SELF-ORGANIZING LEARNING IN ROBOTICS Dimitrios

摘要

One of the most important features of biological motion control is the connection of motor action to sensory perception. Sensorimotor coordination adapts and develops by actions of sensory and motor experience. For tasks in which a-priori knowledge is limited, self-organising controllers are proposed. A novel technique is described, that allows a robot to autonomously determine its sensorimotor mapping. Artificial neural networks are used to learn the sensorimotor coordination, trained using self-organizing learning algorithms. The inverse kinematic mapping is learned by the use of a series of trial movements. The relation of the proposed algorithm to biological motion control is discussed.