A Hybrid Intelligent Active Force Controller for Articulated Robot Arms Using Dynamic Structure Neural Network

The key feature of this paper is the application of a robotic control concept - Active Force Control (AFC). In this type of control, the unknown friction effect of the robotic arm may be compensated by the AFC method. AFC involves the direct measurement of the acceleration and force quantities and t...

Full description

Bibliographic Details
Main Authors: Loo, Chu Kiong, Mandava, Rajeswari, Rao, M. V. C.
Format: Article
Published: 2004
Subjects:
Online Access:http://shdl.mmu.edu.my/2470/
_version_ 1848790063052226560
author Loo, Chu Kiong
Mandava, Rajeswari
Rao, M. V. C.
author_facet Loo, Chu Kiong
Mandava, Rajeswari
Rao, M. V. C.
author_sort Loo, Chu Kiong
building MMU Institutional Repository
collection Online Access
description The key feature of this paper is the application of a robotic control concept - Active Force Control (AFC). In this type of control, the unknown friction effect of the robotic arm may be compensated by the AFC method. AFC involves the direct measurement of the acceleration and force quantities and therefore, the process of estimating the system 'disturbance' due to friction becomes instantaneous and purely algebraic. However, the AFC strategy is very practical provided a good estimation of the inertia matrix of articulated robot arm is acquired. A dynamic structure neural network - Growing Multi-experts Network (GMN) is developed to estimate the robot inertia matrix. The growing and pruning mechanism of GMN ensures the optimum size of the network that results in an excellent generalization capability of the network. Active Force Control ( AFC) in conjunction with GMN successfully reduces the velocity and position tracking errors in spite of robot joint friction. The embedded GMN is capable of coupling the inertia matrix estimation online that clearly enhances the performance of AFC controller. The robustness and effectiveness of the new hybrid neural network-based AFC scheme are demonstrated clearly with regard to two link articulated robot and a simulated two-degree of freedom Puma 560 robot.
first_indexed 2025-11-14T18:06:39Z
format Article
id mmu-2470
institution Multimedia University
institution_category Local University
last_indexed 2025-11-14T18:06:39Z
publishDate 2004
recordtype eprints
repository_type Digital Repository
spelling mmu-24702011-08-22T01:49:56Z http://shdl.mmu.edu.my/2470/ A Hybrid Intelligent Active Force Controller for Articulated Robot Arms Using Dynamic Structure Neural Network Loo, Chu Kiong Mandava, Rajeswari Rao, M. V. C. QA75.5-76.95 Electronic computers. Computer science The key feature of this paper is the application of a robotic control concept - Active Force Control (AFC). In this type of control, the unknown friction effect of the robotic arm may be compensated by the AFC method. AFC involves the direct measurement of the acceleration and force quantities and therefore, the process of estimating the system 'disturbance' due to friction becomes instantaneous and purely algebraic. However, the AFC strategy is very practical provided a good estimation of the inertia matrix of articulated robot arm is acquired. A dynamic structure neural network - Growing Multi-experts Network (GMN) is developed to estimate the robot inertia matrix. The growing and pruning mechanism of GMN ensures the optimum size of the network that results in an excellent generalization capability of the network. Active Force Control ( AFC) in conjunction with GMN successfully reduces the velocity and position tracking errors in spite of robot joint friction. The embedded GMN is capable of coupling the inertia matrix estimation online that clearly enhances the performance of AFC controller. The robustness and effectiveness of the new hybrid neural network-based AFC scheme are demonstrated clearly with regard to two link articulated robot and a simulated two-degree of freedom Puma 560 robot. 2004-06 Article NonPeerReviewed Loo, Chu Kiong and Mandava, Rajeswari and Rao, M. V. C. (2004) A Hybrid Intelligent Active Force Controller for Articulated Robot Arms Using Dynamic Structure Neural Network. Journal of Intelligent and Robotic Systems, 40 (2). pp. 113-145. ISSN 0921-0296 http://dx.doi.org/10.1023/B:JINT.0000039014.41797.dc doi:10.1023/B:JINT.0000039014.41797.dc doi:10.1023/B:JINT.0000039014.41797.dc
spellingShingle QA75.5-76.95 Electronic computers. Computer science
Loo, Chu Kiong
Mandava, Rajeswari
Rao, M. V. C.
A Hybrid Intelligent Active Force Controller for Articulated Robot Arms Using Dynamic Structure Neural Network
title A Hybrid Intelligent Active Force Controller for Articulated Robot Arms Using Dynamic Structure Neural Network
title_full A Hybrid Intelligent Active Force Controller for Articulated Robot Arms Using Dynamic Structure Neural Network
title_fullStr A Hybrid Intelligent Active Force Controller for Articulated Robot Arms Using Dynamic Structure Neural Network
title_full_unstemmed A Hybrid Intelligent Active Force Controller for Articulated Robot Arms Using Dynamic Structure Neural Network
title_short A Hybrid Intelligent Active Force Controller for Articulated Robot Arms Using Dynamic Structure Neural Network
title_sort hybrid intelligent active force controller for articulated robot arms using dynamic structure neural network
topic QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/2470/
http://shdl.mmu.edu.my/2470/
http://shdl.mmu.edu.my/2470/