Researchers discover an AI traffic system that could make traffic jams a distant memory
When you’re late for work or just trying to get to that appointment, that extra driving time you spend in traffic can be more than a little frustrating. This frustration gets worse over time. The honking, shouting, and swearing can be a little too much to handle. Statistics show that in 2019 the average UK resident lost around 115 hours and £894 ($1,115) in waste fuel and lost income each year due to traffic congestion in urban areas of the UK. Ironically, we have traffic lights and road regulations aimed at reducing traffic jams, but a major cause of traffic jams comes from existing traffic lights. Studies show that inefficient traffic light timing is the main cause of the traffic jams experienced on a daily basis.
Read also : Air pollution in cities is responsible for almost two million additional deaths worldwide every year
However, researchers from Aston University have created a new AI-based AI system that uses the “principle of learned behaviors” to ensure a continuous flow of traffic. It is hoped that by using this system, long queues at traffic lights could become a thing of the past.
How does the AI traffic light system work?
Imagine a traffic light system that can quickly adapt to the situation in real time and receive information about the traffic situation. Using live camera footage, the AI traffic light reads the situation and adapts lights to compensate, keeping traffic flowing and reducing congestion. The AI system also receives feedback on the effectiveness of its work, and using deep reinforcement learning, it learns to make necessary adjustments.
Read also : The 14 most common road accidents
This system was first tested virtually using a state-of-the-art photo-realistic traffic stimulator known as Traffic 3D. The AI program was exposed to different traffic and weather scenarios, using the stimulator, thus teaching it how to handle these situations. This simulation worked on a reward system where the system got a positive reward every time it passed a car through traffic, but got a negative reward every time a car had to queue. Interestingly, the system doesn’t require any additional input to work because the only thing the researchers did was control the simulator’s reward system. The researchers also revealed that the reward system could be modified to allow the system to prioritize certain emergency vehicles such as ambulances.
Amazingly, when the system was later tested on a physical intersection, it then adapted to actual traffic intersections despite being drilled on a different simulation, showing the system’s ability to adapt to real traffic intersections. real situations.
Importance of the AI system; a world without traffic jams
Traffic congestion is a global problem and this research by scientists from the University of Aston hopes to solve this problem. The artificial intelligence system would ensure reduced driving time, increased ease in navigating the roads and, above all, reduce the frustration associated with waiting in traffic jams.
Read also : Cameras and sensors to monitor passenger health in self-driving cars
The AI traffic system is a remarkable invention that would surely greatly reduce traffic congestion around the world. The researchers hope to start testing their systems on real roads this year.
Fully autonomous, vision-based traffic light control: from simulation to reality