Google's AI Spotlight Program Is Currently Reducing Traffic In A Dozen Cities Globally

It’s been two years since Google launched Project Green Light, a new approach to reducing street-level pollution generated by automobiles idling at stop lights. On Tuesday, at its Sustainability ’23 event, the business highlighted some of the early findings from that initiative and announced another round of expansions.

Green Light uses machine learning techniques to sift through Maps data to compute the degree of traffic congestion present at a specific light, as well as the average wait durations of vehicles stopped at that light. This data is then used to train AI models that can optimize traffic scheduling at that intersection independently, minimizing idle periods as well as the amount of braking and accelerating cars must perform. All of this is part of Google’s objective of assisting its partners in collectively reducing their carbon emissions by a gigatonne by 2030.

When the initiative was initially unveiled in 2021, it had only been pilot tested in four crossroads in Israel in collaboration with the Israel National Roads Company, but Google claimed saw a “10 to 20 percent reduction in fuel and intersection delay time” during those testing. Since then, the pilot initiative has expanded to a dozen partner cities across the world, including Rio de Janeiro, Brazil, Manchester, England, and Jakarta, Indonesia.

Google’s VP of Geo Sustainability, Yael Maguire, claimed that the program “helped prevent more than 2.4 million metric tons of carbon emissions — the equivalent of taking about 500,000 fuel-based cars off the road for an entire year.”