The first of its kind system reads live camera footage and adapts the lights to compensate, which maintains traffic flow and reduces congestion.
The system uses deep reinforcement learning, where a program understands when it is not doing well and tries a different course of action or continues to improve when it makes progress.
In testing, the system is said to have significantly outperformed all other methods, which tend to rely on manually-designed phase transitions.
In 2019, it was estimated that congestion across the UK’s urban areas led to motorists wasting around 115 hours of time – and £894 in fuel – every year, and a major cause of this situation is inadequate traffic signal timings.
To help overcome this, the researchers built Traffic 3D, a photo-realistic traffic simulator, to train their program by teaching it to handle different traffic and weather scenarios. When tested on a real junction, it adapted to real traffic intersections despite being trained on simulations, a development that could be effective in many real-world settings.
In a statement, Dr Maria Chli, reader in Computer Science at Aston University, said: “We have set this up as a traffic control game. The program gets a ‘reward’ when it gets a car through a junction. 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.”
At present, the main form of traffic light automation used at junctions depends on magnetic induction loops where a wire sits on the road and registers cars passing over it. The program counts that and then reacts to the data. Because the AI created by the Aston University team ‘sees’ high traffic volume before the cars have gone through the lights and makes its decision then, it is more responsive and can react more quickly.
Dr George Vogiatzis, senior lecturer in Computer Science at Aston University, said: “The reason we have based this program on learned behaviours is so that it can understand situations it hasn’t explicitly experienced before. We’ve tested this with a physical obstacle that is causing congestion, rather than traffic light phasing, and the system still did well. As long as there is a causal link, the computer will ultimately figure out what that link is. It’s an intensely powerful system.”
According to the team, the program can be set up to view any traffic junction – real or simulated – and will start learning autonomously. The reward system can be manipulated to encourage the program to let emergency vehicles through quickly; but the program always teaches itself, rather than being programmed with specific instructions.
The researchers hope to begin testing their system on real roads this year.