A Semi-Automated System for Exploring and Fixing OSM Connectivity

Abstract

Routing engines and navigation services are among the top applications that take advantage of the OpenStreetMap (OSM) collaborative project. With that said, the underlying road network data provided by the OSM public geographic datasets must be as accurate as possible for these services to work correctly. This means that road networks must be fully connected, and other constraints such as turn restrictions, road directionality and correct road classification must be respected. However, being an open-license project with around 7 million users and a daily average of about 3 and half million map changes, errors in the data are far from lacking. Issues like misclassified road segments, incorrect connections and gaps in road networks are fairly common, and they pose a complex yet notable obstacle that jeopardizes the accuracy and reliability of routing services that rely on OSM data. In this research, we demonstrate and analyze a system we have developed (the OSM connectivity system, or OCS) that tackles and remedies all sorts of connectivity errors in an OSM road network graph. The system enables the end-user (cartographer) to discover errors and achieve full connectivity in any chosen OSM road network graph.It automatically detects connectivity errors that otherwise require an extensive manual process to discover, accepts user input through its friendly graphical user interface, and allows for further error investigation, fix suggestion, and easy access to official editing tools.