Could AI Traffic Lights be the Answer to Congestion?

by - over 2 years ago

Manchester is set to trial a new AI traffic light system, which will provide quick data analysis, to improve traffic flow around the city.

The traffic lights, created by academics at the University of Huddersfield, are set to also reduce air pollution.

Innovate UK has funded a large proportion of the project, investing over £850,000 in the software developed predominantly by Professor Lee McCluskey. The first traffic lights will be tested later on this year, with a review of the results scheduled for March 2018.

The light system, SimplifAI, can analyse data faster than human operators, which means timings for traffic signals will be better optimised, traffic flow will be improved, and this reduction in congestion will also improve air quality.

The technology is set to become particularly useful on match days within the city.

"Under normal conditions, existing traffic management and traffic signals are not too bad," said McCluskey. "But it is very difficult for managers when normal conditions aren't met - for example, when Man United are playing at Old Trafford, or when an inner ring road link is closed due to an accident. There might also be bottlenecks that occur relatively frequently and you want to try to alleviate them.

"Artificial intelligence is providing a tool for transport operators so they can deal with extremely complicated situations quickly. In just a few seconds it can produce strategies composed of hundreds of different timings at traffic signals."

Depending on the success of SimplifAI, technology will be introduced worldwide. This means that cities across the globe will enjoy reduced congestion, and it will be easier to integrate driverless cars with the traffic system.

McCluskey believes that AI for the road can be enhanced further, with hopes that it will be involved in varying speed limits, message signals and lane closures.

Source: Computer Weekly.

Group Insights & Media