Hybrid Indoor Localization via Reinforcement Learning-based Information Fusion

TL;DR

This paper introduces a reinforcement learning-based fusion framework that combines AoA, RSSI, and IMU data to improve indoor localization accuracy in smart city environments, addressing limitations of standalone models.

Contribution

It proposes a novel RL-based information fusion framework (RL-IFF) that integrates multiple localization methods for enhanced indoor positioning accuracy.

Findings

RL-IFF outperforms standalone models in accuracy

Fusion of AoA, RSSI, and IMU improves robustness

Experimental results demonstrate superior localization performance

Abstract

The paper is motivated by the importance of the Smart Cities (SC) concept for future management of global urbanization. Among all Internet of Things (IoT)-based communication technologies, Bluetooth Low Energy (BLE) plays a vital role in city-wide decision making and services. Extreme fluctuations of the Received Signal Strength Indicator (RSSI), however, prevent this technology from being a reliable solution with acceptable accuracy in the dynamic indoor tracking/localization approaches for ever-changing SC environments. The latest version of the BLE v.5.1 introduced a better possibility for tracking users by utilizing the direction finding approaches based on the Angle of Arrival (AoA), which is more reliable. There are still some fundamental issues remaining to be addressed. Existing works mainly focus on implementing stand-alone models overlooking potentials fusion strategies. The paper addresses this gap and proposes a novel Reinforcement Learning (RL)-based information fusion framework (RL-IFF) by coupling AoA with RSSI-based particle filtering and Inertial Measurement Unit (IMU)-based Pedestrian Dead Reckoning (PDR) frameworks. The proposed RL-IFF solution is evaluated through a comprehensive set of experiments illustrating superior performance compared to its counterparts.