RAILGAP targets the definition of an advanced concept for high fidelity references through the design and development of innovative data-fusion algorithms able to exploit the EGNSS signals and data coming from other independent sensors as IMU, LIDAR and Camera, for elaborating high accuracy ground truth and trackside digital map.
Key Technical Objectives
- Develop a methodology and the related tools to build a novel High Precision and Accurate, Reliable Ground Truth based on EGNSS as primary source with Confidence Interval by using Trains in Commercial Service. Building the Ground Truth does not require installation of equipment on the signalling trackside or any modification to the existing signal trackside;
- Acquire Measurements from EGNSS receivers and sensors such as IMUs, LIDARs, and Cameras and characterize these technologies in order to quantitatively evaluate their performances in railways environments.
- Define, select and validate FDE algorithms for computing (a) high accuracy, high precision, high integrity 1D and 3D Absolute and Relative Positions and (b) odometry information. To this end,
- FDE Algorithms will be assessed in laboratory by using the classified Normal and Degraded scenarios, and the related Ground Truth. Fault Injection techniques can be used and supported by the validation laboratory environment;
- Assessment of integrity boundaries for single or combined technologies (i.e. EGNSS, IMUs, LIDARs, and Cameras) in the railway environment will be performed;
- Build the Trackside Digital Map by using the acquired measured information through commercial trains (not dedicated diagnostic trains or not railway carriages).
- Define and develop the methodology and the toolset for performing the continuous monitoring and control of the Trackside Digital Map to detect critical deviations with respect to the version assumed being the reference Map.