Human–Exoskeleton Interaction Force Estimation in Indego Exoskeleton
Accurate interaction force estimation can play an important role in optimizing human–robot interaction in an exoskeleton. In this work, we propose a novel approach for the system identification of exoskeleton dynamics in the presence of interaction forces as a whole multibody system without imposing...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-05-01
|
Series: | Robotics |
Subjects: | |
Online Access: | https://www.mdpi.com/2218-6581/12/3/66 |
_version_ | 1797592782976581632 |
---|---|
author | Mohammad Shushtari Arash Arami |
author_facet | Mohammad Shushtari Arash Arami |
author_sort | Mohammad Shushtari |
collection | DOAJ |
description | Accurate interaction force estimation can play an important role in optimizing human–robot interaction in an exoskeleton. In this work, we propose a novel approach for the system identification of exoskeleton dynamics in the presence of interaction forces as a whole multibody system without imposing any constraints on the exoskeleton dynamics. We hung the exoskeleton through a linear spring and excited the exoskeleton joints with chirp commands while measuring the exoskeleton–environment interaction force. Several structures of neural networks were trained to model the exoskeleton passive dynamics and estimate the interaction force. Our testing results indicated that a deep neural network with 250 neurons and 10 time–delays could obtain a sufficiently accurate estimation of the interaction force, resulting in an RMSE of 1.23 on Z–normalized applied torques and an adjusted <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.89. |
first_indexed | 2024-03-11T01:58:07Z |
format | Article |
id | doaj.art-8c732d2ca2a44061bb6a3925d1360e44 |
institution | Directory Open Access Journal |
issn | 2218-6581 |
language | English |
last_indexed | 2024-03-11T01:58:07Z |
publishDate | 2023-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Robotics |
spelling | doaj.art-8c732d2ca2a44061bb6a3925d1360e442023-11-18T12:28:42ZengMDPI AGRobotics2218-65812023-05-011236610.3390/robotics12030066Human–Exoskeleton Interaction Force Estimation in Indego ExoskeletonMohammad Shushtari0Arash Arami1Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON N2L 3G1, CanadaDepartment of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON N2L 3G1, CanadaAccurate interaction force estimation can play an important role in optimizing human–robot interaction in an exoskeleton. In this work, we propose a novel approach for the system identification of exoskeleton dynamics in the presence of interaction forces as a whole multibody system without imposing any constraints on the exoskeleton dynamics. We hung the exoskeleton through a linear spring and excited the exoskeleton joints with chirp commands while measuring the exoskeleton–environment interaction force. Several structures of neural networks were trained to model the exoskeleton passive dynamics and estimate the interaction force. Our testing results indicated that a deep neural network with 250 neurons and 10 time–delays could obtain a sufficiently accurate estimation of the interaction force, resulting in an RMSE of 1.23 on Z–normalized applied torques and an adjusted <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.89.https://www.mdpi.com/2218-6581/12/3/66lower-limb exoskeletondynamic identificationinteraction force estimation |
spellingShingle | Mohammad Shushtari Arash Arami Human–Exoskeleton Interaction Force Estimation in Indego Exoskeleton Robotics lower-limb exoskeleton dynamic identification interaction force estimation |
title | Human–Exoskeleton Interaction Force Estimation in Indego Exoskeleton |
title_full | Human–Exoskeleton Interaction Force Estimation in Indego Exoskeleton |
title_fullStr | Human–Exoskeleton Interaction Force Estimation in Indego Exoskeleton |
title_full_unstemmed | Human–Exoskeleton Interaction Force Estimation in Indego Exoskeleton |
title_short | Human–Exoskeleton Interaction Force Estimation in Indego Exoskeleton |
title_sort | human exoskeleton interaction force estimation in indego exoskeleton |
topic | lower-limb exoskeleton dynamic identification interaction force estimation |
url | https://www.mdpi.com/2218-6581/12/3/66 |
work_keys_str_mv | AT mohammadshushtari humanexoskeletoninteractionforceestimationinindegoexoskeleton AT arasharami humanexoskeletoninteractionforceestimationinindegoexoskeleton |