Obstacle detection on rail-tracks: Study on situations for requirement specification

Transportation research procedia, vol. 72, pp. 884–891

Abstract

With the advance in technologies that enable assisted and driverless operations, developing detection systems that can detect any obstacle within a train's clearance gauge is critical. As a first step, it is vital to understand the hazardous track situations resulting in railway accidents. Currently, to the best of our knowledge, no public railway databases that document accident situations focus on obstacles on or near the tracks. In this study, we collect railway accident reports from different sources and establish a database2 of collisions and near-misses, including descriptions of the obstacle involved. Furthermore, our analysis provides a comprehensive list of obstacle classes and critical scenarios to consider during the development and testing of obstacle detection frameworks for a railway system.

Authors 4

1. Philipp Leibner Aachen chair Institute for Rail Vehicles and Transport Systems

   RWTH Aachen University

   Affiliation as printed

   Chair and Institute for Rail Vehicles and Transport Systems, RWTH Aachen University, Aachen. Germany

2. Harish Manjunatheswaran Aachen chair Institute for Rail Vehicles and Transport Systems

   RWTH Aachen University

   Affiliation as printed

   Chair and Institute for Rail Vehicles and Transport Systems, RWTH Aachen University, Aachen. Germany

3. Akke Schotten Aachen chair Institute for Rail Vehicles and Transport Systems

   RWTH Aachen University

   Affiliation as printed

   Chair and Institute for Rail Vehicles and Transport Systems, RWTH Aachen University, Aachen. Germany

4. Christian Schindler Aachen chair Institute for Rail Vehicles and Transport Systems

   RWTH Aachen University

   Affiliation as printed

   Chair and Institute for Rail Vehicles and Transport Systems, RWTH Aachen University, Aachen. Germany