Researchers at the University of Southampton are investigating the use of artificial intelligence (AI) to control traffic lights. More efficient signals could help make better use of road capacity and reduce the environmental impact.
Research by the University’s Transportation Research Group found that, under the right conditions, people are good at controlling traffic flow, much better than existing urban traffic control computers. The Group is trying to emulate the human approach with new software. It has developed ‘machine learning’ traffic control computers that can be taught to control traffic lights like a human would and even learn improved strategies over time.
Dr Simon Box said “In transport research we are always looking ahead, and we can consider a future where all vehicles are equipped with WiFi and GPS and can transmit their positions to signalised junctions. This opens the way to the use of artificial intelligence approaches to traffic control such as machine learning.”
The research is funded by the Technology Strategy Board funding, with Siemens as an industrial partner.
Review: There are many ways that technology can help make transportation more efficient, saving fuel and cutting greenhouse gas emissions. As yet we’ve hardly scratched the surface.
In the case of road transport, a lot of technology has already been applied to vehicles themselves and to help drivers maximise fuel efficiency, but there’s much more that can be done to help improve road use. The most common consideration is road charging, a stick to make sure that people only drive when they need to. Ultimately that’s what needs to be achieved, but helping transport to flow more easily is a much cheaper and less painful step.
While we can all play our part through better driving habits, most other solutions to make road use more efficient and reduce emissions are heavily dependent on technology.