Aston University develops AI traffic lights in bid to cut queues

Artificial intelligence has been used to construct traffic signals, which academics believe will dramatically reduce lineups.

Aston University created the technology, which scans live video footage and adjusts the lights to compensate, keeping traffic flowing.

Developers created a traffic simulator to educate the algorithm how to handle various circumstances.

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

According to experts, the system is capable of learning, allowing it to attempt new ways if queues begin to form.

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

"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."

According to the university, traffic congestion in metropolitan areas in 2019 may cost drivers 115 hours of time and £894 in wasted fuel and lost revenue.

It said that the application may be set up to watch any actual or simulated traffic intersection and will begin learning on its own.
Previous Post Next Post