TCB Publications - Abstract

Jörg A. Walter, Thomas Martinetz, and Klaus Schulten. Industrial robot learns visuo-motor coordination by means of "neural gas" network. In Teuvo Kohonen, Kai Mäkisara, Olli Simula, and Jari Kangas, editors, Artificial Neural Networks, pp. 357-364. Elsevier, Amsterdam, 1991.

WALT91 We implemented a neural network algorithm for visuomotor control of an industrial robot (Puma 562). The algorithm uses a new vector quantization technique, the "neural gas" network, together with an error correction scheme based on a Widrow-Hoff-type learning rule. Based on visual information provided by two cameras, the robot learns to position its end effector without an external teacher. Within only 3000 training steps, the "closed" robot-camera system is capable of reducing the positioning error of the robot's end effector to approximately 0.2 percent of the linear dimension of the work space. By employing immediate feedback the robot succeeds in compensating not only slow calibration erosion, but also sudden changes in its geometry. Some hardware aspects of the robot-camera system are also discussed.

Download Full Text

The manuscripts available on our site are provided for your personal use only and may not be retransmitted or redistributed without written permissions from the paper's publisher and author. You may not upload any of this site's material to any public server, on-line service, network, or bulletin board without prior written permission from the publisher and author. You may not make copies for any commercial purpose. Reproduction or storage of materials retrieved from this web site is subject to the U.S. Copyright Act of 1976, Title 17 U.S.C.

Download full text: PDF (975.2KB)