Computational Intelligence for Cyclic Gestures Recognition of a Partner Robot

This paper proposes a method for cyclic gestures recognition of a partner robot based on computational intelligence. The mobile robot used as a partner robot must make decisions suitable to the human intention in the facing environment. Therefore, it is necessary to recognize the gesture used as a tool for human communication. The proposed method is composed of a fuzzy spiking neural network, a self-organizing map, and a steady-state genetic algorithm. Experimental results show the effectiveness of the proposed method.

[1]  Toshio Fukuda,et al.  An intelligent robotic system based on a fuzzy approach , 1999, Proc. IEEE.

[2]  Naoyuki Kubota,et al.  10212 Recognition of Cyclic Gestures for A Partner Robot Based on Interactive Learning , 2005 .

[3]  Masafumi Hagiwara,et al.  A pulse neural network learning algorithm for POMDP environment , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[4]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[5]  Fumio Harashima.  Interaction and Intelligence , 2002, Proceedings. 11th IEEE International Workshop on Robot and Human Interactive Communication.

[6]  Gilbert Syswerda,et al.  A Study of Reproduction in Generational and Steady State Genetic Algorithms , 1990, FOGA.

[7]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.