Vanderbilt University research shows that AI reduces traffic congestion

As millions of people travel the highways this Thanksgiving, many more will encounter patches of traffic at a standstill for no apparent reason – no construction, no accidents. Researchers say the problem is you.

Human drivers don’t do a good job of navigating in heavy traffic conditions, but an experiment with artificial intelligence in Nashville last week means help may be on the way. Researcher Daniel Work said Tuesday that in the experiment, specially equipped cars were able to ease rush-hour congestion on Interstate 24. In addition to reducing driver frustration, Work said less interrupted driving means less fuel and therefore less pollution.

The professor of civil and environmental engineering at Vanderbilt University is one of a group of engineers and mathematicians from universities across the United States who have been studying the problem of imaginary traffic jams after a simple experiment in Japan twelve years ago showed how they are evolving. There, the researchers put about 20 human drivers on a circular track and asked them to drive at a constant speed. Before long, traffic went from a smooth flow to a series of stops and starts.

“Fake traffic jams are created by drivers like you and me,” the work explained.

One person hits the brakes for whatever reason. The person behind them takes a second to react and has to hit the brakes harder. The next person should hit the brakes harder. The braking wave continues until many cars come to a stop. Then, as the traffic clears up, the drivers speed too quickly, causing more braking and another congestion.

“We know that suddenly braking one car can have a huge impact,” Work said.

Last week’s experience showed that a few cars going slow and steady can have an effect too, for the better.

The experiment used 100 cars that traveled in loops on a 15-mile section of I-24 from about 6 a.m. to 9:45 a.m. each morning. Working on the hypothesis that if 5% of the cars on the road acted together, it could reduce the prevalence of phantom traffic jams, the researchers rigged those 100 cars to communicate wirelessly, sending traffic information back and forth.

They also benefited from adaptive cruise control which is already an option on many new vehicles. This technology allows the driver to set the car to go at a certain speed, but the car automatically slows and speeds up as needed to maintain a safe distance from the vehicle in front. In the experiment, the adaptive cruise control system was modified to react to the overall flow of traffic—including what was going ahead—using artificial intelligence.

Work said the decision-making on cars was done on two levels. At the cloud level, information about traffic conditions was used to create a comprehensive speed plan. This plan was then broadcast to the cars, which used artificial intelligence algorithms to decide the best course of action to take. The researchers were able to assess the impact of connected cars on morning traffic flow using a private 4-mile stretch of I-24 equipped with 300 pole-mounted sensors.

The experiment is a project of the CIRCLES consortium, a group of several automakers and the energy and transportation divisions in the United States. Other principal researchers are at the University of California, Berkeley. Temple University; and Rutgers University-Camden.

Liam Pedersen is deputy general manager for research at Nissan, a partner in the CIRCLES consortium who was in Nashville last week for the experiment. One of the exciting things about it, he said, is that it builds on technology already in many new cars.

“This is not self-driving,” he said. “This is something we could realize very soon.”

Asked if automakers would be willing to cooperate to ease traffic, Pedersen said, “I certainly hope so, because the system works better when you’re sharing lots and lots of cars.”

Last week’s experiment built on One Work and colleagues in 2017 at the University of Arizona. It repeated the Japanese experiment, this time with a single self-driving car thrown into the mix. The self-driving car has smoothed the flow of traffic, reducing braking by 98%. This resulted in an increase in fuel efficiency by 40% and an increase in distance traveled by 14%.

The researchers are still going through the numbers in last week’s experiment, but Work said it has “demonstrated that these bottlenecks can be reduced with new automated vehicle technologies that we have developed. There is no doubt that improved vehicle technology can significantly reduce phantom traffic jams when implemented at scale.” Wide “.

Be warned, however, that technology will not suddenly eliminate congestion.

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

The new Impact Report weekly newsletter will examine how ESG news and trends are shaping the roles and responsibilities of today’s CEOs – and how they can better overcome these challenges. Subscribe here.

Leave a Reply

%d bloggers like this: