Learning Compositional Hierarchies of a Sensorimotor System

We address the problem of learning static spatial representation of a robot motor system and the environment to solve a general forward/inverse kinematics problem. The latter proves complex for high degree-of-freedom systems. The proposed architecture relates to a recent research in cognitive science, which provides a solid evidence that perception and action share common neural architectures. We propose to model both a motor system and an environment with compositional hierarchies and develop an algorithm for learning them together with a mapping between the two. We show that such a representation enables efficient learning and inference of robot states. We present our experiments in a simulated environment and with a humanoid robot Nao.

[1]  Stefan Schaal,et al.  Dynamics systems vs. optimal control--a unifying view. , 2007, Progress in brain research.

[2]  J. Decety,et al.  Motor cognition: a new paradigm to study self–other interactions , 2004, Current Opinion in Neurobiology.

[3]  Ludovic Righetti,et al.  Toward simple control for complex, autonomous robotic applications: combining discrete and rhythmic motor primitives , 2011, Auton. Robots.

[4]  W. Prinz.  Perception and Action Planning , 1997 .

[5]  Josef P. Rauschecker,et al.  An expanded role for the dorsal auditory pathway in sensorimotor control and integration , 2011, Hearing Research.

[6]  Charles Kemp,et al.  How to Grow a Mind: Statistics, Structure, and Abstraction , 2011, Science.

[7]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[8]  Danica Kragic,et al.  Learning Actions from Observations , 2010, IEEE Robotics & Automation Magazine.

[9]  C. S. Green,et al.  Action video game modifies visual selective attention , 2003, Nature.

[10]  C. S. Green,et al.  Enumeration versus multiple object tracking: the case of action video game players , 2006, Cognition.

[11]  R. Johansson,et al.  Eye–Hand Coordination during Learning of a Novel Visuomotor Task , 2005, The Journal of Neuroscience.

[12]  Stefan Schaal,et al.  Learning inverse kinematics , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[13]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[14]  S. Schaal.  Dynamic Movement Primitives -A Framework for Motor Control in Humans and Humanoid Robotics , 2006 .

[15]  Daniel A. Braun,et al.  Motor Task Variation Induces Structural Learning , 2009, Current Biology.

[16]  R. Sperry.  [Neurology and the mind-brain problem]. , 2008, Vertex.

[17]  D. Wolpert,et al.  Principles of sensorimotor learning , 2011, Nature Reviews Neuroscience.

[18]  Stefan Schaal,et al.  2008 Special Issue: Reinforcement learning of motor skills with policy gradients , 2008 .

[19]  Jun Morimoto,et al.  Learning from demonstration and adaptation of biped locomotion , 2004, Robotics Auton. Syst..

[20]  Oliver Kroemer,et al.  Generalization of human grasping for multi-fingered robot hands , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[21]  G. Aschersleben,et al.  The Theory of Event Coding (TEC): a framework for perception and action planning. , 2001, The Behavioral and brain sciences.

[22]  R. Johansson,et al.  Prediction Precedes Control in Motor Learning , 2003, Current Biology.

[23]  Ales Ude,et al.  Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives , 2011, Robotics Auton. Syst..

[24]  Daniel M. Wolpert,et al.  Forward Models for Physiological Motor Control , 1996, Neural Networks.

[25]  D. Wolpert,et al.  Structure Learning in a Sensorimotor Association Task , 2010, PloS one.

[26]  Jun Tani,et al.  Development process of functional hierarchy for actions and motor imagery , 2009, 2009 IEEE 8th International Conference on Development and Learning.

[27]  G. Knoblich,et al.  Predicting the Effects of Actions: Interactions of Perception and Action , 2001, Psychological science.

[28]  Jun Morimoto,et al.  Task-Specific Generalization of Discrete and Periodic Dynamic Movement Primitives , 2010, IEEE Transactions on Robotics.

[29]  Hiroaki Nishino,et al.  An electronic paper craft modeling system for developing geometric sense , 2009, TENCON 2009 - 2009 IEEE Region 10 Conference.

[30]  Jun Nakanishi,et al.  Learning Attractor Landscapes for Learning Motor Primitives , 2002, NIPS.

[31]  James L. McClelland,et al.  The parallel distributed processing approach to semantic cognition , 2003, Nature Reviews Neuroscience.

[32]  Joaquín M. Fuster,et al.  Cortex and Memory: Emergence of a New Paradigm , 2009, Journal of Cognitive Neuroscience.

[33]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[34]  Sanja Fidler,et al.  Similarity-based cross-layered hierarchical representation for object categorization , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[35]  Jan Peters,et al.  Nonamemanuscript No. (will be inserted by the editor) Reinforcement Learning to Adjust Parametrized Motor Primitives to , 2011 .

[36]  James L. McClelland,et al.  Semantic Cognition: A Parallel Distributed Processing Approach , 2004 .

[37]  Yiannis Demiris,et al.  Perceiving the unusual: Temporal properties of hierarchical motor representations for action perception , 2006, Neural Networks.