Google rolls out AI to optimise traffic lights and cut emissions

An artificial intelligence (AI)-powered traffic optimisation project from Google is aiming to cut car emissions in cities globally.

The ‘Green Light’ initiative, part of Google Research, uses AI and Google Maps driving data to analyse patterns and recommend improvements to existing traffic light systems.

The firm claims the technology has the potential to drive a 30 percent reduction in stops at intersections and a 10 percent reduction in emissions.

“For many city traffic engineers, it is hard and expensive to get access to reliable data for traffic light optimisation, which means that many traffic lights rely on outdated configurations,” said Yossi Matias, VP, Engineering and Research, Google.

“Our city partners tell us that prior to Green Light, they would try to optimise traffic lights using expensive sensors or time-consuming manual vehicle counts – and these solutions do not provide complete information on key parameters they need.”

The initiative is currently live in 12 cities globally – Abu Dhabi, Bali, Bangalore, Budapest, Haifa, Hamburg, Hyderabad, Jakarta, Kolkata, Manchester, Rio de Janeiro and Seattle.

How it works

Using data from Google Maps, the company builds an AI-based model of each intersection, including its structure, traffic patterns (such as patterns of starting and stopping), light scheduling, and how traffic and the light schedules interact, and then adds a model of the interaction between traffic lights.

Based on this, AI-based optimisations are developed and recommendations provided to the city.

According to a 2016 study, road pollution at city intersections can be 29 times higher than on open roads.

Google estimates that about half of emissions at intersections come from traffic stopping and starting, and that by leveraging AI, city engineers can implement emissions-savings plans “in as little as five minutes”, using existing infrastructure.

David Atkin, Analysis and Reporting Manager at Transport for Greater Manchester, said: “Green Light identified opportunities where we previously had no visibility and directed engineers to where there were potential benefits in changing signal timings.

“This provided valuable insights for our city with 2,400 traffic signals. Both the Green Light and Transport for Greater Manchester teams brought expertise and ideas to the table to improve journeys and reduce emissions.”

TfL cycle project

Separately, Google has teamed up with Transport for London (TfL) on an initiative to prioritise cycling on safer, quieter roads through Google Maps.

The project stems from an innovation summit hosted by TfL in July 2022 that aimed to understand some of the key problems for people cycling in the UK capital.

During the summit, the cyclists highlighted some of the key barriers they face, which included the need for travel planning tools to include up-to-date data on the 340 kilometres of cycle routes across the city.

“With existing digital journey planning data, cyclists haven’t always been able to see the best route available to them,” said London’s Walking and Cycling Commissioner, Will Norman.

“These updated algorithms will help Londoners choose safer cycling routes, whether it is a road with less traffic or part of the mayor’s growing network of Cycleways, enabling more people to get around by bike as we build a greener and better London for everyone.”

Image: isaac-mehegan-unsplash