Sensory-motor control scheme based on Kohonen Maps and AVITE model

Abstract

In this paper a control scheme is proposed for anticipatory and discrete event sensory motor driven. The control system elaborates a sensory-motor program based on its internal data and a high level objective. The global system implements several biological models in each one of its subsystems. One of the novelties of this work is the structure of the sensory-motor algorithms which are based on cell distributions of the sensorial spaces. Indeed, the correspondence between cells and the sensorial spaces is distributed by Kohonen maps. This control scheme has been tested on a robotic platform constituted by an industrial robot and a stereohead. More relevant results are presented and analyzed in this paper.