A self-organising multiple model architecture for motor imitation

Learning by imitation allows humans to easily transfer motor knowledge between individuals. Our research is aimed towards equipping robots with imitative capabilities, so humans can simply show a robot what to do. This will greatly simplify how humans program robots. To achieve imitative behaviour, we have implemented a self-organising connectionist modular architecture on a simulated robot. Motion tracking was used to gather data of human dance movements. When imitating the dance movements, the architecture self-organises the decomposition of movements into submovements, which are controlled by different modules. The modules both collaborate and compete for control during the movement. The trajectory recorded during motion tracking was repeated, revealing recurrent neural activation patterns of the inverse models (i.e., controllers), indicating that the modules specialise on specific parts of the trajectory.

[1]  J. Piaget.  Play, dreams and imitation in childhood , 1951 .

[2]  E. Vaadia,et al.  Neural interactions between motor cortical hemispheres during bimanual and unimanual arm movements , 2001, The European journal of neuroscience.

[3]  Daniel M. Wolpert,et al.  Internal models underlying grasp can be additively combined , 2004, Experimental Brain Research.

[4]  David Zipser,et al.  Simultaneous control of hand displacements and rotations in orientation-matching experiments. , 2004, Journal of applied physiology.

[5]  A. Meltzoff,et al.  Explaining Facial Imitation: A Theoretical Model. , 1997, Early development & parenting.

[6]  David Zipser,et al.  Neural network models of bilateral coordination , 1999, Biological Cybernetics.

[7]  Emilio Bizzi,et al.  Shared and specific muscle synergies in natural motor behaviors. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[8]  Axel Tidemann,et al.  Self-organizing Multiple Models for Imitation: Teaching a Robot to Dance the YMCA , 2007, IEA/AIE.

[9]  R. Ivry,et al.  Moving to Directly Cued Locations Abolishes Spatial Interference During Bimanual Actions , 2001, Psychological science.

[10]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[11]  M. Arbib.  The mirror system, imitation, and the evolution of language , 2002 .

[12]  Yasuo Kuniyoshi,et al.  From Humanoid Embodiment to Theory of Mind , 2003, Embodied Artificial Intelligence.

[13]  Norman I. Badler,et al.  Real-Time Inverse Kinematics of the Human Arm , 1996, Presence: Teleoperators & Virtual Environments.

[14]  A. Goldman,et al.  Mirror neurons and the simulation theory of mind-reading , 1998, Trends in Cognitive Sciences.

[15]  Gillian M. Hayes,et al.  Imitation as a dual-route process featuring prediction and learning components: A biologically plaus , 2002 .

[16]  S. Cardoso de Oliveira.  The neuronal basis of bimanual coordination: recent neurophysiological evidence and functional models. , 2002, Acta psychologica.

[17]  D. Wolpert,et al.  Internal models in the cerebellum , 1998, Trends in Cognitive Sciences.

[18]  G. Rizzolatti,et al.  Premotor cortex and the recognition of motor actions. , 1996, Brain research. Cognitive brain research.

[19]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[20]  Rolf Pfeifer,et al.  Understanding intelligence , 2020, Inequality by Design.

[21]  K. Dautenhahn,et al.  The correspondence problem , 2002 .

[22]  Stefan Schaal,et al.  Is imitation learning the route to humanoid robots? , 1999, Trends in Cognitive Sciences.

[23]  K. Doya,et al.  A unifying computational framework for motor control and social interaction. , 2003, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[24]  Robert M. French,et al.  Self-refreshing memory in artificial neural networks: learning temporal sequences without catastrophic forgetting , 2004, Connect. Sci..

[25]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[26]  Mitsuo Kawato,et al.  MOSAIC Model for Sensorimotor Learning and Control , 2001, Neural Computation.

[27]  Mitsuo Kawato,et al.  Feedback-Error-Learning Neural Network for Supervised Motor Learning , 1990 .

[28]  Yiannis Demiris,et al.  Hierarchical attentive multiple models for execution and recognition of actions , 2006, Robotics Auton. Syst..