Robust, cost-effective and scalable localization in large indoor areas

Indoor location information plays a fundamental role in supporting various interesting location-aware indoor applications. Widely deployed WiFi networks make it feasible to perform indoor localization by first establishing a received signal strength (RSS) map covering the whole area based on a signal propagation model, then determining a location from an online RSS measurement given the RSS map. However, challenges remain in practical deployments, due to inaccurately estimated RSS values in the RSS map and an insufficient number of access points (APs) in large indoor areas. To address these challenges, we develop a robust, cost-effective and scalable localization system (REAL). Our approach adaptively searches for the best model parameters with limited training resources. In addition, REAL utilizes a probabilistic approach for location searching by considering errors from the signal propagation model. It also exploits information regarding unobserved APs at a given location and an optimal clustering method. We systematically evaluate the accuracy of the propagation model with different configurations. Our intensive real-world experimental results demonstrate that REAL achieves considerable localization accuracy at a very low training cost. In addition, the comparisons over two large indoor environments show that REAL consistently outperforms other state-of-the-art systems and can be effectively applied to various real-world scenarios.