Algorithms for Railway Embedded Control Devices for Safety Maneuvres

Anna Beinarovica, Mikhail Gorobetz, Ivars Alps

Abstract


This study is dedicated to solve maneuvers making task while working on the station with no marshalling hump. It is a part of the project aimed at the development of intelligent safety and optimal control systems of autonomous electric vehicles and transport in general. The main maneuvers safety depends on the lack of items and other objects on the rails as well as position of turnouts. In most cases rails, occupied with other wagons, as well as wrong position of turnouts are marked with prohibiting red or blue signals of the traffic light. Authors propose an algorithm for the traffic light recognition by using Convolutional neural network (CNN) and traffic lights indicators recognition. However the situation, when locomotive needs to drive on the rails, occupied with other wagons, for example, during the manoeuvers on the railway station, can also appear. For this purpose authors have developed a CNN algorithm for the wagons recognition on the rails.

Keywords:

Convolutional Neural Network; Electric transport; Locomotive braking system; Microcontroller; Object recognition; Railway; Safety; Traffic light

Full Text:

Preview Paper

Refbacks

  • There are currently no refbacks.


Developed by Institute of Industrial Electronics and Electrical Engineering of RIGA TECHNICAL UNIVERSITY