Hierarchical Object Classification for Autonomous Mobile Robots

An adaptive neural 3D-object recognition architecture for mobile robot applications is presented. During training, a hierarchy of LVQ classifiers basedon feature vectors with increasingly higher dimensionality is generated. The hierarchy is extended exactly in those regions of the feature space, where objects cannot be distinguished using lowerdimensional feature vectors. During recall, this system can produce object classifications in an anytime fashion with increasingly more detailed and higher confident results. Experimental data obtained from application to two real-worldd ata sets are very encouraging. We foundman y of the confusion classes to represent meaningful concepts, with obvious implications for symbol grounding and integration of subsymbolic and symbolic representations.