NASHVILLE, Tenn. — As millions of people travel the interstates this Thanksgiving week, many will encounter stretches of stopped traffic for no apparent reason — no construction or accident. Researchers say the problem is you.
Human drivers just don’t do a good job navigating heavy traffic, but an artificial intelligence experiment in Nashville last week means help may be on the way. In the experiment, specially equipped cars were able to ease rush-hour congestion on Interstate-24, researcher Daniel Work said Tuesday. In addition to reducing driver frustration, Work said less stop-and-go driving means fuel savings and less pollution overall.
The professor of civil and environmental engineering at Vanderbilt University is one of a group of engineers and mathematicians from US universities studying the problem of phantom traffic jams after a simple experiment in Japan a decade ago showed how they develop. Researchers there put about 20 human drivers on a circular track and asked them to drive at a constant speed. Before long, the traffic went from a smooth flow to a series of stops and starts.
“Phantom traffic jams are created by drivers like you and me,” Work explained.
A man slams on the brakes for a reason. The person behind them takes a second to react and has to brake even harder. The next one should stop even harder. The stop wave continues until many cars stop. Then, when traffic clears, drivers accelerate too fast, causing more braking and another jam.
“We know that the sudden stop of one car can have a huge impact,” Work said.
Last week’s experiment showed that a few cars moving slowly and steadily could also make an impact, for the better.
The experiment used 100 cars that traveled in cycles along a 15-mile stretch of I-24 from about 6 a.m. to 9:45 a.m. each morning. Working on the premise that if 5 percent of the cars on the road acted together, they could reduce the prevalence of phantom traffic jams, the researchers equipped these 100 cars to communicate wirelessly, sending traffic information back and forth.
They also benefited from adaptive cruise control, which is now an option on many new vehicles. This technology allows the driver to set the car to travel at a certain speed, but the car automatically slows down and accelerates as needed to maintain a safe distance from the car in front. In the experiment, the adaptive cruise control was modified to respond to the general flow of traffic – including what was happening far ahead – using artificial intelligence.
Decision-making by cars happens on two levels, Work said. At the cloud level, information about traffic conditions was used to create an overall speed plan. This plan was then broadcast to the cars, which used artificial intelligence algorithms to determine the best course of action to take. The researchers were able to assess the effect connected cars had on morning traffic using a dedicated 4-mile stretch of I-24 equipped with 300 pole-mounted sensors.
The experiment is a project of the CIRCLES consortium, a group that includes several automakers and the US Departments of Energy and Transportation. Other lead researchers are based at the University of California, Berkeley; Temple University; and Rutgers University-Camden.
Liam Pedersen is deputy general manager of research at CIRCLES consortium partner Nissan, which was in Nashville last week for the experiment. He said one of the exciting things about it is that it’s based on technology that’s already in many new cars.
“This is not autonomous driving,” he said. “That’s something we can realize very soon.”
Asked if automakers would be willing to cooperate to ease traffic, Pedersen said, “I certainly hope so, because the system works best when there are lots and lots of cars involved.”
Last week’s experiment is based on one Werk and his colleagues conducted in 2017 at the University of Arizona. It repeated the Japanese experiment, this time with a single self-driving car. The self-driving car smoothed out the flow of traffic so there was 98% less stopping. This resulted in a 40% increase in fuel efficiency and a 14% increase in mileage.
Researchers are still crunching the numbers from last week’s experiment, but Work said it “demonstrates that these traffic jams can be reduced through the new automated vehicle technologies we’ve developed. There’s no doubt that improved vehicle technology can significantly reduce phantom congestion when applied at scale.”
Still, he cautioned that the technology won’t suddenly eliminate congestion.
“When there are more cars on the road than the road can handle, there will always be traffic,” he said. “But it can make that congestion less painful.”