Human-Robot Interaction System with Quantum-Inspired Bidirectional Associative Memory

This paper discussed the Interaction System with Robot Partner using Quantum-Inspired Bi-directional Associative Memory (QBAM). We have been developed QBAM which has the superior Memory Capacity and Recall Reliability compare with conventional models. Due to these advantages, the proposed system can be stored much information and its relationships. Using QBAM, we construct the interaction system that can be associated with gesture, object and voice information. In proposed system, Steady-state genetic algorithms are applied in order to detect objects via image processing. Spiking neural networks are applied to memorize the spatio-temporal patterns of gesture. For voice recognition, we use Julius that is open source large vocabulary continuous speech recognition engine. The results of experiment shows that proposed system is able to contribute for the facilitation of communication with Robot Partner.