Aston University develops AI traffic lights in bid to cut queues

Researchers at Aston University said they hoped to start testing on roads later this year

Traffic lights have been developed with artificial intelligence, which researchers say could significantly cut queues.

The system, developed by Aston University, reads live camera footage and adapts the lights to compensate, keeping the traffic flowing.

Developers built a traffic simulator to train the program, teaching it to handle different scenarios.

They hope to begin testing on real roads later this year.

The system is capable of learning, researchers said, allowing it to try different approaches if queues start to build.

"We have set this up as a traffic control game. The program gets a 'reward' when it gets a car through a junction," Dr Maria Chli, reader in Computer Science at Aston University in Birmingham, explained.

"Every time a car has to wait or there's a jam, there's a negative reward.

"There's actually no input from us - we simply control the reward system."

In 2019 it was estimated congestion in urban areas could lead to drivers wasting about 115 hours of time and £894 in fuel waste and lost income, said the university.

The program can be set up to view any traffic junction - real or simulated - and will start learning autonomously, it added.