Advanced Assistive Maintenance Based on Augmented Reality and 5G Networking.

Sebastiano Verde,Simone Milani,Marco Marcon,Stefano Tubaro

doi:10.3390/s20247157

Sebastiano Verde, Simone Milani + Show 2 more

Open Access

https://doi.org/10.3390/s20247157

Copy DOI

Abstract

Internet of Things (IoT) applications play a relevant role in today’s industry in sharing diagnostic data with off-site service teams, as well as in enabling reliable predictive maintenance systems. Several interventions scenarios, however, require the physical presence of a human operator: Augmented Reality (AR), together with a broad-band connection, represents a major opportunity to integrate diagnostic data with real-time in-situ acquisitions. Diagnostic information can be shared with remote specialists that are able to monitor and guide maintenance operations from a control room as if they were in place. Furthermore, integrating heterogeneous sensors with AR visualization displays could largely improve operators’ safety in complex and dangerous industrial plants. In this paper, we present a complete setup for a remote assistive maintenance intervention based on 5G networking and tested at a Vodafone Base Transceiver Station (BTS) within the Vodafone 5G Program. Technicians’ safety was improved by means of a lightweight AR Head-Mounted Display (HDM) equipped with a thermal camera and a depth sensor to foresee possible collisions with hot surfaces and dangerous objects, by leveraging the processing power of remote computing paired with the low latency of 5G connection. Field testing confirmed that the proposed approach can be a viable solution for egocentric environment understanding and enables an immersive integration of the obtained augmented data within the real scene.

Highlights

Due to the growing cost of specialized technicians, the increasing complexity of maintenance work and the rising criticality of long machine downtime, Augmented Reality (AR) is playing an ever-growing role in advanced and remotely assisted maintenance [1,2]
For the purpose of implementing a reliable framework for assistive maintenance, we addressed a particular focus to the real-time response of the obstacle detection system
In order to evaluate it, we used as Key Performance Indicator (KPI) the mesh processing time in relation to the number of points and triangles

Summary

Introduction

Due to the growing cost of specialized technicians, the increasing complexity of maintenance work and the rising criticality of long machine downtime, Augmented Reality (AR) is playing an ever-growing role in advanced and remotely assisted maintenance [1,2]. New employees need on-site oversight from more experienced technicians, which implies increasing costs and complicating the labor model, compromising service efficiency and effectiveness. Nowadays, these solutions alone are not enough: the whole system can be made more efficient by adopting newer models that enable the assistive guidance of experienced workers without being physically on-site, and deliver guidance to more apprentices at the same time. Thanks to emerging technologies such as AR helmets and 5G networking, traditional interactions by means of cellphones or work-specific messenger applications are overtaken by more immersive and interactive approaches

Objectives

Results

Conclusion