COGNITION IN SYSTEMS

This paper proposes a four-level architecture for the cognitive apparatus of future autonomous systems, addresses the handling of nested time scales, tries a first step toward a technical approximation of consciousness as a linear abstract control channel within a massively parallel architecture, and describes a number of interplays between an intuitive subsymbolic and a symbolic level of information processing. Furthermore, concrete models, namely a task model, model of the environment, partner model, and eigenmodel of a system, are distinguished. Some comments on test beds are included, as are hints about the project AMOS at FAW that addresses some of the topics discussed within a platform-based realization, particularly the interplay between subsymbolic and symbolic forms of information processing.