As millions of people travel across the country over the Thanksgiving weekend, many people encounter traffic jams while parked for no reason – no infrastructure, no accidents. or Researchers say you are the problem.
Human drivers aren’t always good at navigating traffic situations, but a test using artificial intelligence in Nashville last week could help. In a test, the customized cars were able to ease rush hours on Interstate-24, researcher Daniel Work said Tuesday. In addition to reducing driver frustration, Work said less stop-and-go driving saves fuel and, in addition, results in less pollution.
The professor of civil and environmental studies at Vanderbilt University is one of a group of engineers and mathematicians from universities around the US studying the problem of airplanes after the simple experiment in Japan ten years ago showed the nature of their development. The researchers put about 20 human drivers on a roundabout and asked them to drive as fast as possible. Before long, the traffic went from smooth running to a series of stops and starts.
“Drivers like you and me made airplanes,” Work said.
Someone slams on the brakes for whatever reason. The person behind them has a second chance to respond, and should be able to break even more. The next person needs to break even more. The wave of braking continues until several cars are stopped. Then, when the traffic is free, the drivers speed up, causing more damage and another jam.
“We know that any motor vehicle can take a big hit,” Work said.
Last week’s tests showed that some small cars going fast can have the same effect, for the better.
The test used 100 cars traveling on a 15-mile stretch of I-24 from 6 a.m. to 9:45 a.m. each morning. Considering that if only 5% of the cars on the road cooperated, they could reduce the amount of traffic, so the researchers set up those 100 vehicles to communicate wirelessly. , to provide traffic information.
They also had the advantage of running high speed cars that were already on many new cars. This technology allows the driver to set the car to a high speed, but the car slows down and accelerates when needed to stay safe from the car in front. In the test, the adaptive cruise control was changed to focus on the traffic flow – including what was happening in front – using artificial intelligence.
The traffic decision is based on two levels, according to Work. At the cloud level, information about the vehicle’s characteristics was used to create an overall speed map. That plan is broadcast to the cars, which use artificial intelligence algorithms to determine the best course of action. The researchers were able to evaluate the impact of connected vehicles on morning traffic flow using a specific 4-mile stretch of I-24 with 300 traffic lights.
The test is a project of the CIRCLES consortium, a group that includes several engineers and the US Energy and Transportation departments. Other key researchers are at the University of California, Berkeley; Temple University; and Rutgers University-Camden.
Liam Pedersen, associate director of research at Nissan, was a CIRCLES teammate in Nashville last week for the test. He said one of the exciting things about it is that it builds on technology that is in many new cars.
“This is not a private drive,” he said. “That’s something we can figure out as soon as possible.”
Asked if the automakers would be willing to work together to improve the traffic, Pedersen said, “I hope so, because the system works well and many people join in.” many cars.”
The test last week created a Work with his colleagues conducted in 2017 at the University of Arizona. That brought back the Japanese experiment, this time with a single-driver car thrown into the mix. The personal car has smoothed traffic flow with 98% less congestion. That resulted in a 40% increase in fuel efficiency and a 14% increase in mileage.
Researchers are still crunching the numbers for last week’s test, but Work said “it shows that these tickets can be reduced through the automated vehicle technology we’ve developed. It’s undeniable advanced mechanical technology can reduce aircraft costs when implemented at scale.
However, he cautioned that technology will not suddenly eliminate the problem.
“If there are more cars on the road than the road can support, there will be traffic,” he said. “But this will make the problem less painful.”