Publication
Speeding up the learning of robot kinematics
Journal Article (2005)
Journal
IEEE Transactions on Neural Networks
Pages
1504-1512
Volume
16
Number
6
Doc link
http://dx.doi.org/10.1109/TNN.2005.852970
File
Abstract
The main drawback of using neural networks or other example-based learning procedures 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. Off-line and on-line training schemes to learn these component functions are also proposed. Experimental results obtained by using Nearest Neighbours and PSOMs, with and without the decomposition, show that the time savings granted by the proposed scheme grow polynomially with the precision required.
Categories
robots.
Author keywords
learning inverse kinematics, PSOMs, training samples, function approximation, robot kinematics
Scientific reference
V. Ruiz de Angulo and C. Torras. Speeding up the learning of robot kinematics. IEEE Transactions on Neural Networks, 16(6): 1504-1512, 2005.
Follow us!