Please use this identifier to cite or link to this item: https://doi.org/10.3389/frobt.2021.619390
DC FieldValue
dc.titleDevelopment and Grasp Stability Estimation of Sensorized Soft Robotic Hand
dc.contributor.authorKhin, P. M.
dc.contributor.authorLow, Jin H.
dc.contributor.authorAng, Marcelo H., Jr.
dc.contributor.authorYeow, Chen H.
dc.date.accessioned2022-10-11T08:00:57Z
dc.date.available2022-10-11T08:00:57Z
dc.date.issued2021-03-31
dc.identifier.citationKhin, P. M., Low, Jin H., Ang, Marcelo H., Jr., Yeow, Chen H. (2021-03-31). Development and Grasp Stability Estimation of Sensorized Soft Robotic Hand. Frontiers in Robotics and AI 8 : 619390. ScholarBank@NUS Repository. https://doi.org/10.3389/frobt.2021.619390
dc.identifier.issn2296-9144
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/232113
dc.description.abstractThis paper introduces the development of an anthropomorphic soft robotic hand integrated with multiple flexible force sensors in the fingers. By leveraging on the integrated force sensing mechanism, grip state estimation networks have been developed. The robotic hand was tasked to hold the given object on the table for 1.5 s and lift it up within 1 s. The object manipulation experiment of grasping and lifting the given objects were conducted with various pneumatic pressure (50, 80, and 120 kPa). Learning networks were developed to estimate occurrence of object instability and slippage due to acceleration of the robot or insufficient grasp strength. Hence the grip state estimation network can potentially feedback object stability status to the pneumatic control system. This would allow the pneumatic system to use suitable pneumatic pressure to efficiently handle different objects, i.e., lower pneumatic pressure (50 kPa) for lightweight objects which do not require high grasping strength. The learning process of the soft hand is made challenging by curating a diverse selection of daily objects, some of which displays dynamic change in shape upon grasping. To address the cost of collecting extensive training datasets, we adopted one-shot learning (OSL) technique with a long short-term memory (LSTM) recurrent neural network. OSL aims to allow the networks to learn based on limited training data. It also promotes the scalability of the network to accommodate more grasping objects in the future. Three types of LSTM-based networks have been developed and their performance has been evaluated in this study. Among the three LSTM networks, triplet network achieved overall stability estimation accuracy at 89.96%, followed by LSTM network with 88.00% and Siamese LSTM network with 85.16%. © Copyright © 2021 Khin, Low, Ang and Yeow.
dc.publisherFrontiers Media S.A.
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.sourceScopus OA2021
dc.subjectgrasping
dc.subjectmachine learning
dc.subjectone shot learning
dc.subjectpneumatic actuators
dc.subjectsoft end effector
dc.typeArticle
dc.contributor.departmentDEPT OF BIOMEDICAL ENGINEERING
dc.contributor.departmentDEPT OF MECHANICAL ENGINEERING
dc.description.doi10.3389/frobt.2021.619390
dc.description.sourcetitleFrontiers in Robotics and AI
dc.description.volume8
dc.description.page619390
Appears in Collections:Staff Publications
Elements

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
10_3389_frobt_2021_619390.pdf2.82 MBAdobe PDF

OPEN

NoneView/Download

SCOPUSTM   
Citations

5
checked on Jan 30, 2023

Page view(s)

17
checked on Feb 2, 2023

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons