Indoor Localization with Wi-Fi Fine Timing Measurements Through Range Filtering and Fingerprinting Methods

Abstract

Wi-Fi technology has been thoroughly studied for indoor localization. This is mainly due to the existing infrastructure inside buildings for wireless connectivity and the uptake of mobile devices where Wi-Fi location-dependent measurements, e.g., timing and signal strength readings, are readily available to determine the user location. To enhance the accuracy of Wi-Fi solutions, a two-way ranging approach was recently introduced into the IEEE 802.11 standard for the provision of Fine Timing Measurements (FTM). Such measurements enable a more reliable estimation of the distance between FTM-capable Wi-Fi access points and user-carried devices; thus, promising to deliver meterlevel location accuracy. In this work, we propose two novel solutions that leverage FTM and follow different approaches, which have not been investigated in the literature. The first solution is based on an Unscented Kalman Filter (UKF) algorithm to process FTM ranging measurements, while the second solution relies on an FTM fingerprinting method. Experimental results using reallife data collected in a typical office environment demonstrate the effectiveness of both solutions, while the FTM fingerprinting approach demonstrated 1.12m and 2.13m localization errors for the 67-th and 95-th percentiles, respectively. This is a two to three times improvement over the traditional Wi-Fi signal strength fingerprinting approach and the UKF ranging algorithm.

DNN-based Indoor Fingerprinting Localization with WiFi FTM

“…3. Experimental site with AP locations and the measurement routes [10] subjected to shadowing zones and multipath effects as a result of the furniture in the rooms and open space. It was determined that the measuring area encompassed various rooms including a corridor and lounge, as depicted in Fig.…”

“…In our prior work [10], we studied three different localization methods: (i) the standard FTM euclidean fingerprinting method, (ii) the FTM Bhattacharyya fingerprinting method, and (iii) the unscented kalman filter (UKF) method. Each of these methods represent a different form of measurement or a different method of positioning.…”

“…The objective was to determine the accuracy of their localisation in our experimental setting. In this work, the performance of the DeepFiTM will be benchmarked with the FTM Bhattacharyya [10] which returned the best result from our previous work in [10] and a competing FTM weighted euclidean distance method in [9]. The benchmark approaches in [10] and [9] uses the Weighted K-Nearest Neighbor (WKNN) method [15] to calculate the location estimate.…”

“…Experimental results reported a sub-meter localization error using a weighted euclidean distance. In our previous work [10], we proposed two novel solutions; the Unscented Kalman Filter (UKF) and FTM fingerprinting using Bhattacharyya and euclidean distance. We reported an average localization errors of 1.12 m and 2.13 m for the 67-th and 95-th percentiles, respectively.…”

“…We reported an average localization errors of 1.12 m and 2.13 m for the 67-th and 95-th percentiles, respectively. Following our earlier research [10], this work seeks to improve the localization accuracy even more through a DNN-based indoor fingerprinting localization using WiFi FTM. To the best of our knowledge, this is the first study to investigate the potential of achieving a high accuracy for indoor localization through DNN with WiFi FTM.…”