Artificial Intelligence to Support Traffic Control in Future

University of Southampton researchers are exploring the efficiency of artificial intelligence (AI) technology to implement next-generation traffic control.

By formulating and advancing artificial intelligence-based approaches to junction control will create a revolution to existing urban and road capacity, in addition to minimizing the environmental impacts of road traffic.

The University of Southampton team uses simulations and computer games in this research that focuses on exploring ways to implement good traffic control. When presented with the right conditions, humans can better control the traffic and can show better performance than the currently-deployed urban traffic control computers, as represented by the research.

This was validated for the BBC’s ‘One Show’ programme. Presenter Marty Jopson demonstrated controlling a ‘real traffic light junction at the InnovITS proving ground via laptop. At the same time, 30 volunteer drivers made efforts to navigate the junction.

According to Dr Simon Box of the University of Southampton Transportation Research Group, the innovITS Advance demonstration shows that the human brain can function as an efficient and valuable traffic control computer, when used precisely. Through this research, the researchers anticipate emulating this approach within a new type of software that can offer major benefits such as enhancing the competence of traffic flow, enhancing road space utilization, minimizing journey times and enhancing fuel efficiency.

The Southampton researchers have recently created ‘machine learning’ traffic control computers that can be trained with the control of lights similar to a human. In addition, this computer can learn improved strategies with experience.

The research was basically funded by the Engineering and Physical Sciences Research Council (EPSRC) and is now working under Technology Strategy Board funding, where Siemens serves as an industrial partner.

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.