Abstract

• The mirror neuron is a domain in the brain which activates when observing the actions of others, and also activates when he/she tries to perform the same action. Since this domain is like a mirror, which projects the corresponding relation between the actions of others and one's own body, it is appropriately named a 'mirror neuron'. Since this domain is near the cerebral language field, a hypothesis of being deeply concerned with brain functions, such as recognition, generation, abstraction, verbalization of motions, has been proposed. We propose a mathematical technique called a mirror neuron model that calculates the action of this part. The model has been engineered into humanoid robots. In this model, human actions are represented as a series of time series patterns of motions and sensors, such as vision, hearing, tactile sense, and force. Then, abstracting the set of action patterns performed by humans and the name of an action by a stochastic model called the Hidden Markov Model (HMM), and measuring　the similarity between the actions with the hyper-parameters of the HMM. Using the similarity, a certain topological space structure could be built. With the help of the space structure, we can attain the communication/behavior imitation/motion transfer using the state point on the topological space, i.e., a primitive symbol. One of the advantages of the model is that it can recognize strange actions and the generation of a novel action using the geometric spatial relationship of the state points. This enabled the humanoid robots to imitate the users' physical behaviors even if the behavior was strange to the humanoid, by using a combination of known element actions.

Publication

• Tetsunari Inamura｡､Yoshihiko Nakamura and Iwaki Toshima. "Embodied Symbol Emergence based on Mimesis Theory"｡､International Journal of Robotics Research｡､Vol.23, No.4, pp.363--377, 2004. [PDF]
• Tetsunari Inamura, Hiroaki Tanie and Yoshihiko Nakamura "From Stochastic Motion Generation and Recognition to Geometric Symbol Development and Manipulation". In the Proc. of IEEE-RAS Int'l Conf. on Humanoid Robots (Humanoids 2003), 2003. [PDF]
• Tetsunari Inamura, Hiroaki Tanie and Yoshihiko Nakamura "Keyframe Extraction and Decompression for Time Series Data based on Continuous Hidden Markov Models". In the Proc. of Int'l Conf. on Intelligent Robots and Systems (IROS 2003), pp.1487--1492, 2003. [PDF]
• Yoshihiko Nakamura, Tetsunari Inamura and Hiroaki Tanie: "A Statistic Model of Embodied Symbol Emergence," In the Proc. of the Int'l Symbosium on Robotics Research, 2003. [PDF]
• Tetsunari Inamura, Hiroaki Tanie, Iwaki Toshima and Yoshihiko, Nakamura. "An Approach from Motion Generation/Recognition to Intelligence based on Mimesis Principle". In the Proc. of the 2nd Int'l Symposium on Adaptive Motion of Animals and Machines (AMAM2003), pp. SaA-II-1, 2003. [PDF]
• Tetsunari Inamura, Yoshihiko Nakamura and Moriaki Simozaki. "Associative Computational Model of Mirror Neurons that connects Missing Link between Behaviors and Symbols". In the Proc. of Int'l Conf. on Intelligent Robots and Systems (IROS 2002), pp.1032--1037. 2002. [PDF]
• Tetsunari Inamura, Iwaki Toshima and Yoshihiko, Nakamura. "Acquiring Motion Elements for Bidirectional Computation of Motion Recognition and Generation". In the Proc. of Int'l Symposium. on Experimental Robotics (ISER2002), pp. 357--366. 2002 [PDF]
• Tetsunari Inamura, Iwaki Toshima and Yoshihiko, Nakamura. "Acquisition and Embodiment of Motion Elements in Closed Mimesis Loop". In the Proc. of Int'l Conf. on Robotics and Automation (ICRA2002), pp.1539-1544, 2002. [PDF]
• Tetsunari Inamura, Yoshihiko Nakamura, Iwaki Toshima, and Hideaki Ezaki. "Mimesis Embodiment and Proto-symbol Acquisition for Humanoids". In the Proc. of Int'l Conf. on Advanced Intelligent Mechatronics (AIM 2001), pp.159--164, 2001. [PDF]
• Tetsunari Inamura, Yoshihiko Nakamura, Hideaki Ezaki, and Iwaki Toshima. "Imitation and Primitive Symbol Acquisition of Humanoids by the Integrated Mimesis Loop". In the Proc. of Int'l Conf. on Robotics and Automation (ICRA 2001), pp.4208--4213, 2001. [PDF]