LiDAR laser sensors enable digitalization of freight train operations

Overview

To monitor track areas during freight train shunting, even when reversing, a team of five partners including FH Aachen is developing a track monitoring system—SAMIRA shunting assistance system. This involves fusing LiDAR point clouds with camera data to accurately detect objects in the tracks. This digital step saves human resources while laying the foundation for automatic railway operations, enabling safe and efficient freight train shunting.

01 Freight Train Shunting Assistance System

Project Challenge

轨道区域的手动监控越来越难以执行。迄今为止，调动货运列车一直是两人的工作。如果列车向后移动，调车助手必须站在最后一节车厢上，通过无线电通知机车司机轨道区域是否有任何障碍物。这项任务必须在风和日丽的天气中执行，而且存在一定的风险，因此很难找到从事此项工作的人员。虽然列车司机可以通过远程控制自己承担这项任务，需要他们在改变方向时必须走遍列车的整个长度，这非常耗时。也不是最佳解决方案。

Solution

The freight train shunting assistance system developed by the project team takes over track monitoring and provides support to locomotive drivers. The assistance system monitors the entire track area during shunting operations and detects obstacles . This portable battery-powered device is installed at the rear of the train. It contains various sensors for environmental detection and a computer for data processing.

Integrated sensors include two Blickfeld LiDAR sensors for 3D obstacle detection , a stereo camera for short-range detection, two additional cameras providing the data basis for algorithm-based object detection, and a radar sensor. Additionally, the system features a sound warning signal. The locomotive driver is equipped with a tablet in the cab that displays the track area behind the train in real time and indicates objects, personnel, signals, or other vehicles within the monitoring zone.

These objects are detected by fusing camera images and 3D point clouds. Image recognition algorithms identify track areas and objects based on camera images, but they cannot determine the exact position of the objects; only fusion with the point cloud achieves this step. Ensure that the train's path remains unobstructed during reversing without the shunting assistant.

02 Fusion of camera images and LiDAR 3D point clouds

在列车调动应用中，Cube1的70°水平视野非常适合密切关注轨道区域，即使在轻微转弯时也是如此。因为铁路运营中的振动非常大，传感器技术必须保证非常稳健 。Blickfeld 传感器的固态特性能够满足以上要求，并且以低廉的价格提供高分辨率的点云数据也很突出。因此，负责LiDAR和摄像头系统的FH Aachen决定将 Blickfeld传感器技术集成到系统中。

Matthias Blumenschein (Research Assistant Rail Vehicle Engineering, FH Aachen University of Applied Sciences) stated: "Blickfeld's LiDAR sensor technology is exactly what we expected in terms of price, resolution, and field of view . "

03 Outlook

To more comprehensively protect train shunting operations, the next step will be to introduce a project concept for fixed modules used in track inspection. Behind curves or other sections where visibility is difficult for the driver, the system can send real-time information to the cab to enable timely braking when necessary. In the second phase, this technology can serve as a first step toward achieving automatic operation.