Intemational Scxricty for Advanced Research ISSN 1828 - 6984 INTERNATIONAL JOURNAL OF FAaORY AUTOMATION , ROBOTICS AND SOFT COMPUTING

Integration of cognitive aspects into an autonomous perceptual robot is described. The work is based on a virtual autonomous perceptual robot presented earlier. In this work the extension ofthe earlier work with some cognitive features is investigated making use of intelligent technologies and evolutionary multi-objective optimization technology. In particular, intelligent technologies are from the domain of computational intelligence which is an emerging concept employed by the intelligent computing community. The cognitive functions are formed by the integration of a neural tree model for knowledge representation and evolutionary multi-objective optimization for a decision-making outcome among several equaUy valid options. Cognition is defined as the final decision-making based on not only the optimization outcomes but also some higher-order aspects which do not play role on the pure optimization process. By doing so, the decisions are not merely subject to rationales of the computations but they are the resolutions with the presence of higher-order considerations integrated into computations. The work describes a novel tree structure serving for this purpose and a novel evolutionary multi-objective optimization strategy for effective Pareto-front formation serving for the goal. Cognition is exemplified by means of a cognitive design example using human-like visual perceptions provided by a virtual perceptual robot and integration of the cognitive properties to this robot is discussed in the framework of autonomous cognitive robotics.