Change search
ReferencesLink to record
Permanent link

Direct link
Pruning of RBF Networks in Robot Manipulator Learning Control
Norwegian University of Science and Technology, Faculty of Information Technology, Mathematics and Electrical Engineering, Department of Engineering Cybernetics.
2012 (English)MasteroppgaveStudent thesis
Abstract [en]

Radial Basis Function Neural Networks are well suited for learning the system dynamics of a robot manipulator and implementation of these networks in the control scheme for a manipulator is a good way to deal with the system uncertainties and modeling errors which often occur. The problem with RBF networks however is to nd a network with suitable size, not too computational demanding and able to give accurate approximations. In general two methods for creating an appropriate RBF network has been developed, 1) Growing and 2) Pruning. In this report two dierent pruning methods which are suitable for use in a learning controller for robot manipulators are proposed, Weight Magnitude Prun- ing and Neuron Output Pruning. Weight Magnitude Pruning is based on a pruning scheme in [8] while Neuron Output Pruning is based on [2]. Both pruning methods are simple, have low computational cost and are able to remove several units in one pruning period. The thresholds used to nd which neurons to remove are specied as a percent and hence less problem dependent to nd. Simulations with the two proposed pruning methods in a learning inverse kinematic controller for tracking a trajectory by using the three rst joints of the ABB IRB140 manipulator are conducted. The result was that implementing pruned RBF networks in the controller made it more robust towards system uncertainties due to increased generalization ability. These pruned networks were found to give better tracking in the case of unmodeled dynamics compared to the incorrect system model, not pruning the RBFNNs and a type of growing network called RANEKFs. Computational costs were also reduced when the pruning schemes were implemented. NTNU has a manipulator of the type ABB IRB140 and the learning inverse kinematic controller with pruning of RBF networks should be implemented and tested on this in real-life simulations.

Place, publisher, year, edition, pages
Institutt for teknisk kybernetikk , 2012. , 152 p.
Keyword [no]
ntnudaim:6788, MTTK teknisk kybernetikk
URN: urn:nbn:no:ntnu:diva-18591Local ID: ntnudaim:6788OAI: diva2:566105
Available from: 2012-11-08 Created: 2012-11-08

Open Access in DiVA

fulltext(2114 kB)367 downloads
File information
File name FULLTEXT01.pdfFile size 2114 kBChecksum SHA-512
Type fulltextMimetype application/pdf
cover(184 kB)24 downloads
File information
File name COVER01.pdfFile size 184 kBChecksum SHA-512
Type coverMimetype application/pdf
attachment(2017 kB)59 downloads
File information
File name ATTACHMENT01.zipFile size 2017 kBChecksum SHA-512
Type attachmentMimetype application/zip

By organisation
Department of Engineering Cybernetics

Search outside of DiVA

GoogleGoogle Scholar
Total: 367 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 72 hits
ReferencesLink to record
Permanent link

Direct link