The new GPS system uses satellite imagery to more accurately determine the route

Researchers have developed a GPS system that, when constructing a route, analyzes satellite imagery to more accurately determine the type of road and the number of lanes.

Typically, GPS maps are created by large companies such aslike Yandex and Google, sending special cars with cameras to record details of the infrastructure of various areas. However, this method of collecting information is expensive and time-consuming, so some parts of the world are simply ignored and the data obtained is basic. In addition, the system is not always correctdetermines the number of lanes and where they lead, so sometimes the route can change dramatically on the way.

One solution to these problems isthe use of machine learning algorithms for recognizing roads in satellite images of the area. Although this method is cheaper, provides more information and uses regularly updated images, roads are often hidden by trees and buildings, which complicates the work of AI.

Recently researchers from MassachusettsInstitute of Technology and the Qatar Research Institute jointly developed a combination of neural architectures to automatically predict the types of roads and the number of lanes behind obstacles. During testing, the system correctly determined the types of roads in 93% of cases, and the number of lanes with an accuracy of 77%.

In the future, the team plans to teach the system to recognize parking spaces, bike paths and provide information about the current condition of roads.

The efficiency of such systems is still important for unmanned vehicles, which is moving from  test tracks on public roads.

</p>