Sensor-Aided Learning for Wi-Fi Positioning With Beacon Channel State Information

Abstract

Because each indoor site has its own radio propagation characteristics, a site survey process is essential to optimize a Wi-Fi ranging strategy for range-based positioning solutions. This study examines an unsupervised learning technique that autonomously learns an optimal ranging strategy for each site using Wi-Fi and sensor data accumulated while users access a positioning application. Using the collected sensor data, the device trajectory is regenerated, and a Wi-Fi ranging module is optimized to generate the shape of the estimated trajectory using Wi-Fi, similar to that obtained from sensors. In this process, the ranging module learns the way to identify the channel conditions from each Wi-Fi access point (AP) and produces ranging results accordingly. Furthermore, we collect the channel state information (CSI) from beacon frames to investigate the benefit of using CSI in addition to received signal strength measurements. With the CSI, the ranging module can identify diverse channel conditions from each AP and more accurately generate the reliability of each distance estimate to achieve accurate positioning results. The effectiveness of the proposed learning technique is verified using a real-time positioning application implemented on a PC platform.