If your rush-hour commute is getting you down, take heart: A duo of engineers might have a way to make it smoother.
By developing algorithms that take into account various facets of urban areas, researchers have discovered a new method for improving efficiency on city streets, cutting rush-hour travel time by 22 percent, as well as improving fuel economy and reducing emissions.
Engineers who investigate driving patterns to improve conditions in traffic-prone areas typically produce models that tackle only part of the urban scene. For instance, they might build models that assume that all vehicles are the same, or collect data that takes into account different types of vehicles, but only at the most congested streets or intersections.
But now, in a pair of papers published in the journals Transportation Science and Transportation Research: Part B, MIT professor Carolina Osorio and transportation engineer Kanchana Nanduri describe a method that can efficiently combine data at the scale of the driver with that at the scale of the entire network. With the optimization software developed by Dr. Osorio, transportation agencies could ease congestion significantly, simply by changing traffic light patterns, the authors say.
"We came up with a solution that would lead to improved travel times across the entire city," Osorio told MIT News.
To find that solution, the pair of researchers utilized traffic simulations of Lausanne, Switzerland, where Osorio lived while pursuing her doctorate in mathematics. The pair analyzed thousands of vehicles on 47 roads and at 15 major intersections over the course of a day. They then combined data from a number of aspects associated with congestion: the behavior of individual vehicles, traffic patterns across the whole of a city, and changes to drivers' routes over time.
The MIT team came up with an algorithm that is more sophisticated and more dynamic than what most cities currently use to regulate traffic flow, reports Smithsonian magazine:
Traffic-light timing systems typically work in one of two ways. On a large city or regional scale, systems set light timing based on the observed traffic; these are called flow-based models. Other simulators work on a more micro scale, taking into account the actions and habits of individual drivers. These simulators act as a sort of artificial intelligence to help predict how driver behaviors and decisions might change in given traffic conditions. It’s those minute differences and individual decisions that throw flow-based models off-kilter.
“I need to account for how people will react to my changes. If the travel times increase on an arterial [road], then people might divert," Osorio explains. “Most signal-timing software looks at current or historical traffic patterns. It doesn’t take into account how travel might change.”
But the team's investigation didn't aim only to mitigate traffic: they also studied fuel use for the purpose of creating a model that also lowers emissions. The resulting model, which integrates information about the emissions released by different vehicles, reflects the mix of cars, buses, and motorcycles that exists in real cities.
"The data needs to be very detailed, not just about the vehicle fleet in general, but the fleet at a given time," Osorio told MIT News. "Based on that detailed information, we can come up with traffic plans that produce greater efficiency at the city scale in a way that's practical for city agencies to use."
So instead of agencies having to estimate environmental impact after drawing up proposed changes to streets and intersections, planning teams will have that information already.
"We can put the environmental factors in the loop in designing the plan," said Osorio.
As of July, the New York City Department of Transportation was working with the research team to test the pair's approach in Manhattan's high-traffic areas, according to Smithsonian Magazine.