Google Maps uses Artificial Intelligence to predict traffic performance


Google says more than 1 billion kilometres are driven with Google Maps in more than 220 countries and territories, and that is a lot of traffic data to take in.

Using Artificial Intelligence, Maps can you show instant traffic updates from the moment you start navigating. All of it appears extremely simple, but there’s a lot going on behind the scenes which enable Maps to crunch the numbers and get you from Point A to Point B safely and on time.

According to the multinational technology company, the app groups location data to better understand traffic conditions. And this is where technology comes into play. In order to provide accurate predictions, “Google Maps analyses historical traffic patterns for roads over time”. Google then combines that data with live traffic conditions by using machine learning to “generate predictions based on both sets of data”. Machine learning is the study of computer algorithms that improve automatically through experience.

Google recently partnered with DeepMind, an Alphabet AI research lab, to improve the accuracy of Maps’ prediction capabilities. “[Google Maps] ETA predictions are already consistently accurate for over 97% of trips. By partnering with DeepMind, we’ve improved that”.

In their recent statement, DeepMind said their collaboration with Maps will “minimise the remaining inaccuracies even further – sometimes by more than 50% in cities like Taichung”.

Google clarifies that if you’re heading to a doctor’s appointment through town on a route you take on a regular basis, the “traffic predictions combined with live traffic conditions” will notify you of possible delays along the way. Google Maps will then automatically reroute your trip “using its knowledge about nearby road conditions and incidents”. The process is incredibly complex, and the team promises to keep improving.

Main Image: Pieuvre

About Author

Leave A Reply