Hierarchies of Coupled Inverse and Forward Models for Abstraction in Robot Action Planning, Recognition and Imitation

Coupling internal inverse and forward models gives rise to on-line simulation processes that may be used as a common computational substrate for action execution, planning, recognition, imitation and learning. In this paper, multiple coupled internal inverse and forward models are arranged in a hierarchical fashion, with each level of the hierarchy interacting with other levels through top-down and bottom-up processes. Through experiments involving imitation of a human demonstrator performing object manipulation tasks, this architecture is shown to equip a robot with a multi-level motor abstraction capability. This is then used to solve the correspondence problem in action recognition. The architecture is inspired by biological evidence.

[1]  Gary Bradski,et al.  Computer Vision Face Tracking For Use in a Perceptual User Interface , 1998 .

[2]  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.

[3]  D M Wolpert,et al.  Multiple paired forward and inverse models for motor control , 1998, Neural Networks.

[4]  G. Rizzolatti,et al.  Motor and cognitive functions of the ventral premotor cortex , 2002, Current Opinion in Neurobiology.

[5]  Yiannis Demiris,et al.  Distributed, predictive perception of actions: a biologically inspired robotics architecture for imitation and learning , 2003, Connect. Sci..

[6]  Chrystopher L. Nehaniv,et al.  Imitation as a Dual-Route Process Featuring Predictive and Learning Components: A Biologically Plausible Computational Model , 2002 .

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

[8]  Mitsuo Kawato,et al.  A neural network model for arm trajectory formation using forward and inverse dynamics models , 1993, Neural Networks.

[9]  Luciano Fadiga,et al.  New insights on sensorimotor integration: From hand action to speech perception , 2003, Brain and Cognition.

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

[11]  Daniel M. Wolpert,et al.  Hierarchical MOSAIC for movement generation , 2003 .

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

[13]  Yiannis Demiris,et al.  Imitation of human demonstration using a biologically inspired modular optimal control scheme , 2004, 4th IEEE/RAS International Conference on Humanoid Robots, 2004..

[14]  John Demiris,et al.  Movement imitation mechanisms in robots and humans , 1999 .

[15]  Ivan Poupyrev,et al.  The MagicBook: a transitional AR interface , 2001, Comput. Graph..

[16]  Yiannis Demiris,et al.  Abstraction in Recognition to Solve the Correspondence Problem for Robot Imitation , 2004 .

[17]  A. Meltzoff,et al.  What imitation tells us about social cognition: a rapprochement between developmental psychology and cognitive neuroscience. , 2003, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[18]  R. B. Frost.  DIRECTED GRAPHS AND THEIR ADJACENCY MATRICES: MISCONCEPTIONS AND MORE EFFICIENT METHODS , 1992 .

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

[20]  Christopher G. Atkeson,et al.  A Framework for Learning from Observation Using Primitives , 2002, RoboCup.

[21]  Chrystopher L. Nehaniv,et al.  Imitation with ALICE: learning to imitate corresponding actions across dissimilar embodiments , 2002, IEEE Trans. Syst. Man Cybern. Part A.

[22]  Kumpati S. Narendra,et al.  Adaptive control using multiple models , 1997, IEEE Trans. Autom. Control..