Title :
Humanoid Robot´s Autonomous Acquisition of Proto-Symbols through Motion Segmentation
Author :
Takano, Wataru ; Nakamura, Yoshihiko
Author_Institution :
Dept. of Mechano-Informatics, Tokyo Univ.
Abstract :
Mimesis is the theory that human intelligence originated in the interactive communication of motion recognition and generation through imitation. A mimesis model has been proposed using hidden Markov models (HMMs), which represent proto symbols. In our previous system, the user had to manually divided a sequence of motion into segments in order to embed each segment as an HMM. Automatic segmentation is essential for a system to autonomously learn and develop through imitation. In this paper, we propose an automatic motion segmentation method utilizing correlation among movements for a short time period. In addition, we show that it is possible to acquire proto symbols by providing the automatically segmented motion patterns with the mimesis system
Keywords :
biomimetics; hidden Markov models; humanoid robots; image motion analysis; image segmentation; knowledge acquisition; learning (artificial intelligence); robot vision; autonomous protosymbol acquisition; hidden Markov models; humanoid robot; imitation learning; mimesis system; motion patterns; motion recognition; motion segmentation; motion sequence; movement correlation; Computer vision; Data mining; Hidden Markov models; Humanoid robots; Humans; Learning; Mirrors; Motion control; Motion segmentation; Neurons; Hidden Markov Model; Imitation Learning; Mimesis; Segmentation;
Conference_Titel :
Humanoid Robots, 2006 6th IEEE-RAS International Conference on
Conference_Location :
Genova
Print_ISBN :
1-4244-0200-X
Electronic_ISBN :
1-4244-0200-X
DOI :
10.1109/ICHR.2006.321307
