improve how autonomous locomotives navigate underground mining tunnels. This is one of the most challenging environments for vehicle automation, given the potential for hazards. The team has combined advanced laser-based mapping with wireless positioning and demonstrates that their system promises safer and more reliable navigation in settings where traditional sensing technologies often fail.

Underground mining poses distinct problems for autonomous vehicles. Tunnels are narrow, poorly lit, and often filled with dust and smoke, conditions that render conventional cameras almost useless and reduce the effectiveness of radar. This study addresses these challenges with a hybrid approach that pairs Light Detection and Ranging (LiDAR) sensors with Ultra Wide Band (UWB) wireless positioning.

LiDAR works by emitting laser pulses and measuring the time it takes for the light to return after bouncing off nearby objects. Unlike cameras, LiDAR does not depend on ambient light and can generate detailed 3D maps even in visually obscured environments. But the raw data it produces is often noisy and difficult to interpret, especially in cluttered or uneven spaces like those found in mining tunnels.

To refine this data, the researchers employed a technique known as multi-iteration plane fitting, which systematically isolates the ground surface from the rest of the environment. This step is essential for identifying true obstacles rather than confusing irregularities in the terrain for actual hazards. Once the ground is mapped, remaining data points, representing non-ground objects, are grouped into clusters.

Clustering in irregular environments presents its own difficulties. Traditional algorithms can misinterpret the scene, either by merging separate objects into one or splitting a single object into several false positives. The research team addressed this by analysing the scan line distribution from the LiDAR sensors, that is, the geometric pattern in which the laser sweeps across the environment. This allowed them to group points that belong to the same physical object more effectively. This approach not only improves obstacle recognition accuracy but also speeds up data processing by more than a fifth, which is important for systems operating in real time.

Wang, H., Wang, Y. and Shen, Y. (2025) ‘Identification of intrusion obstacles for underground locomotives based on the fusion of LiDAR and wireless positioning technology’, Int. J. Vehicle Performance, Vol. 11, No. 3, pp.253–277.