Skip to main content

MIT scientists develop SignalGuru app to help drivers avoid red lights and reduce fuel consumption

The Massachusetts Institute of Technology (MIT) is making strides in the field of vehicle fuel consumption.

Researchers have developed a system to help drivers avoid red lights by using a dashboard-mounted smartphone and an app called SignalGuru, Reuters reported.

With an aim to saving petrol, SignalGuru predicts when a traffic light is going to change, and provides the driver with an approximate speed to approach the intersection and cruise through the signal without stopping.

"The stop-and-go pattern that traffic signals create increases fuel consumption significantly," Emmanouil Koukoumidis, app's creator, told Reuters. He was looking for a way to help motorists save on petrol while improving the flow of vehicles.

The app works by utilising the camera on the mounted smartphone – it activates when approaching an intersection, and detects when a signal will turn from red to green, and back again. The app then determines the necessarily speed for the driver to avoid stopping at a signal just before it turns green, or getting caught traveling through a red light.

"It tells the drivers that 'if you drive at 30 miles per hour then you'll be able to cruise through without stopping," Koukoumidis said. The speed recommendations are always within legal speed limits, he promised.

The scientist reported that the US spends one-third of its annual energy consumption on transportation.

While testing the app prototype in Cambridge, Massachusetts, Koukoumidis said the researchers calculated a 20 per cent decrease in fuel consumption. When tested in Singapore, the app was less accurate, he said, but was still correct within two seconds.

But what happens if the app tells you to hit the gas at 45 mph to make it through the light before it signals for you to stop, but instead it turns to amber, then red, before you expect it to?

"SignalGuru will advise the driver when to arrive at the intersection but the driver should always check for himself that the light indeed turned green," Koukoumidis told Reuters. He compared the situation to a driver not blindly following a navigation device.

The app is not available just yet, as the researchers are still looking for partners to help commercialise the software.