Artificial Neural Networks for Robotics Coordinate Transformation

Stephen Aylor, University of Missouri - Rolla, Rolla, Missouri
Luis Rabelo, Ohio University, Athens, Ohio
Sema E. Alptekin, University of Missouri - Rolla, Rolla, Missouri

Article comments

Copyright © 1992 Elsevier Science Ltd. DOI: http://dx.doi.org/10.1016/0360-8352(92)90023-D.

NOTE: At the time of publication, the author Sema Alptekin was not yet affiliated with Cal Poly.

Abstract

Artificial neural networks with such characteristics as learning, graceful degradation, and speed inherent to parallel distributed architectures might provide a flexible and cost solution to the real time control of robotics systems. In this investigation artificial neural networks are presented for the coordinate transformation mapping of a two-axis robot modeled with Fischertechnik physical modeling components. The results indicate that artificial neural systems could be utilized for practical situations and that extended research in these neural structures could provide adaptive architectures for dynamic robotics control.