Google is a company that improves the lives of millions of people around the world. The brand offers us free access to a database of information, videos, productivity and collaboration tools, interactive calendars or maps. All of this adds convenience to everyday life. Now it decided to go one step further and do something good for the planet. The company proposed an innovative solution called Green Light with artificial intelligence as its key element.

Road transportation is responsible for emitting huge amounts of harmful substances. This is why public transport is recommended to move around in cities as it less harmful for the environment. Increasingly, cities are also opting for electric substitutes for buses or cars and urban bicycles are used in many parts of the world as well. The above ways of combating toxic fumes have been known and practised to a greater or lesser extent for years. Now the time has come for cities to make use of artificial intelligence.

Based on research Google estimated that emissions of harmful substances at intersections can be up to 29 times higher than on open roads. Half of these emissions appear due to cars accelerating after stopping. In order to reduce the emission of toxic fumes and at the same time improve traffic flow, traffic lights need to be synchronised. Optimising the traffic lights on the roads can be done with costly equipment or by counting all the vehicles in a city. Both solutions are very expensive, so Google decided to do something about it.

The Green Light project uses artificial intelligence and driving trends it gathers from Google Maps users. Using this database of road information and the appropriate application of AI, it is estimated that the number of unnecessary stops and accelerations can be decreased by around 30% and harmful emissions at intersections by 10%. By optimising all roads, it will be possible to create waves of green lights to help deal with toxic fumes and traffic jams. Green Light is currently used at 70 intersections in 12 cities on four continents.

Google outlined how Green Light works as follows:

1. Understanding the intersection - Building on our decades-long effort to map cities across the world, we can infer existing traffic light parameters including: cycle length, transition time, green split (i.e. right-of-way time and order), coordination and sensor operation (actuation).
2. Measuring traffic trends - We create a model to understand how traffic flows through the intersection. This helps us understand typical traffic patterns including patterns of starting and stopping, average wait times at a traffic light, coordination between adjacent intersections (or lack thereof), and how traffic light plans change throughout the day.
3. Developing recommendations for the city - Using AI, we identify possible adjustments to traffic light timing. We share these adjustments as actionable recommendations with the city. The city’s traffic engineers review the recommendations, approve them, and they can easily implement them in as little as 5 minutes, using the city's existing policies and tools.
4. Analysing impact - We measure how many stops we’ve saved for drivers, and its impact on traffic patterns. We then use industry standards models to calculate the climate impact of these changes. We share this with the partner city and continue monitoring for any future needed changes.

Source: Google Research