4Tel and University of Newcastle Robotics are working together to develop specialist artificial intelligence and deep machine learning systems for use in the rail environment. Using driverless car technologies, our team has been able to use the hardware systems to develop 'Horus' which is an artifical intelligent system to assist train drivers in detecting hazards in the rail corridor.
Rail corridors rarely change making it ideal to explore and develop real-time visual detection software. By capturing the corridor master sequence and then using on-board super-machine visual processing, the corridor information is cross checked with a detailed database enabling the system to detect if a trespasser or object is in a potentially dangerous position to the trains path. While the system won't stop incidents from happening, it will minimise the impact from earlier response.
The system is also deisgned to aid driver safety through engaging in detecting the signal aspect and alerting the driver to potential issues, like a Signal Passed at Danger (SPAD) or exceeding the trains authority.
The benefits are yet to be realised but the expected outcomes include:
- As an on-board processor, the system is designed to meet the needs of trains operating across multiple open access rail networks
- Instantaneous sharing of obstructions, hazards and other issues in the network to other trains and the network control centre
- Immediate updates of software improvements by using the best of Internet-of-Things (IoT) technologies
- Real-time reporting of events creates meaningful data for business performance
- Independence from below rail operators/maintainers in driver performance information
- The system will work in cities, regional and rural areas of Australia and can be applied to international markets
The system is currently under development with an expectation that it will be commissioned into operation within 2018.
Contact us for more information.