Publication

Using PSOMs to learn inverse kinematics through virtual decomposition of the robot

Conference Article

Conference

International Workshop on Artificial Neural Networks (293)

Edition

8th

Pages

701-708

Doc link

http://dx.doi.org/10.1007/11494669_86

File

Download the digital copy of the doc pdf document

Abstract

We propose a technique to speed up the learning of the inverse kinematics of a robot manipulator by decomposing it into two or more virtual robot arms. Unlike previous decomposition approaches, this one does not place any requirement on the robot architecture and, thus, it is completely general. Parametrized Self-Organizing Maps (PSOM) are particularly adequate for this type of learning, and permit comparing results obtained directly and through the decomposition. Experimentation shows that time reductions of up to two orders of magnitude are easily attained.

Categories

robots.

Author keywords

inverse kinematics, learning, PSOMs

Scientific reference

V. Ruiz de Angulo and C. Torras. Using PSOMs to learn inverse kinematics through virtual decomposition of the robot, 8th International Workshop on Artificial Neural Networks, 2005, Barcelona, Espanya, in Computational Intelligence and Bioinspired Systems, Vol 3512 of Lecture Notes in Computer Science, pp. 701-708, 2005, Springer, Berlin, Alemanya.