Map-assisted Indoor Positioning Utilizing Ubiquitous WiFi Signals

The demand of indoor positioning solution is on the increase dramatically, and WiFi-based indoor positioning is known as a very promising approach because of the ubiquitous WiFi signals and WiFi-compatible mobile devices. Improving the positioning accuracy is the primary target of most recent works, while the excessive deployment overhead is also a challenging problem behind. In this thesis, the author is investigating the indoor positioning problem from the aspects of indoor map information and the ubiquity of WiFi signals. This thesis proposes a set of novel WiFi positioning schemes to improve the accuracy and efficiency. Firstly, considering the access point (AP) placement is the first step to deploy indoor positioning system using WiFi, an AP placement algorithm is provided to generate the placement of APs in a given indoor environment. The AP placement algorithm utilises the floor plan information from the indoor map, in which the placement of APs is optimised to benefit the fingerprinting- based positioning. Secondly, the patterns of WiFi signals are observed and deeply analysed from sibling and spatial aspects in conjunction with pathway map from indoor map to address the problem of inconsistent WiFi signal observations. The sibling and spatial signal patterns are used to improve both positioning accuracy and efficiency. Thirdly, an AP-centred architecture is proposed by moving the positioning modules from mobile handheld to APs to facilitate the applications where mobile handheld doesn’t directly participate positioning. Meanwhile, the fingerprint technique is adopted into the AP-centred architecture to maintain comparable positioning accuracy. All the proposed works in this thesis are adequately designed, implemented and evaluated in the real-world environment and show improved performance.