RALEIGH, N.C. — When it comes to the rules of the road, rule number one is green means go, yellow means slow down, and red means STOP! However, the growing use of artificial intelligence may change even those basic traffic rules. Researchers from North Carolina State University propose adding a fourth color to traffic lights, a white light, enabling self-driving vehicles to help control traffic flow, and let human drivers in on what’s going on.
Across a series of computational simulations, study authors found that adding this fourth white light significantly improved travel time through intersections and reduced fuel consumption.
“This concept we’re proposing for traffic intersections, which we call a ‘white phase,’ taps into the computing power of autonomous vehicles (AVs) themselves,” says Ali Hajbabaie, corresponding author of the paper and an associate professor of civil, construction and environmental engineering at NC State, in a university release. “The white phase concept also incorporates a new traffic signal, so that human drivers know what they are supposed to do. Red lights will still mean stop. Green lights will still mean go. And white lights will tell human drivers to simply follow the car in front of them.”
How would a 4th traffic light work?
The white light concept relies on the fact that AVs can communicate wirelessly amongst themselves and the computers controlling traffic signals. When enough AVs are simultaneously approaching an intersection, this would activate the white light. Generally speaking, the white light will serve as a signal that AVs are coordinating their movement to promote a more efficient traffic flow through the intersection. Meanwhile, any cars under the control of boring old humans will just have to follow the vehicle in front of them. If the car in front stops, you stop. If the car in front of you goes through the intersection, you proceed through the intersection.
In situations where many human-controlled vehicles are approaching the intersection, the traffic light will simply go back to the usual green-yellow-red signal pattern.
“Granting some of the traffic flow control to the AVs is a relatively new idea, called the mobile control paradigm,” Prof. Hajbabaie adds. “It can be used to coordinate traffic in any scenario involving AVs. But we think it is important to incorporate the white light concept at intersections because it tells human drivers what’s going on, so that they know what they are supposed to do as they approach the intersection.”
“And, just to be clear, the color of the ‘white light’ doesn’t matter. What’s important is that there be a signal that is clearly identifiable by drivers.”
This “white phase” traffic intersection concept was actually first introduced by the team at NC state in 2020. However, that initial concept focused on using a centralized computing approach, with the computer controlling the traffic light totally responsible for receiving input from all approaching AVs, making the necessary calculations, and ultimately directing the AVs on how they should proceed through the intersection. That’s a lot of work for one computer.
“We’ve improved on that concept, and this paper outlines a white phase concept that relies on distributed computing – effectively using the computing resources of all the AVs to dictate traffic flow,” Prof. Hajbabaie comments. “This is both more efficient, and less likely to fall prey to communication failures. For example, if there’s an interruption or time lag in communication with the traffic light, the distributed computing approach would still be able to handle traffic flow smoothly.”
Self-driving cars still improve traffic flow without a new light
The research team used microscopic traffic simulators to test the performance of the distributed computing white phase concept. Such simulators are incredibly complex computational models which replicate real-world traffic, including the behavior of individual vehicles. Thanks to this incredible technology, study authors were able to successfully compare traffic behavior at intersections with and without the white phase, as well as gauge how the number of AVs involved influences such behavior.
“The simulations tell us several things,” the study author continues. “First, AVs improve traffic flow, regardless of the presence of the white phase. Second, if there are AVs present, the white phase further improves traffic flow. This also reduces fuel consumption, because there is less stop-and-go traffic. Third, the higher the percentage of traffic at a white phase intersection that is made up of AVs, the faster the traffic moves through the intersection and the better the fuel consumption numbers.”
More specifically, when roughly 10 to 30 percent of the traffic at a white phase intersection were AVs, the simulations indicated relatively small improvements in traffic flow. Yet, as the percentage of AVs at white phase intersections increased, so did the benefits.
“That said, even if only 10% of the vehicles at a white phase intersection are autonomous, you still see fewer delays,” Prof. Hajbabaie notes. “For example, when 10% of vehicles are autonomous, you see delays reduced by 3%. When 30% of vehicles are autonomous, delays are reduced by 10.7%.”
New traffic lights are still a long way off
To be clear, study authors acknowledge that AV technology and current models are not ready to adopt the new distributed computing approach tomorrow, nor are governments about to install brand new traffic lights at every intersection in the immediate future for that matter.
“However, there are various elements of the white phase concept that could be adopted with only minor modifications to both intersections and existing AVs,” Prof. Hajbabaie concludes. “We also think there are opportunities to test drive this approach at specific locations.
“For example, ports see high volumes of commercial vehicle traffic, for which traffic flow is particularly important. Commercial vehicles seem to have higher rates of autonomous vehicle adoption, so there could be an opportunity to implement a pilot project in that setting that could benefit port traffic and commercial transportation.”
The study is published in the journal IEEE Transactions on Intelligent Transportation Systems.