Researchers: Artificial intelligence in connected cars reduced rush hour traffic

Content of the article

NASHVILLE, Tenn. (AP) – As millions of people travel the interstate this Thanksgiving, many will encounter traffic patches in parking lots for no apparent reason — construction or an accident. Researchers say you’re the problem.

Human drivers don’t do a good job navigating heavy traffic, but an experiment using artificial intelligence in Nashville last week suggests help may be on the way. In an experiment, specially equipped cars were able to relieve 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 better fuel economy and, by extension, less pollution.

Advertising 2

Content of the article

Content of the article

The professor of civil and environmental engineering at Vanderbilt University is one of a group of engineers and mathematicians from various universities in the United States. They study the problem of phantom jams after a simple experiment in Japan ten years ago showed how they evolved. Researchers there put about 20 human drivers on a roundabout and asked them to drive at a constant speed. It wasn’t long before 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 said.

A person hits the brakes for whatever reason. The person behind them takes a second to react and is forced to brake even harder. The next person has to brake even harder. The braking wave continues until many cars stop. Then, as the traffic clears, drivers accelerate too fast, more braking and more traffic.

Advertising 3

Content of the article

“We know that the sudden braking of a car can have a huge impact,” Work said.

Last week’s experience showed that a few cars driving slowly and steadily can have a positive effect.

The experiment used 100 vehicles driving curves on a 15-mile stretch of I-24 each morning from approximately 6:00 a.m. to 9:45 a.m. The researchers outfitted 100 of these cars to communicate wirelessly, sending traffic data back and forth, on the premise that if 5% of the cars on the road moved together, they could reduce the prevalence of phantom traffic jams.

They also benefited from the adaptive cruise control system that is now an option on many new cars. This technology allows the driver to cruise at a set speed, but the car automatically slows down and accelerates as needed to maintain a safe distance from the vehicle in front. In practice, the adaptive cruise control was modified to react to the general traffic flow, including what is happening in the distance, using artificial intelligence.

Advertising 4

Content of the article

Work said that the decision-making of cars happened on two levels. Road conditions information was used to generate the overall speed map at the cloud level. This plan is then broadcast to the cars, which use artificial intelligence algorithms to determine the best course of action to take. Using a dedicated 4-mile stretch of I-24 equipped with 300 pole-mounted sensors, the researchers were able to assess the impact of connected cars on morning traffic flow.

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.

Advertising 5

Content of the article

Liam Pedersen is deputy senior manager of research at CIRCLES consortium partner Nissan, who was in Nashville last week for the experiment. One of the interesting things about it, he says, is that it’s based on technology already in many new cars.

“It’s not autonomous driving,” he said. “That’s something we can figure out 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 builds on one Ish and his colleagues conducted in 2017 at the University of Arizona. It repeated the Japanese experiment, this time with a single self-driving car thrown into the mix. A self-driving car has smoothed traffic for 98% less braking. This led to a 40% increase in fuel efficiency and a 14% increase in driving range.

Researchers are still crunching the numbers from last week’s experiment, but Work said it “demonstrated that these congestion can be reduced through the new automated vehicle technologies we’re working on. Undoubtedly, advanced vehicle technology could significantly reduce phantom traffic if implemented on a large scale.

However, he cautioned that the technology will not suddenly eliminate congestion.

“When there are more cars on the road than the road can hold, there will always be traffic,” he said. “But it can make congestion less painful.”



Postmedia is committed to maintaining a forum for lively but civil discussion and encouraging all readers to share their thoughts on our articles. Comments may take up to an hour for moderation before appearing on the site. Please keep your comments relevant and respectful. We’ve enabled email notifications – you’ll now receive an email if you get a reply to your comment, if there’s an update on a comment thread you’re following, or a user whose comments you’re following. For more information and details on how to adjust your email settings, visit our Community Guidelines.