Google uses AI to control traffic lights and reduce emissions in what could be future of driving
The rollout comes after Google piloted its Project Green Light in Manchester and found huge improvements in journey times, emissions and the amount of stop-starts in each journey.
The initiative used Google's AI to optimise traffic signal timings, specifically targeting 'stop-and-go' emissions - where a vehicle has to come to a halt before moving again - which Google estimates account for half of all vehicle emissions at busy intersections.
Transport for Greater Manchester (TfGM) found the pilot, which took place in late 2023, successfully reduced stop-start traffic by up to 22% at key junctions. Its success has led to a permanent implementation across Manchester’s primary commuter corridors.
The city has expanded the technology to over 50 major intersections, integrating it with the 'Bee Network' to prioritise public transport and further reduce carbon emissions in the city centre.
And the technology has transitioned from a limited experiment into a core component of 'Smart City' infrastructure across several major UK hubs, providing a glimpse into the future for urban driving.
Google has already installed the artificial intelligence technology across 70 junctions in 12 cities including Haifa in Israel, Rio de Janeiro in Brazil and Bangalore in India.
Data from these projects around the world show the potential to reduce vehicle stopping by 30 percent and emissions at junctions by 10 percent, Google said.
The Department for Transport (DfT) has invested £50 million into the Intelligent Traffic Management Fund to roll out AI-driven signals across the UK.
By March 2026, this technology is transitioning from a localised trial to a nationwide standard, with major cities including London, Birmingham, and Leeds deploying AI sensors to hit the benchmark 30% reduction in stop-start congestion.
Manchester's Green Light programme uses AI and driving trends from Google Maps to model traffic patterns and make traffic lights more efficient.
Recommendations to change the lights can be implemented in five minutes, and don't require changes to infrastructure. Theoretically it could mean cities can also react to traffic and improve flow, for example if an event or diversion has caused one-way congestion at a junction.
Manchester has more than 2,400 traffic lights and a million journeys are made each week.
Transport for Great Manchester's analysis found the pilot improved journey times by 18% and reduced emissions by approximately 10%.
Read more: