Hebbian Multilayer Network in a Wheelchair Robot

. Motivation to study Hebbian learning arises from its neurophysiological plausibility and its suitability for hardware implementation. Up to now, artificial Hebbian learning, embedded in a real system that performs adaptive motor control, has been restricted to one-layer networks. To overcome this limitation, a novel approach to adaptive preprocessing based on Hebbian learning is presented. It is shown how this network is integrated in an adaptive motor control system inspired by classical and operant conditioning models. Experimental results with a real mobile robot are described. 1 Motivation One especially attractive learning rule for hardware implementation is Hebbian learning due to its simplicity and locality. Moreover, Hebbian learning is the most likely physiological basis for the learning ability of natural beings. Hence, neuroethological models of classical and operant conditioning that employ Hebbian learning can be adapted for technical applications [1]. A missing feature..