Citation: Vianello, L.; Gomes, W.;
Stulp, F.; Aubry, A.; Maurice, P.;
Ivaldi, S. Latent Ergonomics Maps:
Real-Time Visualization of Estimated
Ergonomics of Human Movements.
Sensors 2022, 22, 3981. https://
doi.org/10.3390/s22113981
Academic Editors: Yuansong Qiao
and Seamus Gordon
Received: 24 March 2022
Accepted: 19 May 2022
Published: 24 May 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
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
Latent Ergonomics Maps: Real-Time Visualization of Estimated
Ergonomics of Human Movements
Lorenzo Vianello
1,2,
*
,†
, Waldez Gomes
1,3,
*
,†
, Freek Stulp
4
, Alexis Aubry
2
, Pauline Maurice
1
and Serena Ivaldi
1
1
Université de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France; pauline.maurice@loria.fr (P.M.);
serena.ivaldi@inria.fr (S.I.)
2
Université de Lorraine, CNRS, CRAN, F-54000 Nancy, France; alexis.aubry@univ-lorraine.fr
3
CIAMS, Université Paris-Saclay, F-91405 Orsay, France
4
Department of Cognitive Robotics, Institute of Robotics and Mechatronics, German Aerospace Center (DLR),
82234 Wessling, Germany; freek.stulp@dlr.de
* Correspondence: lorenzo.vianello@univ-lorraine.fr (L.V.); waldez@ieee.org (W.G.)
† These authors contributed equally to this work.
Abstract:
Improving the ergonomy of working environments is essential to reducing work-related
musculo-skeletal disorders. We consider real-time ergonomic feedback a key technology for achieving
such improvements. To this end, we present supportive tools for online evaluation and visualization
of strenuous efforts and postures of a worker, also when physically interacting with a robot. A digital
human model is used to estimate human kinematics and dynamics and visualize non-ergonomic
joint angles, based on the on-line data acquired from a wearable motion tracking device.
Keywords: ergonomics tools; digital human model; wearable sensors
1. Introduction
Poor ergonomics conditions in work environments may lead to serious work-related
musculoskeletal disorders (WMSDs), including severe disabilities [
1
]. The development
of WMSDs is an issue not only for the workers’ health and well-being but also repre-
sents an important cost for companies and society [
2
,
3
]. In recent years, there has been
a surge in robotic solutions for ergonomics interventions, notably using industrial ma-
nipulators conceived for collaboration with humans (i.e., cobots) and exoskeletons [
4
,
5
].
These robotics solutions require ergonomics specialists to identify dangerous conditions and
develop adequate interventions, whilst maintaining operational safety and productivity.
Classic kinematics ergonomics evaluation tools such as RULA, REBA and OWAS
[6–8]
use human joint positions to produce an ergonomics score for a given body posture.
Kinematics-based scores are fast to compute, but dynamics aspects of the task may not
be negligible [
9
]. Dynamics estimation may be an important complementary evaluation
to the classic tools throughout an entire task execution, as they are more suitable for
evaluating more accurately varied body morphologies, and external wrenches applied
to the human body. Many recent works evaluate dynamic aspects of the task execution,
such as internal and external human wrenches [10–13].
Recently, there has been much attention on improving the intuitiveness of ergonomics
evaluation tools, as industrial operators should not be expected to have a background in er-
gonomics. Previous works have used digital human models (DHMs) alongside different
types of visual cues for ergonomics evaluation: visualization of the human DHM with
colored joints [
14
] or displaying relevant information such as COP [
15
], overloaded joint
torque [11], level of fatigue [16].
The data relevant to assessing ergonomics is high-dimensional, including kinematic
and dynamic state variables related to posture and efforts. This high-dimensional data
Sensors 2022, 22, 3981. https://doi.org/10.3390/s22113981 https://www.mdpi.com/journal/sensors
