MEC-based UWB Indoor Tracking System

Abstract

Real-time localization is the underlying requirement for providing context-aware services in the Internet of Things (IoT), Although several methods have been proposed to provide indoor localization, most of them implement the running algorithms locally in the mobile device to be located. However, the limited computational resources of mobile devices make it difficult to run complex algorithms. As an alternative, Multi-Access Edge Computing (MEC) as a promising paradigm extends the traditional cloud computing capabilities towards the edge of the network. This enables accurate location-aware services. In this work, we present an indoor tracking system based on the MEC paradigm for ultra wide band devices. Our tracking algorithms fuse machine learning-based zone prediction, Ultra Wide Band (UWB) radio ranging, inertial measurement units, and floor plan information into an enhanced particle filter. The localization process is hosted in an Edge server, which performs the resource-demanding calculation that is offloaded from the client devices. Moreover, the client devices are also equipped with certain processing power to handle sensor data processing. Our system includes also a Cloud layer, which enables data storage and data visualization for multiple clients. We evaluate our system in two complex environments. Experiment results show that our tracking system can achieve the average tracking error of 0.49 meters and 90% accuracy of 0.6 meters in real-time.