Indoor Positioning using Wi-Fi and Machine Learning for Industry 5.0

TL;DR

This paper presents a novel indoor positioning system for Industry 5.0 using Wi-Fi RSSI and machine learning, enabling real-time safe distance detection between humans and robots with high accuracy.

Contribution

It introduces a cost-effective indoor positioning approach leveraging Wi-Fi RSSI and machine learning for Industry 5.0 applications, demonstrating real-time safety monitoring.

Findings

Average deviation of less than 1 meter in distance measurement

Effective real-time detection of safe proximity between humans and robots

Utilization of low-cost ESP32 Arduino boards for indoor positioning

Abstract

Humans and robots working together in an environment to enhance human performance is the aim of Industry 5.0. Although significant progress in outdoor positioning has been seen, indoor positioning remains a challenge. In this paper, we introduce a new research concept by exploiting the potential of indoor positioning for Industry 5.0. We use Wi-Fi Received Signal Strength Indicator (RSSI) with trilateration using cheap and easily available ESP32 Arduino boards for positioning as well as sending effective route signals to a human and a robot working in a simulated-indoor factory environment in real-time. We utilized machine learning models to detect safe closeness between two co-workers (a human subject and a robot). Experimental data and analysis show an average deviation of less than 1m from the actual distance while the targets are mobile or stationary.