Matching Pursuit based Joint Angle and Delay Estimation for Bluetooth Direction Finding

Indoor localization is a desired technique for both end-user and industrial applications. The support for Angle of Arrival (AoA) based Direction Finding with version 5.1 of the Bluetooth Core Specification recently generated a particular interest for AoA-based Bluetooth localization systems. Using state-of-the-art AoA estimation algorithms like the Joint Angle and Delay Estimation MUltiple SIgnal Classification (JADE MUSIC) algorithm, high localization accuracies can be achieved with such systems. However, these MUSIC-based algorithms come along with a rather high computational complexity that makes it challenging to implement them in practical systems. Proposing a compromise between localization accuracy and computational complexity, we present a novel Joint Angle and Delay Estimation Matching Pursuit (JADE MP) approach for AoA-based indoor localization. Using a publicly-available dataset from a 100 m(2) Bluetooth 5.1 localization testbed, an evaluation of the proposed algorithm is presented. It is shown that the proposed JADE MP approach can achieve almost the same accuracy as state-of-the-art systems, while being significantly faster at the same time.