Using Machine Learning to Localize BLE devices on a Single Anchor

Abstract

Indoor localization using Bluetooth Low Energy (BLE) technology can be accomplished by a variety of methods. One appreciable benefits is the single-anchor solution, which allows for low-cost deployments. In this paper, five different methods of single-anchor localization have been investigated, including different methods of determining the angle of arrival and distance estimation. The best performing single-anchor localization method was found to be a dedicated machine learning algorithm whose output is the location of the target device. Once a Kalman filter was applied to it, it achieved a mean distance error of 0.34 m on the test scenario.