IKADO Enhances Shunting Safety with Blickfeld LiDAR Sensors
When freight trains are shunted in reverse, train drivers have no direct view of the track ahead in the direction of travel. Traditionally, a second person positioned at the rear of the train monitors the track and communicates information about potential obstacles to the driver via radio. The SAMIRA project takes a different approach: A mobile sensor system mounted on the last wagon monitors the surroundings and provides relevant information directly to the driver in the cab.
The initial SAMIRA project successfully demonstrated the technical feasibility of such a system through a proof of concept.
With SAMIRA 2.0, development is now taking a significant step forward. IKADO GmbH, an IT systems integrator based in Aachen, Germany, is further developing the existing system for practical deployment. Key priorities include increasing software maturity, developing a robust, railway-grade housing, and optimizing the sensor technology. Blickfeld’s 3D LiDAR technology plays a central role in precisely capturing the railway environment.
The original idea behind SAMIRA addresses a specific challenge in shunting operations at industrial sites: When a freight train moves in reverse, the track behind the train must be reliably monitored for obstacles. Manual monitoring requires additional personnel, is affected by weather conditions, and places the person accompanying the train in close proximity to moving rail vehicles.
However, an assistance system must also perform this task under demanding conditions. Existing railway infrastructure, including rails, ballast, and sleepers, must be accurately distinguished from relevant obstacles under varying lighting conditions.
Monitoring the railway clearance envelope is particularly challenging. This is the space that must remain unobstructed to allow a train to pass safely. Even small objects within this area can pose a risk. At the same time, the system must avoid incorrectly classifying objects outside the train’s path, such as overhead line masts or trains on adjacent tracks, as obstacles.
The hardware must also meet demanding requirements. A train-mounted system needs to withstand vibrations, dust, moisture, and changing weather conditions.
The original SAMIRA system combined camera data with 3D LiDAR point clouds. While cameras can identify objects based on their visual appearance, LiDAR provides the depth information needed to determine their precise spatial position.
This approach continues with SAMIRA 2.0. Throughout development, LiDAR point clouds have proven particularly valuable as a foundation for developing IKADO’s own detection algorithms.
Because the system knows its direction of movement, it can analyze sensor data over time rather than relying solely on individual measurements. This makes it possible to detect objects that are initially captured by only a few scan lines. By evaluating successive measurements, the system can improve its effective detection performance.
Precise Detection Within the Railway Clearance Envelope
One of the system’s key applications is monitoring the railway clearance envelope. This requires highly accurate spatial boundaries: An object located just a few centimeters outside the relevant area must be assessed differently from an obstacle extending into the train’s path.
The 3D point cloud makes it possible to define these spatial boundaries precisely. For IKADO, this represents a significant advantage over the radar and camera technologies used in the system. While radar faces challenges in railway environments, including reflections from ballast and sleepers, LiDAR provides detailed spatial information that can be processed using IKADO’s proprietary algorithms.
New Application: Detecting Railway Wheel Chocks
The extensive work with LiDAR data has also opened up additional applications. One example is the detection of railway wheel chocks, steel wedges placed on rails to prevent rail vehicles from moving.
Because these chocks are only around 15 to 20 centimeters high and difficult to see from a distance, detecting them with cameras alone is challenging. IKADO is therefore developing an approach in which a small reflector is attached to the wheel chock, allowing its characteristic reflection to be identified in the LiDAR data.
The aim is to enable reliable detection at distances exceeding 50 meters.
Railway-Grade Hardware for Real-World Deployment
Alongside software development, the hardware has undergone significant improvements. The new housing is water-resistant and weatherproof, specifically designed to meet the demands of railway operations.
Cooling presented a particular challenge. Shunting yards are often dusty environments, making active cooling with outside air unsuitable. In collaboration with Blickfeld, IKADO therefore developed a sealed cooling concept incorporating an external heat dissipation mechanism and water cooling. The Blickfeld sensor can be mounted directly onto the cooling surfaces.
Wireless data transmission has also been upgraded compared to the initial project. SAMIRA 2.0 now uses 5G instead of Wi-Fi.
Development to date has brought SAMIRA significantly closer to practical deployment. Following the successful proof of concept in the initial project, the detection algorithms have been further refined, and the requirements of railway operations have been incorporated into the system’s development.
LiDAR technology plays a key role in detecting obstacles at short and medium ranges. Its strengths are particularly evident in the precise spatial monitoring of the railway clearance envelope, where accurate 3D detection is essential.
The next major milestone is an extended period of field testing. Trials are planned to run for several months, particularly throughout the winter, to validate the system under real operating and weather conditions. Product development will continue in parallel.
The sensor architecture may also evolve further. Rather than continuing to combine radar and LiDAR in the long term, IKADO is evaluating whether a second LiDAR sensor with different characteristics could provide a more effective redundant sensing solution.
The original SAMIRA concept is thus continuing to evolve. What began as an initiative to support train drivers during reverse shunting by providing digital information about the track ahead is being developed into a robust assistance system for real-world freight railway operations.
You are currently viewing a placeholder content from Vimeo. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationYou are currently viewing a placeholder content from YouTube. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationYou need to load content from reCAPTCHA to submit the form. Please note that doing so will share data with third-party providers.
More InformationYou are currently viewing a placeholder content from Facebook. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationYou are currently viewing a placeholder content from Instagram. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationYou are currently viewing a placeholder content from Google Maps. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationYou are currently viewing a placeholder content from Google Maps. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationYou are currently viewing a placeholder content from Mapbox. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationYou are currently viewing a placeholder content from OpenStreetMap. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More InformationYou are currently viewing a placeholder content from X. To access the actual content, click the button below. Please note that doing so will share data with third-party providers.
More Information