Google Maps partners with Deep Mind AI to improve ETA’s

Courtesy: Google

Courtesy: Google

Every day, over 1 billion kilometres are driven with Google Maps in more than 220 countries and territories around the world. Google says the accuracy of its service is spot-on over 97% of the time. But, the remaining 3% is what Google has set out to work on.

In order to achieve better estimated travel times, Google Maps has recently partnered with DeepMind: an Alphabet AI research lab. The two will work together to improve the accuracy of Googles traffic prediction capabilities by using a machine learning architecture known as Graph Neural Networks.

Courtesy: Deepanker Verma

Courtesy: Deepanker Verma

To calculate ETAs (Estimated Time of Arrival) Google Maps analyses live traffic data for road segments around the world. While this data gives Google Maps an accurate picture of current traffic, it doesn’t account for the traffic a driver can expect to see 10, 20, or even 50 minutes into their drive.
— Deep Mind

DeepMind's parnership with Google will use advance Machine Learning to analyze road quality, speed limits, and closures. With this new processing power, Google Maps data will be used to provide users with a more accurate ETA before their journey starts.

taxi-cab-381233_1920.jpg

Google also used uses Authoritative data from local governments and real-time feedback from users. Authoritative data Google Maps uses includes speed limits, tolls, construction and more. Incident reports from drivers also help Google Maps quickly show road or lane closures, broken down vehicles, objects in the road and nearby construction.

Google’s claims its partnership with DeepMind has already made fruitful impact on Google maps and its users. The AI has improved accuracy of real time ETAs by up to 50% in places like Berlin, Sydney, Tokyo, Jakarta, São Paulo, and Washington D.C.

The great improvements from Googles traffic data being fed into an upgraded algorithm gives us a glimpse into the impactful possibilities of AI. While working silently, it could be the difference between you being 20 minutes late or right on time in the case of a 50% more accurate ETA.


Vinay Singhania

Instagram

Twitter

Previous
Previous

Huawei’s new “Harmony OS” and what that means for consumers

Next
Next

Here’s LG’s new game-changing Mask