Google Maps continues to stay a step ahead of the crowd
In this article (5)
Google uses historical traffic data with Google Maps to help it produce an estimated time of arrival (ETA). This allows a user to see what time he should arrive at his destination. The ETA can also be shared with friends or family so that the user won’t have to pick up his phone while driving to pass along the information. But we don’t have to tell you that there have been changes in traffic patterns over the last few months because of the pandemic which led many cities to shutdown. When cities starting closing earlier this year, worldwide traffic declined by as much as 50%.
The lockdowns led to a situation where data from Google Maps could not be relied upon, forcing Google to revise traffic patterns. To account for the effects of COVID-19 on Google Maps, the apps prioritize more recent traffic patterns from the last two to four weeks while deprioritizing patterns from any time before that.
Last week, Google published a blog post that discusses how the company computes traffic and routing on the Maps app. Location data is aggregated and used as a tool to determine what the traffic is like on roads around the world. As Google points out, this information is great at determining current driving conditions but doesn’t explain what will happen to traffic “10, 20, or even 50 minutes into your journey.”
To guess what will happen in the future, Google Maps analyses traffic patterns on specific roads. For example, one pattern shows that the 280 freeway in Northern California typically has vehicles traveling at 65mph between 6-7 am, but only at 15-20mph during the late afternoon. Google combines the data from historical traffic patterns with the data from live traffic conditions. Using machine learning on both sets of data, Google generates an estimate of an estimated time of arrival.
“10, 20, or even 50 minutes into your journey.”
Google says that on 97% of trips using the Maps app, its predictions have been accurate. Partnering with parent company Alphabet’s DeepMind AI research lab, Google can reduce the number of inaccurate ETA’s through the use of Graph Neural Networks. Available in places like Berlin, Jakarta, São Paulo, Sydney, Tokyo, and Washington D.C., the technology allows Maps to predict whether you will be caught in a slowdown that hasn’t even started yet.
To help the app pick the route that you should take, different factors are looked at including the amount of traffic along the way; less traffic is preferred of course. Road quality is also important; is the road paved or is it a gravel-covered road that is hard to drive on. Other drivers can report things like the weather (snowstorm, torrential showers, etc.), accidents, construction, and police activity that can slow things down.
Have you ever used Google Maps to get directions to a place that you’ve been to many times before, but noticed that the app is taking you a different way? That’s because Google will find a new route if the usual one includes delays. Google describes what happens: “Say you’re heading to a doctor’s appointment across town, driving down the road you typically take to get there.
When you leave the house, traffic is flowing freely, with zero indication of any disruptions along the way. With Google Maps’ traffic predictions combined with live traffic conditions, we let you know that if you continue down your current route, there’s a good chance you’ll get stuck in unexpected gridlock traffic about 30 minutes into your ride—which would mean missing your appointment. As a result, Google Maps automatically reroutes you using its knowledge about nearby road conditions and incidents—helping you avoid the jam altogether and get to your appointment on time.”
Questions & Answers
Q.How did the pandemic affect Google Maps' traffic prediction capabilities?
How did the pandemic affect Google Maps' traffic prediction capabilities?
Worldwide traffic declined significantly during city shutdowns, making historical data unreliable. Google revised its approach by prioritising recent traffic patterns from the last two to four weeks, while deprioritising older information to maintain accuracy.
Q.What methods does Google Maps use to predict future traffic conditions?
What methods does Google Maps use to predict future traffic conditions?
Google Maps analyses historical traffic patterns on specific roads, such as the 280 freeway example, and combines this with live traffic data. Machine learning is then applied to both datasets to generate future travel time estimates.
Q.How does Google Maps help users avoid unexpected delays during a journey?
How does Google Maps help users avoid unexpected delays during a journey?
Google Maps uses traffic predictions and live conditions to anticipate delays before they occur. If a route is likely to encounter gridlock, the app automatically reroutes the user, utilising its knowledge of nearby road conditions and incidents to help them avoid the jam.
Q.Which specific cities are currently benefiting from Google Maps' advanced traffic prediction technology?
Which specific cities are currently benefiting from Google Maps' advanced traffic prediction technology?
The advanced technology, developed with Alphabet’s DeepMind, is available in several cities. These include Berlin, Jakarta, São Paulo, Sydney, Tokyo, and Washington D.C., allowing Maps to predict slowdowns before they start.