TRAFFIC patterns across the world could change as experts plan to add a fourth light amid AI-powered plans.
Researchers at North Carolina State have proposed a new traffic signal system at intersections with “artificially intelligent white light” to ease out city congestion.
Scientists suggest this would ease congestion in city traffic and lower drivers’ fuel consumption, essentially saving drivers lots of money over time.
The fourth light would be used to regulate the traffic for self-driving autonomous vehicles – and will sync with their computing systems, according to lead researcher Ali Hajbabaie.
Hajbabaie and his team tried and tested the “white light” concept on complex micro-traffic simulators, which were tuned to anticipate the varied situations that could come on the road and how the self-driving cars would react to them.
“AVs improve traffic flow, regardless of the presence of the white phase,” Hajbabaie said.
“The white phase further improves traffic flow. This also reduces fuel consumption, because there is less stop-and-go traffic.
“[And] 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.”
It was also found that the higher volume of AVs on the road led to the most reductions in traffic.
[The proposed traffic system] can be used to coordinate traffic in any given scenario that involves self-driving cars
Ali Hajbabaie
According to the proposed plans, the AV cars would remotely communicate with one another in addition to the main computing system, which would control the smart traffic lights.
“The white phase concept also incorporates a new traffic signal, so that human drivers know what they are supposed to do,” Hajbabaie said.
“Red lights will still mean stop. Green lights will still mean go. And white lights will tell human drivers to follow the car in front of them.”
The proposed “white light” would activate when “enough AVs are approaching a given intersection” and an AI-powered machine learning system would help create the most efficient sequence for the traffic to travel, avoiding congestion and jams.
It will also direct human drivers in traffic full of self-driving cars to coordinate in the best possible way.
And at times when there are more human drivers on the road, the light would revert to a conventional red, yellow, and green combination system.
“Granting some of the traffic flow control to the AVs is a relatively new idea, called the mobile control paradigm,” said Hajbabaie.
He added that the fourth light could be of any desired colour – and it can be used “to coordinate traffic in any given scenario that involves self-driving cars”.
Hajbabaie’s latest plans, however, differ from the model of a four-light intersection proposed back in 2020.
It was designed with a centralised system where a computer built into the light would communicate with all vehicles rather than having them talk with one another.
The researcher explained: “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.
“This is both more efficient, and less likely to fall prey to communication failures.”
While the practical implementation of the new traffic signal system could be years away from now, Hajbabaie and his research team are scouting for areas where they could plan a test run for the system.
