International Conference on Artificial Neural Networks (ICANN), 2002, Madrid (España) ; 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. ; This work was supported by the project 'Computación mediante restricciones en robótica y gestión de recursos' (070-725). ; Peer Reviewed
Learning inverse kinematics via cross-point function decomposition
2002-01-01
Conference paper
Electronic Resource
English
DDC: | 629 |
Learning inverse kinematics: Reduced sampling through decomposition into virtual robots
BASE | 2008
|Springer Verlag | 2022
|Springer Verlag | 2021
|An Inverse Kinematics Solution for Flexible Manipulators Using Learning Algorithm
British Library Online Contents | 1997
|