Google has announced Project Green Light, an initiative that uses artificial intelligence to optimise traffic light timing and reduce stop-and-go traffic emissions in cities worldwide.
Project Green Light leverages over a decade of Google Maps driving trends, to create AI models that measure traffic flow through intersections. These models identify potential improvements in traffic light timing, which city engineers can then implement using existing infrastructure.
The project aims to address the fact that about half of road transport emissions come from vehicles accelerating after stopping at traffic lights. By optimising traffic light timing, Project Green Light seeks to reduce unnecessary stops and, consequently, fuel emissions.
Alon Harris, Green Light Programme Manager, emphasised the project's simplicity and scalability: "We purposely set up everything to be simple and lightweight — cities don't need to invest in any dedicated software or hardware integrations."
Since its first pilot in 2021, Project Green Light has expanded to more than a dozen cities across the world, including Rio de Janeiro, Seattle, Bengaluru, and Boston. The initiative is currently live in over 70 intersections, impacting up to 30 million car rides monthly.
Early results are promising, with the potential to reduce stops by up to 30% and lower emissions at intersections by up to 10%. Google plans to scale Green Light to hundreds of cities and tens of thousands of intersections in the next few years.