Traffic signals that ‘learn’ could make for easier commutes

While most people today might be smarter than the average traffic signal, we could — in the future — enjoy easier commutes and better gas mileage with the help of traffic lights using human-like “intelligence.”

Using computer games and simulations, researchers at the UK’s University of Southampton have found that people — under the right conditions — can control traffic significantly better than today’s urban traffic-control computers. Following that logic, they’re working on a traffic-light system that could eventually “learn” like humans do and keep improving with continued experience.

A test recently broadcast on the BBC’s “One Show” program put presenter Marty Jopson to the test by having him use a laptop to control traffic lights at a technology testing intersection called innovITS Advance.

“The demonstration carried out at innovITS Advance indicates that the human brain, carefully employed, can be an extremely effective traffic control computer,” said Simon Box, who’s with the university’s Transportation Research Group. “In our research we aim to be able to emulate this approach in a new kind of software that can provide significant benefits in improving the efficiency of traffic flow, hence improving road space utilisation, reducing journey times and potentially, improving fuel efficiency.”

Box continued, “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 signalized junctions. This opens the way to the use of artificial intelligence approaches to traffic control such as machine learning.”


Share this

Follow Us


Get Our Emails

Stay connected