Citation: Li, C.; Chrysostomou, D.;
Pinto, D.; Hansen, A.K.; Bøgh, S.;
Madsen, O. Hey Max, Can You Help
Me? An Intuitive Virtual Assistant
for Industrial Robots. Appl. Sci. 2023,
13, 205. https://doi.org/10.3390/
app13010205
Academic Editors: Gabriele Baronio,
Enrico Vezzetti, Andrea Luigi Guerra,
Domenico Speranza, Luca Ulrich and
Alexandre Carvalho
Received: 2 October 2022
Revised: 18 October 2022
Accepted: 18 December 2022
Published: 23 December 2022
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Hey Max, Can You Help Me? An Intuitive Virtual Assistant for
Industrial Robots
Chen Li
1,
* , Dimitrios Chrysostomou
1
, Daniela Pinto
1
, Andreas Kornmaaler Hansen
2,3
, Simon Bøgh
1
and Ole Madsen
1
1
Robotics and Automation Group, Department of Materials and Production, Aalborg University,
Fibigerstraede 16, 9220 Aalborg, Denmark
2
Center for Industrial Production, Department of Materials and Production, Aalborg University,
Fibigerstraede 16, 9220 Aalborg, Denmark
3
Department of Technology and Business, University College of Northern Denmark, Sofiendalsvej 60,
9000 Aalborg, Denmark
* Correspondence: cl@mp.aau.dk; Tel.: +45-52-645-576
Abstract:
Assisting employees in acquiring the knowledge and skills necessary to use new services
and technologies on the shop floor is critical for manufacturers to adapt to Industry 4.0 successfully.
In this paper, we employ a learning, training, assistance-formats, issues, tools (LTA-FIT) approach
and propose a framework for a language-enabled virtual assistant (VA) to facilitate this adaptation.
In our system, the human–robot interaction is achieved through spoken natural language and a
dashboard implemented as a web-based application. This type of interaction enables operators of
all levels to control a collaborative robot intuitively in several industrial scenarios and use it as a
complementary tool for developing their competencies. Our proposed framework has been tested
with 29 users who completed various tasks while interacting with the proposed VA and industrial
robots. Through three different scenarios, we evaluated the usability of the system for LTA-FIT based
on an established system usability scale (SUS) and the cognitive effort required by the users based
on the standardised NASA-TLX questionnaire. The qualitative and quantitative results of the study
show that users of all levels found the VA user friendly with low requirements for physical and
mental effort during the interaction.
Keywords:
natural language processing; virtual assistant; human–robot interaction; usability studies;
NASA TLX; system usability scale
1. Introduction
Digitalization is changing the manufacturing world. The exponential growth in digital
technologies provides manufacturing companies with possibilities for introducing new
products, processes, and services, many of which have the potential to be disruptive. Hence,
the manufacturing industry has adapted to Industry 4.0 values and is slowly transitioning
to the Industry 5.0 era [
1
]. However, due to the complexity of the manufacturing tasks and
the speed of the technological development, the adoption of new technologies remains a
grand challenge [2].
As the nature of many proposed solutions typically involves multidisciplinary activi-
ties, operators with years of experience and domain knowledge are needed. However, in
modern industrial settings, such expertise is not always readily available, and new, more
flexible approaches for knowledge acquisition and dissemination of learned experience
should be utilized [
3
]. One revolutionary model used to assist workers in their learning
and training is the learning, training, assistance-formats, issues, tools (LTA-FIT) model
proposed by [
4
]. The model offers a flexible approach to assist the re-qualification and
training of workers in new digital tools.
Appl. Sci. 2023, 13, 205. https://doi.org/10.3390/app13010205 https://www.mdpi.com/journal/applsci
