A major problem in indoor localization based on WiFi RSS (Received Signal Strength) is the tedious offline surveying process for fingerprinting. To address this problem, we propose an unsupervised Simultaneous Localization and Mapping (SLAM) system for automatic floor map and radio map construction. To set up this system, a surveyor needs only to walk through the coverage area randomly several times to collect traces of WiFi RSS measurements. Based on similarity matching of these measurements, a floor map in the form of a graph is automatically constructed, together with a radio map which associates individual WiFi RSS distributions with sample points along the graph. In the online stage, this system is able to update very efficiently when there is any configuration change of APs’ deplo...[ Read more ]

A major problem in indoor localization based on WiFi RSS (Received Signal Strength) is the tedious offline surveying process for fingerprinting. To address this problem, we propose an unsupervised Simultaneous Localization and Mapping (SLAM) system for automatic floor map and radio map construction. To set up this system, a surveyor needs only to walk through the coverage area randomly several times to collect traces of WiFi RSS measurements. Based on similarity matching of these measurements, a floor map in the form of a graph is automatically constructed, together with a radio map which associates individual WiFi RSS distributions with sample points along the graph. In the online stage, this system is able to update very efficiently when there is any configuration change of APs’ deployment. This is done by using crowdsourced RSS data to dynamically update the map. Algorithms are also discussed to increase the computational efficiency, as the size of the database can increase squarely with the scale of the test bed.