Artificial Intelligence To Increase Train Efficiency

19th November 2018

Indian Pacific_Desert Bridge

Software company 4Tel has been working with students from the University of Newcastle to develop artificial intelligence (AI) robotics technology that can be used in trains.

"The technology certainly has the potential to create autonomous trains, and that will happen in tunnels or closed systems," said Derel Wurst, managing director of 4Tel.

The AI technology will improve the safety of trains, make them more efficient and lessen wait times for commuters in major cities.

"We see that the most immediate application is to make the drivers work safer and help the driver, not replace the driver," Mr Wurst said.

"For the travelling public, the future AI agents will improve the safety of the system because they will not get tired or distracted," he said.

Engineering students from the University of Newcastle step off campus once a week to work with technical staff at 4Tel to apply deep learning concepts to problems that occur in train safety.

"As for running on time… the ability to get on the train and know that it's going to get to the destination when promised is fundamentally what people are after, and any improvements in the processes to enable that to happen are going to be appreciated by the public," Mr Wurst said.

The technology to be implemented will resemble AI technology used in the autonomous car industry. It will involve attaching a radar with various cameras that will measure distances, detect incidences and assess speed and weather conditions.

"And while we won't be able to stop all accidents by any means - we are hopeful that we will be able to intervene a lot quicker, sooner and effectively than what's happened in the past," Mr Wurst said.

"Australia has a good safety record, but if I can generalise that to look around the world, a lot of the accidents come about by staff being distracted, obstacles on the track, or something gone wrong in the infrastructure… and most of those items are candidates to be detected by artificial intelligence," he said.