Self-organisation of grounded symbols for fusions of symbolic processing and parallel distributed processing

The architecture constructed with two types of processing, symbolic processing and parallel distributed processing, seems promising for intelligent systems. However, there is the "symbol grounding problem" which involves the discrepancy between the system and the symbols given by top-down approach. To solve this problem, this paper presents a framework in which the system self-organizes grounded symbols and uses them for symbolic processing. A navigation task of autonomous robot is employed in this paper. The state space for the robot is self-organized by the distributions of the input-output relationships through the interactions between the robot and the environment. Using the self-organized symbols, the robot can navigate by switching some neural controllers autonomously. Some simulations show the effectiveness of the proposed method.