A new artificial intelligence system reads live camera footage and adapts the lights to compensate.
AI Traffic Light System – Making Traffic Jams a Thing of the Past
During traffic jams, the average commuter used an surplus 19 gallons of gas. This amounts to$ 160 billion in lost time and energy each time. In multiple big US megacities, traffic may waste over 100 hours per year for the typical driver. At a typical workplace, that’s enough time to take two and a half weeks off. Fortunately, experimenters are working to reduce traffic jam, whether via the development of driverless automobiles or the use of artificial intelligence in traffic lights.
For instance, long lines at traffic signals might be a thing of the past thanks to Aston University researchers ’ new artificial intelligence technology( AI). The first- of- its- kind system scans live videotape footage and adjusts the lights to compensate, keeping traffic moving and reducing jam. The system utilizes deep reinforcement knowledge, in which software recognizes when it isn’t doing well and attempts a new approach – or continues to enhance when it’s making progress. The system surpassed all other approaches in testing, which frequently depend on manually- designed phase transitions. Inadequate traffic signal timing is a major cause of jam.
The experimenters made up a state- of- the- art photograph-realistic traffic simulator, Traffic 3D, to train their program, training it to handle different traffic and weather scenarios. When the system was tested on a real junction, it thereafter adapted to real traffic crossways despite being trained entirely on simulations. It could thus be effective in numerous real- world settings. 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, for instance, 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.
For more such updates on latest news, keep reading on techinnews.com
