Adaptive Classification in Autonomous Agents

One of the fundamental tasks facing autonomous robots is to reduce the many degrees of freedom of the input space by some sorts of classiication mechanism. The sensory stimulation caused by one and the same object, for instance, varies enormously depending on lighting conditions, distance from object, orientation and so on. EEorts to solve this problem, say in classical computer vision, have only had limited success. In this paper a new approach towards classiication in autonomous robots is proposed. It's cornerstone is the integration of the robots own actions into the classiication process. More speciically, correlations through time-linked independent samples of sensory stimuli and of kinesthetic signals produced by self-motion of the system form the basis of the category learning. Thus, it is suggested that classiication should not be seen as an isolated perceptual (subsystem m but rather as a sensory-motor coordination which comes about through a self-organizing process. These ideas are illustrated with a case study of an autonomous system that has to learn to distinguish between graspable and non-graspable objects.