Home Driverless Cars White light at traffic signals could support autonomous vehicles

White light at traffic signals could support autonomous vehicles

by Charles Choi
An illustration of how a fourth light might influence autonomous vehicles in traffic. Credit: R. Niroumand et al.

A fourth light on traffic signals for autonomous vehicles could help self-driving and human traffic interact better together, according to a new study.

In computational simulations, this extra “white phase,” in addition to the conventional red, yellow and green lights, significantly improved travel time through intersections and reduced fuel consumption.

The researchers acknowledged that autonomous vehicles are not ready to adopt this new distributed computing approach, nor are governments going to install brand new traffic lights at every intersection any time soon.

“However, there are various elements of the white phase concept that could be adopted with only minor modifications to both intersections and existing autonomous vehicles,” Ali Hajbabaie, study senior author of the paper and an associate professor of civil, construction and environmental engineering at North Carolina State University, said in a statement.

Areas where this white phase idea could be tested include ports which see high volumes of commercial vehicle traffic and 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,” Hajbabaie said in a statement.

The new approach depends on how autonomous vehicles can communicate wirelessly both with each other and the computer controlling a traffic signal. The white light activates when a sufficient number of autonomous vehicles approach the intersection.

“This concept we’re proposing for traffic intersections, which we call a ‘white phase,’ taps into the computing power of autonomous vehicles themselves,” Hajbabaie said in a statement. “The white phase concept also incorporates a new traffic signal, so that human drivers know what they are supposed to do.”

The white light is a signal that the autonomous vehicles will coordinate their movement to help traffic move through the intersection more efficiently. Any non-automated vehicle driven by a person would only have to follow the vehicle in front of them—if the car in front of them stops, they stop, and if the car in front of them goes through the intersection, they go through the intersection.

When a sufficient number of vehicles approaching the intersection are controlled by human drivers, rather than autonomous vehicles, the traffic light would revert to the conventional green-yellow-red signal pattern.

“Granting some of the traffic flow control to the autonomous vehicles is a relatively new idea, called the mobile control paradigm,” Hajbabaie said in a statement. “It can be used to coordinate traffic in any scenario involving autonomous vehicles. 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.”

Although the researchers currently dub this extra signal “white,” they noted its color does not actually matter. “What’s important is that there be a signal that is clearly identifiable by drivers,” Hajbabaie said in a statement.

When the researchers first conceived of this “white phase” concept in 2020, they initially relied on a centralized computing approach. In other words, the computer that controlled the traffic light would also be responsible for receiving input from all the approaching autonomous vehicles, making the necessary calculations, and then telling the autonomous vehicles how they should proceed through the intersection.

“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 autonomous vehicles to dictate traffic flow,” Hajbabaie said in a statement. “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.”

In order to test the performance of the new distributed computing white phase concept, the researchers made use of complex computational models designed to replicate real-world traffic down to the behavior of individual vehicles. Using these simulators, the researchers were able to compare traffic behavior at intersections with and without the white phase, as well as how the number of autonomous vehicles involved influenced that behavior.

“The simulations tell us several things,” Hajbabaie said in a statement. “First, autonomous vehicles improve traffic flow, regardless of the presence of the white phase. Second, if there are autonomous vehicles 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 autonomous vehicles, the faster the traffic moves through the intersection and the better the fuel consumption numbers.”

When only 10 to 30 percent of the traffic at a white phase intersection was made up of autonomous vehicles, the simulations found there were only relatively small improvements in traffic flow. As the percentage of autonomous vehicles at white phase intersections increased, so did the benefits.

“That said, even if only 10 percent of the vehicles at a white phase intersection are autonomous, you still see fewer delays,” Hajbabaie said in a statement. “For example, when 10 percent of vehicles are autonomous, you see delays reduced by 3 percent. When 30 percent of vehicles are autonomous, delays are reduced by 10.7 percent.”

The scientists detailed their findings earlier this month in the journal IEEE Transactions on Intelligent Transportation Systems.

You may also like