Position-Based ANN Impedance Control for A Three-Fingered Robot Hand

A feedforward ANN was previously developed for recognition of two objects i.e. a spongy ball and a plastic bottle but was verified through simulation only. In this work, the feasibility of the ANN model is tested by applying it to the robot’s impedance control which takes the exerted force at the fi...

Full description

Bibliographic Details
Published in:Journal of Mechanical Engineering
Main Author: Shauri R.L.A.; Sabri M.A.A.M.; Roslan A.B.
Format: Article
Language:English
Published: UiTM Press 2024
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85202698508&doi=10.24191%2fjmeche.v21i3.27357&partnerID=40&md5=692eddc7dcfd0002f6c689e8d0d6f770
id 2-s2.0-85202698508
spelling 2-s2.0-85202698508
Shauri R.L.A.; Sabri M.A.A.M.; Roslan A.B.
Position-Based ANN Impedance Control for A Three-Fingered Robot Hand
2024
Journal of Mechanical Engineering
21
3
10.24191/jmeche.v21i3.27357
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85202698508&doi=10.24191%2fjmeche.v21i3.27357&partnerID=40&md5=692eddc7dcfd0002f6c689e8d0d6f770
A feedforward ANN was previously developed for recognition of two objects i.e. a spongy ball and a plastic bottle but was verified through simulation only. In this work, the feasibility of the ANN model is tested by applying it to the robot’s impedance control which takes the exerted force at the finger as input while resulting in an output for the selection rule of the impedance stiffness parameter, named Kd. From the results, the different object textures can be distinguished by the ANN where the absolute peak values of measured rate force during contact with the ball reached 0.15 N and a slightly higher value of 0.32 N for the bottle. Kd values were found to switch between 1000 and 250 based on the ANN outputs for the ball and bottle, respectively, thus affecting the dynamics of the fingertip through modified position reference of the fingertip. However, it is also observed that the object was incorrectly classified in some moments when the exerted force was not sufficient due to the weak grasp of the object. This shows that the nonlinear factor from the hardware defects needs to be considered when refining the Kd selection rule in future studies. © 2024 College of Engineering. All rights reserved.
UiTM Press
18235514
English
Article

author Shauri R.L.A.; Sabri M.A.A.M.; Roslan A.B.
spellingShingle Shauri R.L.A.; Sabri M.A.A.M.; Roslan A.B.
Position-Based ANN Impedance Control for A Three-Fingered Robot Hand
author_facet Shauri R.L.A.; Sabri M.A.A.M.; Roslan A.B.
author_sort Shauri R.L.A.; Sabri M.A.A.M.; Roslan A.B.
title Position-Based ANN Impedance Control for A Three-Fingered Robot Hand
title_short Position-Based ANN Impedance Control for A Three-Fingered Robot Hand
title_full Position-Based ANN Impedance Control for A Three-Fingered Robot Hand
title_fullStr Position-Based ANN Impedance Control for A Three-Fingered Robot Hand
title_full_unstemmed Position-Based ANN Impedance Control for A Three-Fingered Robot Hand
title_sort Position-Based ANN Impedance Control for A Three-Fingered Robot Hand
publishDate 2024
container_title Journal of Mechanical Engineering
container_volume 21
container_issue 3
doi_str_mv 10.24191/jmeche.v21i3.27357
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85202698508&doi=10.24191%2fjmeche.v21i3.27357&partnerID=40&md5=692eddc7dcfd0002f6c689e8d0d6f770
description A feedforward ANN was previously developed for recognition of two objects i.e. a spongy ball and a plastic bottle but was verified through simulation only. In this work, the feasibility of the ANN model is tested by applying it to the robot’s impedance control which takes the exerted force at the finger as input while resulting in an output for the selection rule of the impedance stiffness parameter, named Kd. From the results, the different object textures can be distinguished by the ANN where the absolute peak values of measured rate force during contact with the ball reached 0.15 N and a slightly higher value of 0.32 N for the bottle. Kd values were found to switch between 1000 and 250 based on the ANN outputs for the ball and bottle, respectively, thus affecting the dynamics of the fingertip through modified position reference of the fingertip. However, it is also observed that the object was incorrectly classified in some moments when the exerted force was not sufficient due to the weak grasp of the object. This shows that the nonlinear factor from the hardware defects needs to be considered when refining the Kd selection rule in future studies. © 2024 College of Engineering. All rights reserved.
publisher UiTM Press
issn 18235514
language English
format Article
accesstype
record_format scopus
collection Scopus
_version_ 1812871796177764352