Empirical Control System for Robots That Learn

Abstract

Autonomous behaviour of industrial robot is based on the ability of machine learning. Unlike natural systems which could learn on the basis of experience, artificial systems are thought to be unable to do so for a long time. However, the concept of empirical control realizes the ability of machine learning on the basis of experience. This paper shows the algorithm of empirical control which presents the key for establishing developed empirical control system. The validity of established empirical control system pointed out that, after machine learning by using artificial neural networks, specially designed robot named "Don Kihot" approaches directly towards the work-piece. Developed software subsystems as well as experimental results of machine learning are presented in this paper.