These Traffic Lights Predict Your Behavior To Give You A Speedier Commute

If all of a city’s traffic lights could speak to one another, commute times would decrease by 22%.

These Traffic Lights Predict Your Behavior To Give You A Speedier Commute
[Image: Traffic lights via Flickr / Stephan Geyer]

There should be a German word for that feeling when you desperately need to be somewhere on time, and the traffic lights seem like they’re conspiring against you. When the greens feel especially short, the reds especially long, and both appear as if they’re in cahoots to keep you idling.


It’s not a conspiracy, but it is something called fixed time control. Most intersections, if they don’t have embedded sensors under the road, abide by traffic light timing determined by observed data from years or months past. Fixed time control based on historical data is usually pretty accurate for specific intersections, but what if entire cities coordinated their traffic lights to cut down on mass commute times and fuel use?

Each color on these maps generated by Osorio’s system represents the average travel time of each car. Red represents the longest, green, the quickest.

That’s the model that MIT assistant professor Carolina Osorio and researcher Kanchana Nanduri have devised. By creating intelligent software to coordinate traffic lights modeled off of a 12,000-person system in Lausanne, Switzerland, the pair were able to decrease commute times city-wide by 22%. A subsequent paper describes how they were able to decrease fuel use, too.

Plugging all the inputs into the system wasn’t easy. First, Osorio and Nanduri had to take into account the hundreds of miniature simulators that Lausanne already developed. These smaller models, called microscopic simulators, use survey data about driver commuting behavior to try and anticipate flows through certain intersections. The surveys might ask when drivers leave in the morning, or what factors influence their decisions about different routes. Weather, the desire to read a book on public transit, and various habits all contribute to the final timing choreography at an intersection built off a microscopic simulator. Many cities have them.

City-wide, however, microscopic simulators don’t talk to one another. The timing at one intersection may very well influence congestion down the road, but traffic lights don’t acknowledge the bigger picture. The new model does.

“We’re saying [cities] can take these really complicated microscopic simulators, use this option, and have it give you suggestions on how to time your traffic lights,” Osorio says. “We designed an algorithm that gives them a better way to design their systems.“

Right now, the New York City Department of Transportation is working with Osorio’s model to create efficiencies in various Manhattan neighborhoods. But the model won’t just be used for cutting down on commute times. Just in time for the arrival of car-sharing (maybe) in the city, Osorio says that her system can also be used to predict the best placements for car and bike-sharing hubs.

About the author

Sydney Brownstone is a Seattle-based former staff writer at Co.Exist. She lives in a Brooklyn apartment with windows that don’t quite open, and covers environment, health, and data.