Google is undertaking a significant expansion of a new product called Greenlightdesigned to optimize traffic lights and reduce waiting time at 14 cities around the world. Through this technology, they seek to create “green waves” or sequences of consecutive green lights to keep traffic flowing.
Juliet Rothenbergproduct leader of Climate AI in Google Researchhighlighted when consulted by The Wall Street Journal (WSJ) that the implementation of this tool does not require new hardware, as it is based on data obtained from vehicles connected to the Internet and navigation applications on mobile phones.
But Google He is not the only one who sees the potential in traffic light optimization. Researchers of the University of Michigan suggest that these systems could save traffic agencies money, making their adoption easier.
Henry Liuwho leads a research team in the University of Michiganspecified the importance of using vehicles as traffic sensors: “instead of installing cameras at an intersection, if we know the trajectory of the vehicle, then the vehicle itself becomes the traffic sensor,” he said. WSJ.
The methodology developed in Michigan has been applied to evaluate and adjust the time of 34 road signs in Birmingham, Michigantaking advantage of telemetry data provided by General Motors. This initiative had a significant impact on traffic flow during peak hoursaccording to Danielle Deneaucounty traffic safety director Oakland.
If these innovations were implemented at the national level, they could significantly reduce the time drivers spend at traffic lights. Data from cities where it is already used Greenlightas Abu Dhabi, Hamburg, Seattle and Calcuttashow a 30% reduction in stop-start traffic at intersections.
A study of Inrix of 2021 found that, on short trips, Americans spend an average of 10% of their time stopped at traffic lights. Reducing this time could help the environment and human health, since the Pollution at intersections is 29 times higher than on open roads due to vehicle downtime.
Another benefit of this system is that it eliminates the need for expensive and time-consuming studies normally required to change the timing of a traffic signal. These studies generally cost around $5,000 each time they are done,” said Liu.
The expensive updating of fixed traffic signs is one of the reasons why the Traffic light timing at most intersections is updated only once every five yearsand there are intersections whose timing has not been updated in decades, he added.
According to him WSJToday, at least half of the traffic lights in the world work as they did 30 years ago. They are “fixed time” signals, as opposed to newer dynamic signals, which use cameras or sensors under the road surface to detect the number of vehicles present and adjust your timing accordingly.
In an ideal world, every traffic signal would be dynamic and connected to a central control system so that an entire city or county would be optimized moment by moment, in the same way that traffic in Internet It is constantly optimized. However, this is not possible because dynamic, connected traffic signals can cost tens of thousands of dollars.
Complete modernization of an intersection can cost up to $250,000 with additional maintenance costs of 5,000 dollars a yearhe explained Deneau. Because of these high costs, regional agencies with budget constraints are forced to use what they already have: fixed-time traffic lights.
When cities sign up Greenlightthey receive a dashboard that offers recommendations for updating the timing of specific intersections. Importantly, Google’s AI-powered system evaluates how traffic patterns change after updating traffic light timingallowing cities to measure the real results of their changes.
In seattlethe data from Greenlight convinced transportation planners to update lights timing in five intersections starting in June 2022, according to a spokesperson for the city transportation department. After further analysis, planners kept those updates at four of the intersections. The city continues to use the system alongside traditional methods and planners believe it has the potential to save money in the future.
At the moment, Greenlight has a waiting list, but the project is rapidly expanding to new cities, which Google will announce later this year, according to RothenbergEdit. Liu He noted that any technology startup or transit agency could replicate what his team did, since they have made their methodology public and anyone can use it.
All that is required is to obtain the right type of real-time data from car manufacturers or navigation app developers. “All the math was already there, the beauty of our approach is that the previous models were too complicated and we simplified them,” he concluded. Liu.
