Gaussian Mixture Models for Control of Quasi-Passive Spinal Exoskeletons
Research and development of active and passive exoskeletons for preventing work related injuries has steadily increased in the last decade. Recently, new types of quasi-passive designs have been emerging. These exoskeletons use passive viscoelastic elements, such as springs and dampers, to provide s...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/9/2705 |
id |
doaj-3c639950d1a544aa91d004af4743797e |
---|---|
record_format |
Article |
spelling |
doaj-3c639950d1a544aa91d004af4743797e2020-11-25T03:10:02ZengMDPI AGSensors1424-82202020-05-01202705270510.3390/s20092705Gaussian Mixture Models for Control of Quasi-Passive Spinal ExoskeletonsMarko Jamšek0Tadej Petrič1Jan Babič2Laboratory for Neuromechanics and Biorobotics, Department of Automation, Biocybernetics and Robotics, Jožef Stefan Institute, 1000 Ljubljana, SloveniaLaboratory for Neuromechanics and Biorobotics, Department of Automation, Biocybernetics and Robotics, Jožef Stefan Institute, 1000 Ljubljana, SloveniaLaboratory for Neuromechanics and Biorobotics, Department of Automation, Biocybernetics and Robotics, Jožef Stefan Institute, 1000 Ljubljana, SloveniaResearch and development of active and passive exoskeletons for preventing work related injuries has steadily increased in the last decade. Recently, new types of quasi-passive designs have been emerging. These exoskeletons use passive viscoelastic elements, such as springs and dampers, to provide support to the user, while using small actuators only to change the level of support or to disengage the passive elements. Control of such devices is still largely unexplored, especially the algorithms that predict the movement of the user, to take maximum advantage of the passive viscoelastic elements. To address this issue, we developed a new control scheme consisting of Gaussian mixture models (GMM) in combination with a state machine controller to identify and classify the movement of the user as early as possible and thus provide a timely control output for the quasi-passive spinal exoskeleton. In a leave-one-out cross-validation procedure, the overall accuracy for providing support to the user was <inline-formula> <math display="inline"> <semantics> <mrow> <mn>86</mn> <mo>.</mo> <mn>72</mn> <mo>±</mo> <mn>0</mn> <mo>.</mo> <mn>86</mn> </mrow> </semantics> </math> </inline-formula>% (mean ± s.d.) with a sensitivity and specificity of <inline-formula> <math display="inline"> <semantics> <mrow> <mn>97</mn> <mo>.</mo> <mn>46</mn> <mo>±</mo> <mn>2</mn> <mo>.</mo> <mn>09</mn> </mrow> </semantics> </math> </inline-formula>% and <inline-formula> <math display="inline"> <semantics> <mrow> <mn>83</mn> <mo>.</mo> <mn>15</mn> <mo>±</mo> <mn>0</mn> <mo>.</mo> <mn>85</mn> </mrow> </semantics> </math> </inline-formula>% respectively. The results of this study indicate that our approach is a promising tool for the control of quasi-passive spinal exoskeletons.https://www.mdpi.com/1424-8220/20/9/2705pattern recognitionmovement predictionexoskeleton controlclutched elastic actuators |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Marko Jamšek Tadej Petrič Jan Babič |
spellingShingle |
Marko Jamšek Tadej Petrič Jan Babič Gaussian Mixture Models for Control of Quasi-Passive Spinal Exoskeletons Sensors pattern recognition movement prediction exoskeleton control clutched elastic actuators |
author_facet |
Marko Jamšek Tadej Petrič Jan Babič |
author_sort |
Marko Jamšek |
title |
Gaussian Mixture Models for Control of Quasi-Passive Spinal Exoskeletons |
title_short |
Gaussian Mixture Models for Control of Quasi-Passive Spinal Exoskeletons |
title_full |
Gaussian Mixture Models for Control of Quasi-Passive Spinal Exoskeletons |
title_fullStr |
Gaussian Mixture Models for Control of Quasi-Passive Spinal Exoskeletons |
title_full_unstemmed |
Gaussian Mixture Models for Control of Quasi-Passive Spinal Exoskeletons |
title_sort |
gaussian mixture models for control of quasi-passive spinal exoskeletons |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2020-05-01 |
description |
Research and development of active and passive exoskeletons for preventing work related injuries has steadily increased in the last decade. Recently, new types of quasi-passive designs have been emerging. These exoskeletons use passive viscoelastic elements, such as springs and dampers, to provide support to the user, while using small actuators only to change the level of support or to disengage the passive elements. Control of such devices is still largely unexplored, especially the algorithms that predict the movement of the user, to take maximum advantage of the passive viscoelastic elements. To address this issue, we developed a new control scheme consisting of Gaussian mixture models (GMM) in combination with a state machine controller to identify and classify the movement of the user as early as possible and thus provide a timely control output for the quasi-passive spinal exoskeleton. In a leave-one-out cross-validation procedure, the overall accuracy for providing support to the user was <inline-formula> <math display="inline"> <semantics> <mrow> <mn>86</mn> <mo>.</mo> <mn>72</mn> <mo>±</mo> <mn>0</mn> <mo>.</mo> <mn>86</mn> </mrow> </semantics> </math> </inline-formula>% (mean ± s.d.) with a sensitivity and specificity of <inline-formula> <math display="inline"> <semantics> <mrow> <mn>97</mn> <mo>.</mo> <mn>46</mn> <mo>±</mo> <mn>2</mn> <mo>.</mo> <mn>09</mn> </mrow> </semantics> </math> </inline-formula>% and <inline-formula> <math display="inline"> <semantics> <mrow> <mn>83</mn> <mo>.</mo> <mn>15</mn> <mo>±</mo> <mn>0</mn> <mo>.</mo> <mn>85</mn> </mrow> </semantics> </math> </inline-formula>% respectively. The results of this study indicate that our approach is a promising tool for the control of quasi-passive spinal exoskeletons. |
topic |
pattern recognition movement prediction exoskeleton control clutched elastic actuators |
url |
https://www.mdpi.com/1424-8220/20/9/2705 |
work_keys_str_mv |
AT markojamsek gaussianmixturemodelsforcontrolofquasipassivespinalexoskeletons AT tadejpetric gaussianmixturemodelsforcontrolofquasipassivespinalexoskeletons AT janbabic gaussianmixturemodelsforcontrolofquasipassivespinalexoskeletons |
_version_ |
1724661036113461248 |