Embodied Symbol Emergence Based on Mimesis Theory
Top Cited Papers
- 1 April 2004
- journal article
- other
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 23 (4-5) , 363-377
- https://doi.org/10.1177/0278364904042199
Abstract
“Mimesis” theory focused in the cognitive science field and “mirror neurons” found in the biology field show that the behavior generation process is not independent of the behavior cognition process. The generation and cognition processes have a close relationship with each other. During the behavioral imitation period, a human being does not practice simple joint coordinate transformation, but will acknowledge the parents’ behavior. It understands the behavior after abstraction as symbols, and will generate its self-behavior. Focusing on these facts, we propose a new method which carries out the behavior cognition and behavior generation processes at the same time. We also propose a mathematical model based on hidden Markov models in order to integrate four abilities: (1) symbol emergence; (2) behavior recognition; (3) self-behavior generation; (4) acquiring the motion primitives. Finally, the feasibility of this method is shown through several experiments on a humanoid robot.Keywords
This publication has 17 references indexed in Scilit:
- Inter-module credit assignment in modular reinforcement learningNeural Networks, 2003
- Appearance based behavior recognition by event driven selective attentionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Speech parameter generation from HMM using dynamic featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- On the dynamics of robot exploration learningCognitive Systems Research, 2002
- Getting humanoids to move and imitateIEEE Intelligent Systems and their Applications, 2000
- Is imitation learning the route to humanoid robots?Published by Elsevier ,1999
- Mirror neurons and the simulation theory of mind-readingTrends in Cognitive Sciences, 1998
- A tennis serve and upswing learning robot based on bi-directional theoryNeural Networks, 1998
- Memory and Learning of Sequential Patterns by Nonmonotone Neural NetworksNeural Networks, 1996
- Learning by watching: extracting reusable task knowledge from visual observation of human performanceIEEE Transactions on Robotics and Automation, 1994