Computational Technology Resources - CCP

Paper IV.1

Neural-Network Control of Large Flexible Manipulator Systems, using the Cerebellar Model Arithmetic Computer

C.J. Macnab and G.M.T. D'Eleuterio

Institute for Aerospace Studies, University of Toronto, Downsview, Canada

doi:10.4203/ccp.34.4.1

C.J. Macnab, G.M.T. D'Eleuterio, "Neural-Network Control of Large Flexible Manipulator Systems, using the Cerebellar Model Arithmetic Computer", in B.H.V. Topping, (Editor), "Developments in Neural Networks and Evolutionary Computing for Civil and Structural Engineering", Civil-Comp Press, Edinburgh, UK, pp 79-85, 1995. doi:10.4203/ccp.34.4.1

Abstract

A neural-network control concept is introduced for structurally flexible robotic manipulators. The control architecture is based on Albus's Cerebellar Model Arithmetic Computer (CMAC) The scheme employs Jordan's supervised learning technique with a distal teacher. The resulting control architecture is the Forward-Inverse CMAC, or FICMAC for short. A forward-dynamics module of the robotic system is used to train an inverse-dynamics module that provides control torques to the system. The technique is suitable for on-line learning and moreover, as a numerical example illustrates, learning can be achieved in a relatively few trials.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £55 +P&P)

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Proceedings ISSN 1759-3433 CCP: 34 DEVELOPMENTS IN NEURAL NETWORKS AND EVOLUTIONARY COMPUTING FOR CIVIL AND STRUCTURAL ENGINEERING Edited by: B.H.V. Topping Paper IV.1 Neural-Network Control of Large Flexible Manipulator Systems, using the Cerebellar Model Arithmetic Computer C.J. Macnab and G.M.T. D'Eleuterio Institute for Aerospace Studies, University of Toronto, Downsview, Canada doi:10.4203/ccp.34.4.1 purchase the full-text of this paper Full Bibliographic Reference for this paper C.J. Macnab, G.M.T. D'Eleuterio, "Neural-Network Control of Large Flexible Manipulator Systems, using the Cerebellar Model Arithmetic Computer", in B.H.V. Topping, (Editor), "Developments in Neural Networks and Evolutionary Computing for Civil and Structural Engineering", Civil-Comp Press, Edinburgh, UK, pp 79-85, 1995. doi:10.4203/ccp.34.4.1 Abstract A neural-network control concept is introduced for structurally flexible robotic manipulators. The control architecture is based on Albus's Cerebellar Model Arithmetic Computer (CMAC) The scheme employs Jordan's supervised learning technique with a distal teacher. The resulting control architecture is the Forward-Inverse CMAC, or FICMAC for short. A forward-dynamics module of the robotic system is used to train an inverse-dynamics module that provides control torques to the system. The technique is suitable for on-line learning and moreover, as a numerical example illustrates, learning can be achieved in a relatively few trials. purchase the full-text of this paper (price £20) go to the previous paper go to the next paper return to the table of contents return to the book description purchase this book (price £55 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions