Acquisition of manipulative grounded symbols for integration of symbolic processing and stimulus-reaction type parallel processing
Abstract:The architecture constructed with two types of processing, logical symbol processing and stimulus-reaction type parallel processing, seems promising for intelligent systems. Since symbol processing is constructed by a top-down approach and stimulus-reaction type processing is built up by a bottom-up approach, a discrepancy, which is called the 'symbol grounding problem', takes place. This paper presents a framework for integration of symbol processing and stimulus-reaction type processing from the viewpoint of solving the symbol grounding problem. In this framework designers or users use the conventional heuristic symbols and the systems use the self-organized symbols based on the characteristics/environment of the systems themselves. Translation from one to another produces the fusion of those two symbols. The self-organized symbols are grounded and manipulative. Navigation of an autonomous robot is simulated. Acquisition of manipulative grounded symbols with the proposed framework is demonstrated. Since the constructed robot is equipped only with a stimulus-reaction type controller, it has a robustness against noise and temporary geometrical changes.
Document Type: Research Article
Affiliations: Department of Information Electronics Engineering, Graduate School of Engineering, Nagoya University, Furo-cho, Chikusa-ku, Nagoya 464-8603, Japan
Publication date: January 1, 1997