Localization in an Industrial Environment: A Case Study on the Difficulties for Positioning in a Harsh Environment

Abstract

While indoor localization has become a highly growing application domain in the last few years, it is hardly investigated in industrial environments. Interferences of magnetic fields, shadowing, and multipath propagation discourage positioning system vendors from porting their techniques to these harsh environments. However, the actual influence of these interferences on the positioning accuracy and the differences between an industrial and a nonindustrial environment have never been evaluated. This paper analyzes the actual differences for a positioning technique that is based on Wi-Fi fingerprinting, map matching, dead reckoning, filtering, and a plausibility determination. An investigation of the Wi-Fi signal strengths and compass sensor values in an industrial and a nonindustrial environment thereby showed that the differences between them are significant. In fact, it shows that more interferences and shadowing in the industrial environment resulted in even more accurate positioning.

Evaluation of accurate indoor localization systems in industrial environments

“…Several studies have been conducted that investigate the challenges and solutions for localization technologies in industrial-like environments [1,7,11,12]. However, unlike the focus of this paper, they generally study fingerprinting based technologies or solutions, which realize lower level of accuracy, or lack a comparison in real-life conditions.…”

“…In [1], Holzl et al evaluate the impact of electromagnetic influences and shadowing effects in an industrial environment on the accuracy of positioning systems that are based on Wi-Fi fingerprinting and dead reckoning. Similarly, in [7], a Wi-Fi fingerprinting method is studied for an indoor positioning application in a real construction site and a practical labor tracking application is developed.…”

“…In recent years, the demand for indoor localization solutions has been rapidly expanding in many fields [1][2][3]. Particularly, there is a significant potential for such applications in the industrial world to improve automation and increase efficiency, including tracking goods and robots, operator guidance, etc.…”

“…Particularly, there is a significant potential for such applications in the industrial world to improve automation and increase efficiency, including tracking goods and robots, operator guidance, etc. However, industrial environments impose additional challenges for localization systems because of the large number of active and passive perturbations, especially shadowing and multipath effects due to metallic objects [1,4,5]. Therefore, there is a need for further evaluation and validation of current localization technologies in real-life industrial conditions.…”

Fully Connected Neural Networks Ensemble with Signal Strength Clustering for Indoor Localization in Wireless Sensor Networks

“…In many cases sensor readings collected in WSN are not useful without the location information. Thus, there is a growing research interest in the localization methods due to their potential use in a variety of WSN applications [3].…”