Cargando…
Fault-Tolerant Six-DoF Pose Estimation for Tendon-Driven Continuum Mechanisms
We propose a fault-tolerant estimation technique for the six-DoF pose of a tendon-driven continuum mechanisms using machine learning. In contrast to previous estimation techniques, no deformation model is required, and the pose prediction is rather performed with polynomial regression. As only a few...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8120429/ https://www.ncbi.nlm.nih.gov/pubmed/33996921 http://dx.doi.org/10.3389/frobt.2021.619238 |
_version_ | 1783692095481970688 |
---|---|
author | Raffin, Antonin Deutschmann, Bastian Stulp, Freek |
author_facet | Raffin, Antonin Deutschmann, Bastian Stulp, Freek |
author_sort | Raffin, Antonin |
collection | PubMed |
description | We propose a fault-tolerant estimation technique for the six-DoF pose of a tendon-driven continuum mechanisms using machine learning. In contrast to previous estimation techniques, no deformation model is required, and the pose prediction is rather performed with polynomial regression. As only a few datapoints are required for the regression, several estimators are trained with structured occlusions of the available sensor information, and clustered into ensembles based on the available sensors. By computing the variance of one ensemble, the uncertainty in the prediction is monitored and, if the variance is above a threshold, sensor loss is detected and handled. Experiments on the humanoid neck of the DLR robot DAVID, demonstrate that the accuracy of the predicted pose is significantly improved, and a reliable prediction can still be performed using only 3 out of 8 sensors. |
format | Online Article Text |
id | pubmed-8120429 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-81204292021-05-15 Fault-Tolerant Six-DoF Pose Estimation for Tendon-Driven Continuum Mechanisms Raffin, Antonin Deutschmann, Bastian Stulp, Freek Front Robot AI Robotics and AI We propose a fault-tolerant estimation technique for the six-DoF pose of a tendon-driven continuum mechanisms using machine learning. In contrast to previous estimation techniques, no deformation model is required, and the pose prediction is rather performed with polynomial regression. As only a few datapoints are required for the regression, several estimators are trained with structured occlusions of the available sensor information, and clustered into ensembles based on the available sensors. By computing the variance of one ensemble, the uncertainty in the prediction is monitored and, if the variance is above a threshold, sensor loss is detected and handled. Experiments on the humanoid neck of the DLR robot DAVID, demonstrate that the accuracy of the predicted pose is significantly improved, and a reliable prediction can still be performed using only 3 out of 8 sensors. Frontiers Media S.A. 2021-04-30 /pmc/articles/PMC8120429/ /pubmed/33996921 http://dx.doi.org/10.3389/frobt.2021.619238 Text en Copyright © 2021 Raffin, Deutschmann and Stulp. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Robotics and AI Raffin, Antonin Deutschmann, Bastian Stulp, Freek Fault-Tolerant Six-DoF Pose Estimation for Tendon-Driven Continuum Mechanisms |
title | Fault-Tolerant Six-DoF Pose Estimation for Tendon-Driven Continuum Mechanisms |
title_full | Fault-Tolerant Six-DoF Pose Estimation for Tendon-Driven Continuum Mechanisms |
title_fullStr | Fault-Tolerant Six-DoF Pose Estimation for Tendon-Driven Continuum Mechanisms |
title_full_unstemmed | Fault-Tolerant Six-DoF Pose Estimation for Tendon-Driven Continuum Mechanisms |
title_short | Fault-Tolerant Six-DoF Pose Estimation for Tendon-Driven Continuum Mechanisms |
title_sort | fault-tolerant six-dof pose estimation for tendon-driven continuum mechanisms |
topic | Robotics and AI |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8120429/ https://www.ncbi.nlm.nih.gov/pubmed/33996921 http://dx.doi.org/10.3389/frobt.2021.619238 |
work_keys_str_mv | AT raffinantonin faulttolerantsixdofposeestimationfortendondrivencontinuummechanisms AT deutschmannbastian faulttolerantsixdofposeestimationfortendondrivencontinuummechanisms AT stulpfreek faulttolerantsixdofposeestimationfortendondrivencontinuummechanisms |