Publication
Learning inverse kinematics via cross-point function decomposition
Conference Article
Conference
International Conference on Artificial Neural Networks (ICANN)
Edition
2002
Pages
856-861
Doc link
http://dx.doi.org/10.1007/3-540-46084-5_139
File
Abstract
The main drawback of using neural networks to approximate the inverse kinematics (IK) of robot arms is the high number of training samples (i.e., robot movements) required to attain an acceptable precision. We propose here a trick, valid for most industrial robots, that greatly reduces the number of movements needed to learn or relearn the IK to a given accuracy. This trick consists in expressing the IK as a composition of learnable functions, each having half the dimensionality of the original mapping. A training scheme to learn these component functions is also proposed. Experimental results obtained by using PSOMs, with and without the decomposition, show that the time savings granted by the proposed scheme grow polynomically with the precision required.
Categories
robots.
Scientific reference
V. Ruiz de Angulo and C. Torras. Learning inverse kinematics via cross-point function decomposition, 2002 International Conference on Artificial Neural Networks, 2002, Madrid, Spain, in Artificial Neural Networks, Vol 2415 of Lecture Notes in Computer Science, pp. 856-861, 2002, Springer, Heidelberg, Alemanya.
Follow us!