Research on Posture Sensing and Error Elimination for Soft Manipulator Using FBG Sensors
Fiber-optic sensors are highly promising within soft robot sensing applications, but sensing methods based on geometry-based reconstruction limit the sensing capability and range. In this study, a fiber-optic sensor with a different deployment strategy for indirect sensing to monitor the outside pos...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-03-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/6/1476 |
_version_ | 1797612179791282176 |
---|---|
author | Wenyu Li Yanlin He Peng Geng Yi Yang |
author_facet | Wenyu Li Yanlin He Peng Geng Yi Yang |
author_sort | Wenyu Li |
collection | DOAJ |
description | Fiber-optic sensors are highly promising within soft robot sensing applications, but sensing methods based on geometry-based reconstruction limit the sensing capability and range. In this study, a fiber-optic sensor with a different deployment strategy for indirect sensing to monitor the outside posture of a soft manipulator is presented. The internal support structure’s curvature was measured using the FBG sensor, and its mapping to the external pose was then modelled using a modified LSTM network. The error was assumed to follow the Gaussian distribution in the LSTM neural network and was rectified by maximum likelihood estimation to address the issue of noise generated during the deformation transfer and curvature sensing of the soft structure. For the soft manipulator, the network model’s sensing performance was demonstrated. The proposed method’s average absolute error for posture sensing was 63.3% lower than the error before optimization, and the root mean square error was 56.9% lower than the error before optimization. The comparison results between the experiment and the simulation demonstrate the viability of the indirect measurement of the soft structure posture using FBG sensors based on the data-driven method, as well as the significant impact of the error optimization method based on the Gaussian distribution assumption. |
first_indexed | 2024-03-11T06:37:39Z |
format | Article |
id | doaj.art-3d954744c8544478b3510c9dbb34f265 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-11T06:37:39Z |
publishDate | 2023-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-3d954744c8544478b3510c9dbb34f2652023-11-17T10:46:04ZengMDPI AGElectronics2079-92922023-03-01126147610.3390/electronics12061476Research on Posture Sensing and Error Elimination for Soft Manipulator Using FBG SensorsWenyu Li0Yanlin He1Peng Geng2Yi Yang3Beijing Laboratory of Optical Fiber Sensing and System, Beijing Information Science & Technology University, Beijing 100192, ChinaBeijing Laboratory of Optical Fiber Sensing and System, Beijing Information Science & Technology University, Beijing 100192, ChinaBeijing Laboratory of Optical Fiber Sensing and System, Beijing Information Science & Technology University, Beijing 100192, ChinaBeijing Laboratory of Optical Fiber Sensing and System, Beijing Information Science & Technology University, Beijing 100192, ChinaFiber-optic sensors are highly promising within soft robot sensing applications, but sensing methods based on geometry-based reconstruction limit the sensing capability and range. In this study, a fiber-optic sensor with a different deployment strategy for indirect sensing to monitor the outside posture of a soft manipulator is presented. The internal support structure’s curvature was measured using the FBG sensor, and its mapping to the external pose was then modelled using a modified LSTM network. The error was assumed to follow the Gaussian distribution in the LSTM neural network and was rectified by maximum likelihood estimation to address the issue of noise generated during the deformation transfer and curvature sensing of the soft structure. For the soft manipulator, the network model’s sensing performance was demonstrated. The proposed method’s average absolute error for posture sensing was 63.3% lower than the error before optimization, and the root mean square error was 56.9% lower than the error before optimization. The comparison results between the experiment and the simulation demonstrate the viability of the indirect measurement of the soft structure posture using FBG sensors based on the data-driven method, as well as the significant impact of the error optimization method based on the Gaussian distribution assumption.https://www.mdpi.com/2079-9292/12/6/1476soft manipulatorposture sensingdeep learningfiber optic sensor |
spellingShingle | Wenyu Li Yanlin He Peng Geng Yi Yang Research on Posture Sensing and Error Elimination for Soft Manipulator Using FBG Sensors Electronics soft manipulator posture sensing deep learning fiber optic sensor |
title | Research on Posture Sensing and Error Elimination for Soft Manipulator Using FBG Sensors |
title_full | Research on Posture Sensing and Error Elimination for Soft Manipulator Using FBG Sensors |
title_fullStr | Research on Posture Sensing and Error Elimination for Soft Manipulator Using FBG Sensors |
title_full_unstemmed | Research on Posture Sensing and Error Elimination for Soft Manipulator Using FBG Sensors |
title_short | Research on Posture Sensing and Error Elimination for Soft Manipulator Using FBG Sensors |
title_sort | research on posture sensing and error elimination for soft manipulator using fbg sensors |
topic | soft manipulator posture sensing deep learning fiber optic sensor |
url | https://www.mdpi.com/2079-9292/12/6/1476 |
work_keys_str_mv | AT wenyuli researchonposturesensinganderroreliminationforsoftmanipulatorusingfbgsensors AT yanlinhe researchonposturesensinganderroreliminationforsoftmanipulatorusingfbgsensors AT penggeng researchonposturesensinganderroreliminationforsoftmanipulatorusingfbgsensors AT yiyang researchonposturesensinganderroreliminationforsoftmanipulatorusingfbgsensors |