Opportunities and Challenges in Crowdsourced Wardriving

Knowing the physical location of a mobile device is crucial for a number of context-aware applications. This information is usually obtained using the Global Positioning System (GPS), or by calculating the position based on proximity of WiFi access points with known location (where the position of the access points is stored in a database at a central server). To date, most of the research regarding the creation of such a database has investigated datasets collected both artificially and over short periods of time (e.g., during a one-day drive around a city). In contrast, most in-use databases are collected by mobile devices automatically, and are maintained by large mobile OS providers.

As a result, the research community has a poor understanding of the challenges in creating and using large-scale WiFi localization databases. We address this situation using the deployment of over 800 mobile devices to real users over a 1.5 year period. Each device periodically records WiFi scans and its GPS coordinates, reporting the collected data to us. We identify a number of challenges in using such data to build a WiFi localization database (e.g., mobility of access points), and introduce techniques to mitigate them. We also explore the level of coverage needed to accurately estimate a user's location, showing that only a small subset of the database is needed to achieve high accuracy.