Title :
A Geometric Radial Basis Function Network for Robot Perception and Action
Author :
Vázquez-Santacruz, E. ; Bayro-Corrochano, E.
Author_Institution :
CINVESTAV Unidad Guadalajara, Zapopan, Mexico
Abstract :
This paper presents a new hyper complex valued Radial Basis Network. This network constitutes a generalization of the standard real valued RBF. This geometric RBF can be used in real time to estimate changes in linear transformations between sets of geometric entities. Experiments using stereo image sequences validate this proposal. We propose a Geometric RBF Network (GRBF-N) designed in the geometric algebra framework. We present an application to estimate linear transformations between sets of geometric entities. Our experiments validate our proposal.
Keywords :
control engineering computing; image sequences; radial basis function networks; robot vision; stereo image processing; geometric entities; geometric radial basis function network; hypercomplex valued radial basis network; robot action; robot perception; standard real valued RBF; stereo image sequences; Algebra; Argon; Artificial neural networks; Blades; Radial basis function networks; Rotors; Training; RBF; geometric algebra; geometric computing;
Conference_Titel :
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4244-7542-1
DOI :
10.1109/ICPR.2010.725
