Train Driver’s Intelligent Visualization and Early Warning Unit
When driving trains, the drivers control the freedom of the track ahead from foreign objects and people relying solely on their visual perception and the signal aspects. According to experimental data, the range of obstacle detection by a train driver is between 300 and 400 m during the day and between 100 and 200 m at night. Weather conditions, such as fog, rain, sun glare, etc., make it much more difficult to detect objects, reducing the level of train traffic safety. The train driver assistance system warns on the presence of obstacles ahead of the train detected at a distance of up to 1200 m and displays the aspects of trackside signals at distances of up to 400 m.
Artificial Intelligence And Digital Services
Artificial intelligence
The project was initiated in 2023 and is undergoing prototype testing with potential commercial operation and mass deployment in 2025.
The prototype is installed on a mainline locomotive and is being tested by JSC Russian Railways (Oktyabrskaya Railway).
• Improved train protection and transportation safety; • Operation under adverse weather conditions (thick fog, heavy rain, high temperature); • Identification of obstacles at distances greater than can be reliably estimated by a person; • Reduced number of falsely interpreted signal aspects and temporary signs; • Enabling the transition to fully automatic train control; • Registration and long-term storage of video recordings of emergency situations and incidents for engagement with law enforcement agencies and insurance companies.
Nominated for the first time. Since the beginning of the pilot project, patents that were developed by the project team and duly registered have received several prizes and awards of international innovation and invention shows.
Patents and registration certificates: KKhatlamadzhyan A.E., Popov P.A., Chebotarev E.S., Kataenko A.A. Articles: • Popov. P.A. Application of AI technologies in railway transport. Railway Equipment Journal 2024;1(65):22-25. (in Russ.) • Popov P.A., Tsvetkov A.A., Kudryashov S.V. [MCC automatic control scenarios]. Zheleznodorozhny transport 2023;9:41-43. (in Russ.) • Kudryashov S.V., Popov P.A., Metky M.G., Fuyarchuk K.G. [Calibration system for onboard machine vision systems]. Zheleznodorozhny transport 2023;5:31-33. (in Russ.)
