Ever wondered how Google Maps predicts traffic on your route? Here's the tea

Google has shared how it uses artificial intelligence (AI) for its Maps app to predict what traffic will look like throughout the day and the best routes its users should take.

The search engine said it analyses historical traffic patterns for roads over time and combines the database with live traffic conditions to generate predictions and estimate the time of arrival.

Google Maps product manager Johann Lau shared on Tuesday that to improve accuracy, the company partnered with DeepMind, an Alphabet AI research lab.

“This technique enables Google Maps to better predict whether you’ll be affected by a slowdown that may not have even started yet,” he said.

Lau said Google has seen accurate prediction rates on more than 97% of trips.

“If it predicts that traffic is likely to become heavy in one direction, the app automatically finds you a lower-traffic alternative.

“We also look at a number of other factors, like road quality, the size, and directness of a road — a highway is often more efficient than taking a smaller road with multiple stops,” he said.

Since the start of the Covid-19 pandemic, Lau said traffic patterns around the globe have shifted dramatically and there is an up to 50% decrease in worldwide traffic from when lockdowns started.

“Since then, parts of the world have reopened gradually, while others maintain restrictions. To account for this, we’ve updated our models to automatically prioritise historical traffic patterns from the last two to four weeks,” he said.

According to Lau, two other sources of information are important in making sure Google recommends the best routes: authoritative data from local governments and real-time feedback from users.

He said 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,” he said.

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