AI experts join drive for safety on UK rail crossings

Credit: Synoptix

Leicester researchers are lending their artificial intelligence (AI) expertise to a prototype device designed to improve safety on the UK’s rail network.

Experts from the University of Leicester’s School of Computing and Mathematical Sciences, working as part of an Innovate UK Knowledge Transfer Partnership (KTP) with systems engineering specialists Synoptix, have this week installed a prototype device at a Network Rail-operated level crossing on one of the UK’s busiest rail lines.

The OPTIMUS prototype uses machine learning and an AI-based object detection system, hosted locally on the device, to identify and quantify different types of traffic using the level crossing near Cheltenham, Gloucestershire. The crossing is located on the Cross Country Route and sees up to 130 trains a day.

Software developed by Leicester researchers will detect road users including pedestrians and cyclists on, and close to, the crossing and generate statistical reports characterising relevant parameters of traffic. This locally-processed data can then be relayed in a condensed form to a Network Rail control centre in real time. Further iterations will develop this detection capability in greater detail.

Image courtesy of Synoptix Ltd with promotional support from University of Leicester.

The Leicester team includes Professors Ivan Tyukin and Alexander Gorban, Dr Bogdan Grechuk, Tatiana Tyukina and George Leete, all of the School of Computing and Mathematical Sciences.

George Leete is KTP Research Associate within the Artificial Intelligence, Data Analytics, and Modelling (AIDAM) Centre at the University of Leicester, and leads development of the machine learning aspect of the project under the supervision of Professor Ivan Tyukin. He said:

“The deployment of the initial prototype at the level crossing marks a huge milestone for the project, as well as the safety of the wider UK rail network. Through the accurate real time census data gathered via the OPTIMUS prototype, Network Rail will be able to accurately evaluate the risk at the level crossing and adjust safety procedures as required. The hope is to expand the deployment of the device to all of Network Rail’s near 6,000 level crossings, making the UK rail network safer for all.”

Professor Tyukin added: “The importance of this project and its current progress is difficult to overestimate. In addition to addressing an important technical challenge we aim at developing a solution to this challenge which is certifiably robust, reliable, stable, maintainable, and trustworthy. This is an excellent opportunity to demonstrate the impact of our research in the area of reliable, maintainable, and stable AI on increasing public safety in the UK.”

According to Network Rail, which is responsible for the country’s rail infrastructure, there are around 6,000 level crossing in the UK. Figures for 2019/20 show that there were 316 near misses with pedestrians on UK level crossings, and two pedestrian fatalities.

All crossings are regularly assessed for risk, and while Network Rail has closed more than 1,250 level crossings since 2009, their strategy also includes enhancing safety at other sites. 

This device is planned to operate for an initial trial period of four months in its current location, with further trials planned in partnership with Synoptix. The KTP is funded by Innovate UK.

Justin Mountjoy, Programmes Director at Synoptix, said: “This is an exemplary of Leicester University and Synoptix combining to rapidly innovate a highly technical and effective Artificial Intelligence solution which promises not only to improve the census gathering techniques required by Network Rail, but also to roadmap the long-term objective of significantly improving safety throughout the entire rail network.

“Synoptix will be working over the forthcoming months to develop Optimus into a fully certified System with the potential to be integrated into the Network to optimise Level Crossing and Safety Barriers thus improving overall safety and reduce major incidents.”

Synoptix provides multi-disciplinary systems engineering support across various technical industries. The organisation is certified by the Railway Industry Supplier Qualification Scheme (RISQS) for the provision of Systems and Safety Engineering Consultancy to the Rail Industry.

Credit: Synoptix