Structure variable multi-sensoric supervisory control of human interactive robots

In this paper, a new structure variable NF based supervisory control concept for advanced multi-sensory robots (humanoid robots) is presented. It relies on a reliable identification of the actual process phases or fault cases. For each identified process phase and fault scenario by means of a heuristic Fuzzy Logic mode selector a dynamic reconfiguration of optimal situation-specific sub-controllers will be activated. About first results with its implementation within the framework of the on-going German Humanoid Robot Project will be reported.