Local newsNews

Google Maps explains how it predicts traffic

According to a statement released on September 29, more than one billion kilometres in more than 200 countries around the world are driven with Google Maps every day.

Whenever you start navigating with the app you are shown several things such as which direction to travel, if there is some heavy traffic on your route, estimated travel time and even an estimated arrival time.

All of these things just appear on your maps but have you ever wondered what goes on behind the scenes?

How does the app know when there is an accident on your travelling route or a heavy traffic jam and how does it determine which route is best for you to take?

Google Maps product manager, Johann Lau explains how Maps knows there’s traffic before there’s even traffic.

ALSO READ: Maintain a hectare of national parkland and stand a chance to win

Google Maps is powered by drivers all around the world

When people navigate with Google Maps, aggregate location data can be used to understand traffic conditions. But while this information helps you find current traffic estimates, it doesn’t account for what traffic will look like 10, 20, or even 50 minutes into your journey. This is where technology really comes into play.

To predict what traffic will look like, the app analyses historical traffic patterns for roads over time. It then combines the database of historical traffic patterns with live traffic conditions, using machine learning to generate predictions based on both sets of data.

To improve the accuracy of prediction capabilities Google Maps recently partnered up with DeepMind, an Alphabet AI research lab.

Estimated time of arrival predictions are already consistently accurate for over 97% of trips. By partnering with DeepMind, it improved that.

Using a machine learning architecture known as Graph Neural Networks, Google Maps have seen significant improvements from Berlin to Jakarta, São Paulo, Sydney, Tokyo, and Washington D.C.

This technique enables Google Maps to better predict whether or not you’ll be affected by a slowdown that may not have even started yet!

Keeping it fresh

For most of the 13 years that Google Maps has provided traffic data, historical traffic patterns have been reliable indicators of what your conditions on the road could look like, but that’s not always the case.

Since the start of the Covid-19 pandemic, traffic patterns around the globe have shifted dramatically. The app saw up to a 50% decrease in worldwide traffic when lockdowns started.

Since then, parts of the world have reopened gradually, while others maintain restrictions. To account for this, Maps has updated models to automatically prioritise historical traffic patterns from the past two to four weeks.

How Google Maps selects routes

Predictive traffic models are a key part of how Google Maps determines driving routes.

If a road is predicted to have heavy traffic Google Maps will automatically find you a lower traffic alternative route. Maps also look at a number of other factors, like road quality. Is the road paved or unpaved, or covered in gravel, dirt or mud? We also look at the size and directness of a road – a highway is often more efficient than taking a smaller road with multiple stops.

Maps also makes use of two other sources to ensure that it recommends the best routes: authoritative data from local governments and real-time feedback from users.

Authoritative data lets Google Maps know about speed limits, tolls, or if certain roads are restricted due to things like construction or Covid-19.

Incident reports from drivers let Google Maps quickly show if a road or lane is closed, if there’s construction nearby, or if there’s a disabled vehicle or an object on the road.

Both sources also help them understand when road conditions change unexpectedly due to mudslides, snowstorms, or other forces of nature.

Putting it all together

How does this all work in real life? Say you’re heading to a doctor’s appointment across town, taking your usual route.

With Google Maps’ traffic predictions combined with live traffic conditions, it will let you know there’s a good chance you’ll get stuck in unexpected traffic about 30 minutes into your ride – which would mean missing your appointment.

Google Maps will automatically reroute you using its knowledge about nearby road conditions and incidents – helping you avoid the jam altogether and reach your appointment on time.

Predicting traffic and determining routes is incredibly complex – and Google Maps will keep working on tools and technology to keep you out of gridlock, and on a route, that’s as safe and efficient as possible.

ALSO READ: Highest traffic count of 2020 on N4

At Caxton, we employ humans to generate daily fresh news, not AI intervention. Happy reading!
Stay in the know. Download the Caxton Local News Network App here.
Back to top button