In-car satnav systems and mobile mapping apps have made it much easier to travel from one place to another without getting lost, but a new innovation promises to help fix a remaining pain point – getting in the right lane at intersections.
Today's mapping apps aren't always much help if you're at an unfamiliar intersection and aren't sure exactly where on the road your car is supposed to be: the apps often don't have the detail or the knowledge to warn you in good time about changing lanes.
The system developed by researchers at MIT and the Qatar Computing Research Institute uses satellite imagery to augment existing mapping data, but the smart part is applying artificial intelligence to work out the layout of roads hidden by trees and buildings.
It's called RoadTagger, and by deploying machine learning on satellite imagery, the system is able to figure out with a high degree of accuracy some extra details on roads – including, for example, how many lanes they have. That could give drivers an early warning about diverging or merging lanes.
RoadTagger could also be adapted to make educated guesses about bike lanes and parking spots, the researchers behind it say. This would be particularly useful in places where little existing mapping data is available, because maps can be given extra detail relatively quickly and relatively cheaply.
"Most updated digital maps are from places that big companies care the most about," says MIT's Sam Madden. "If you're in places they don't care about much, you're at a disadvantage with respect to the quality of map. Our goal is to automate the process of generating high-quality digital maps, so they can be available in any country."
In tests across 20 cities in the US, the RoadTagger system was able to count lanes with an accuracy of 77 percent where the view of the road was at least partially blocked. In identifying road types (residential or highway), it hit an accuracy rate of 93 percent.
Other areas where this analysis can prove useful are in spotting dirt roads that have become paved, and in calculating what road features are hidden by overpasses.
The AI underpinning the program splits roads up into tiles, and uses information from surrounding tiles to help it figure out the layout of roads when the satellite view is blocked. It's an "end-to-end" model that can produce outputs from raw data without any human intervention along the way.
Satellite imagery is usually updated more regularly than mapping data, and the hope is that maps can get more accurate in regards to recent changes in layouts – and perhaps give you some advance warning the next time you need to change lanes.
Source: MIT