A network of dashboard smartphones that monitors traffic lights and congestion can tell drivers when to slow down to avoid idling, cutting fuel use by 20 percent, according to researchers at Princeton University and MIT.
SignalGuru (PDF) collates traffic data from images captured by dashboard smartphones.
It also graphically shows drivers how fast to go to avoid stopping at the next light; a commercial version would have audio suggestions. The system could also be developed to advise motorists to take a side street to avoid congestion ahead.
The researchers deployed iPhones on car dashboards in Cambridge, Mass., and in Singapore. In the former, where traffic signals with fixed schedules are used, SignalGuru could predict when lights would change with an error margin of two-thirds of a second. In Singapore, which has signals that adapt to traffic volume, the error increased to one second up to just over two seconds.
SignalGuru recalls user-generated traffic apps like, but could also be used to monitor things like gas prices, bus movements, and parking space availability.
The average fuels savings for the system was 20.3 percent. MIT points out in a release that about a third of U.S. CO2 emissions come from cars.
"If you can save even a small percentage of that, then you can have a large effect on the energy that the U.S. consumes," Emmanouil Koukoumidis, a Princeton PhD candidate and visiting researcher at MIT, was quoted as saying.
The SignalGuru study won a best paper award at last month's Association for Computing Machinery MobiSys conference, but would require many users to be a real solution for traffic congestion.