Cargando…

A Recurrent Neural-Network-Based Real-Time Dynamic Model for Soft Continuum Manipulators

This paper introduces and validates a real-time dynamic predictive model based on a neural network approach for soft continuum manipulators. The presented model provides a real-time prediction framework using neural-network-based strategies and continuum mechanics principles. A time-space integratio...

Descripción completa

Detalles Bibliográficos
Autores principales: Tariverdi, Abbas, Venkiteswaran, Venkatasubramanian Kalpathy, Richter, Michiel, Elle, Ole J., Tørresen, Jim, Mathiassen, Kim, Misra, Sarthak, Martinsen, Ørjan G.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8044932/
https://www.ncbi.nlm.nih.gov/pubmed/33869294
http://dx.doi.org/10.3389/frobt.2021.631303
_version_ 1783678597062459392
author Tariverdi, Abbas
Venkiteswaran, Venkatasubramanian Kalpathy
Richter, Michiel
Elle, Ole J.
Tørresen, Jim
Mathiassen, Kim
Misra, Sarthak
Martinsen, Ørjan G.
author_facet Tariverdi, Abbas
Venkiteswaran, Venkatasubramanian Kalpathy
Richter, Michiel
Elle, Ole J.
Tørresen, Jim
Mathiassen, Kim
Misra, Sarthak
Martinsen, Ørjan G.
author_sort Tariverdi, Abbas
collection PubMed
description This paper introduces and validates a real-time dynamic predictive model based on a neural network approach for soft continuum manipulators. The presented model provides a real-time prediction framework using neural-network-based strategies and continuum mechanics principles. A time-space integration scheme is employed to discretize the continuous dynamics and decouple the dynamic equations for translation and rotation for each node of a soft continuum manipulator. Then the resulting architecture is used to develop distributed prediction algorithms using recurrent neural networks. The proposed RNN-based parallel predictive scheme does not rely on computationally intensive algorithms; therefore, it is useful in real-time applications. Furthermore, simulations are shown to illustrate the approach performance on soft continuum elastica, and the approach is also validated through an experiment on a magnetically-actuated soft continuum manipulator. The results demonstrate that the presented model can outperform classical modeling approaches such as the Cosserat rod model while also shows possibilities for being used in practice.
format Online
Article
Text
id pubmed-8044932
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-80449322021-04-15 A Recurrent Neural-Network-Based Real-Time Dynamic Model for Soft Continuum Manipulators Tariverdi, Abbas Venkiteswaran, Venkatasubramanian Kalpathy Richter, Michiel Elle, Ole J. Tørresen, Jim Mathiassen, Kim Misra, Sarthak Martinsen, Ørjan G. Front Robot AI Robotics and AI This paper introduces and validates a real-time dynamic predictive model based on a neural network approach for soft continuum manipulators. The presented model provides a real-time prediction framework using neural-network-based strategies and continuum mechanics principles. A time-space integration scheme is employed to discretize the continuous dynamics and decouple the dynamic equations for translation and rotation for each node of a soft continuum manipulator. Then the resulting architecture is used to develop distributed prediction algorithms using recurrent neural networks. The proposed RNN-based parallel predictive scheme does not rely on computationally intensive algorithms; therefore, it is useful in real-time applications. Furthermore, simulations are shown to illustrate the approach performance on soft continuum elastica, and the approach is also validated through an experiment on a magnetically-actuated soft continuum manipulator. The results demonstrate that the presented model can outperform classical modeling approaches such as the Cosserat rod model while also shows possibilities for being used in practice. Frontiers Media S.A. 2021-03-18 /pmc/articles/PMC8044932/ /pubmed/33869294 http://dx.doi.org/10.3389/frobt.2021.631303 Text en Copyright © 2021 Tariverdi, Venkiteswaran, Richter, Elle, Tørresen, Mathiassen, Misra and Martinsen. 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
Tariverdi, Abbas
Venkiteswaran, Venkatasubramanian Kalpathy
Richter, Michiel
Elle, Ole J.
Tørresen, Jim
Mathiassen, Kim
Misra, Sarthak
Martinsen, Ørjan G.
A Recurrent Neural-Network-Based Real-Time Dynamic Model for Soft Continuum Manipulators
title A Recurrent Neural-Network-Based Real-Time Dynamic Model for Soft Continuum Manipulators
title_full A Recurrent Neural-Network-Based Real-Time Dynamic Model for Soft Continuum Manipulators
title_fullStr A Recurrent Neural-Network-Based Real-Time Dynamic Model for Soft Continuum Manipulators
title_full_unstemmed A Recurrent Neural-Network-Based Real-Time Dynamic Model for Soft Continuum Manipulators
title_short A Recurrent Neural-Network-Based Real-Time Dynamic Model for Soft Continuum Manipulators
title_sort recurrent neural-network-based real-time dynamic model for soft continuum manipulators
topic Robotics and AI
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8044932/
https://www.ncbi.nlm.nih.gov/pubmed/33869294
http://dx.doi.org/10.3389/frobt.2021.631303
work_keys_str_mv AT tariverdiabbas arecurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT venkiteswaranvenkatasubramaniankalpathy arecurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT richtermichiel arecurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT elleolej arecurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT tørresenjim arecurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT mathiassenkim arecurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT misrasarthak arecurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT martinsenørjang arecurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT tariverdiabbas recurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT venkiteswaranvenkatasubramaniankalpathy recurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT richtermichiel recurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT elleolej recurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT tørresenjim recurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT mathiassenkim recurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT misrasarthak recurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators
AT martinsenørjang recurrentneuralnetworkbasedrealtimedynamicmodelforsoftcontinuummanipulators