MIT Invents App to Help Drivers Avoid Red Lights
Researchers at Massachusetts Institute of Technology (MIT) won a best-paper award recently from the Association for Computing Machinery’s MobiSys for an app they created to help drivers avoid red lights and thus use less fuel. The system works via a network of smartphones mounted on car dashboards that collect information about traffic signals.
Unlike previous in-car cellphone applications, the new system relies on images captured by the phones’ cameras, Larry Hardesty explains in an MIT News Office press release. The technology tells drivers when slowing down can help them avoid waiting at red lights.
“In addition to designing an application that instructs drivers when to slow down, the researchers also modeled the effect of instructing them to speed up to catch lights,” Hardesty writes. But, lead researcher Emmanouil Koukoumidis said, “we think that this [speeding up] application is not a safe thing to have.”
In a September 17 article for Reuters, Natasha Baker writes that the app, called SignalGuru, predicts when a traffic signal is about to change and suggests the speed a vehicle should be driven when approaching an intersection so as to avoid red lights — as well as green lights just about to turn red — so a driver can cruise through an intersection without having to stop.
MIT’s Hardesty writes:
By reducing the need to idle and accelerate from a standstill, the system saves gas: In tests conducted in Cambridge, Mass., it helped drivers cut fuel consumption by 20 percent.
Cars are responsible for 28 percent of the energy consumption and 32 percent of the carbon dioxide emissions in the United States, says Emmanouil Koukoumidis, a visiting researcher at MIT who led the project. ‘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,’ Koukoumidis says.
Koukoumidis said the app only recommends speeds within legal speed limits, Baker reports. She notes the fact that not all locales have computerized traffic signals, “[b]ut this could also pose safety concerns, for example, a signal not changing when predicted due to inaccuracies.”
“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 Baker. He added that is similar to a driver’s being smart to not blindly follow a navigation device, but rather should use his or her own judgment.
The research team tested the app in Cambridge, Massachusetts, which traffic lights adhere to fixed schedules, and in Singapore, where the signals vary continuously according to fluctuations in traffic flow, Hardesty writes. “The good news for the U.S.,” Koukoumidis says, “is that most signals in the U.S. are dummy signals” — signals with fixed schedules. He said predictions for variable signals will improve as more cars use the system, thus collecting more data.
Baker writes that the researchers are looking for industrial partners in order to commercialize the software, and when they find them they plan to implement other safety features, such as thresholds on deceleration. One obstacle to bringing the app to the market, according to Marco Gruteser, an associate professor of electrical and computer engineering in the Wireless Information Network Laboratory at Rutgers University, could be finding a way to get a large number of people to use the app, Hardesty reports. “There’s a lot of people who have to use the system to provide fresh sensing data,” Gruteser said.