Behavior categorization using Correlation Based Adaptive Resonance Theory

This paper presents a new method of categorizing robot behavior, which is based on a variation of correlation based adaptive resonance theory (CobART) learning. CobART is a type of ART 2 network and its main contribution is the usage of correlation analysis methods for category matching. This study uses derivation based correspondence and Euclidian distance as correlation analysis methods for behavior categorization. Tests show that the proposed method generates better results than ART 2 categorization even when a priori SOM (self-organizing map) categorization is combined with ART 2 categorization.