Achieving "organic compositionality" through self-organization: Reviews on brain-inspired robotics experiments

The current paper examines how compositional structures can self-organize in given neuro-dynamical systems when robot agents are forced to learn multiple goal-directed behaviors simultaneously. Firstly, we propose a basic model accounting for the roles of parietal-premotor interactions for representing skills for goal-directed behaviors. The basic model had been implemented in a set of robotics experiments employing different neural network architectures. The comparative reviews among those experimental results address the issues of local vs distributed representations in representing behavior and the effectiveness of level structures associated with different sensory-motor articulation mechanisms. It is concluded that the compositional structures can be acquired "organically" by achieving generalization in learning and by capturing the contextual nature of skilled behaviors under specific conditions. Furthermore, the paper discusses possible feedback for empirical neuroscience studies in the future.

[1]  Aude Billard,et al.  Learning human arm movements by imitation: : Evaluation of a biologically inspired connectionist architecture , 2000, Robotics Auton. Syst..

[2]  J A Kelso,et al.  Dynamic pattern generation in behavioral and neural systems. , 1988, Science.

[3]  Masayuki Inaba,et al.  Learning by watching: extracting reusable task knowledge from visual observation of human performance , 1994, IEEE Trans. Robotics Autom..

[4]  Atsushi Iriki,et al.  Inferior parietal somatosensory neurons coding face-hand coordination in Japanese macaques , 2003, Somatosensory & motor research.

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

[6]  Aude Billard,et al.  From Animals to Animats , 2004 .

[7]  C. Blakemore.  The Working Brain , 1972, Nature.

[8]  Stefan Schaal,et al.  http://www.jstor.org/about/terms.html. JSTOR's Terms and Conditions of Use provides, in part, that unless you have obtained , 2007 .

[9]  E. Fetz,et al.  Sensory and motor responses of precentral cortex cells during comparable passive and active joint movements. , 1980, Journal of neurophysiology.

[10]  Jun Tani,et al.  Learning Multiple Goal-Directed Actions Through Self-Organization of a Dynamic Neural Network Model: A Humanoid Robot Experiment , 2008, Adapt. Behav..

[11]  Jun Tani,et al.  Codevelopmental Learning Between Human and Humanoid Robot Using a Dynamic Neural-Network Model , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[12]  Jun Tani,et al.  Learning to Generate Combinatorial Action Sequences Utilizing the Initial Sensitivity of Deterministic Dynamical Systems , 2003, IWANN.

[13]  D. Wolpert,et al.  Mental state inference using visual control parameters. , 2005, Brain research. Cognitive brain research.

[14]  Stanley J. Rosenschein,et al.  A dynamical systems perspective on agent-environment interaction , 1996 .

[15]  H. Sakata,et al.  Neural mechanisms of visual guidance of hand action in the parietal cortex of the monkey. , 1995, Cerebral cortex.

[16]  L. Paninski,et al.  Information about movement direction obtained from synchronous activity of motor cortical neurons. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[17]  Jun Tani,et al.  Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes , 2005, Adapt. Behav..

[18]  Michael I. Jordan.  Attractor dynamics and parallelism in a connectionist sequential machine , 1990 .

[19]  Hideo Sakata,et al.  Navigation-associated medial parietal neurons in monkeys , 2006, Proceedings of the National Academy of Sciences.

[20]  Michael A. Arbib,et al.  Modeling parietal-premotor interactions in primate control of grasping , 1998, Neural Networks.

[21]  S. Wiggins.  Introduction to Applied Nonlinear Dynamical Systems and Chaos , 1989 .

[22]  M Ito,et al.  Neurophysiological aspects of the cerebellar motor control system. , 1970, International journal of neurology.

[23]  Jun Tani,et al.  Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment , 2003, IEEE Trans. Syst. Man Cybern. Part A.

[24]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[25]  G. Hesslow.  Conscious thought as simulation of behaviour and perception , 2002, Trends in Cognitive Sciences.

[26]  K M Heilman,et al.  Ideational apraxia--a re-definition. , 1973, Brain : a journal of neurology.

[27]  G. Rizzolatti,et al.  Parietal Lobe: From Action Organization to Intention Understanding , 2005, Science.

[28]  Jun Tani,et al.  Learning to generate articulated behavior through the bottom-up and the top-down interaction processes , 2003, Neural Networks.

[29]  Naohiro Fukumura,et al.  Learning goal-directed sensory-based navigation of a mobile robot , 1994, Neural Networks.

[30]  Yoshihiko Nakamura,et al.  Embodied Symbol Emergence Based on Mimesis Theory , 2004, Int. J. Robotics Res..

[31]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[32]  Jun Tani,et al.  Model-based learning for mobile robot navigation from the dynamical systems perspective , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[33]  M. Jeannerod.  The representing brain: Neural correlates of motor intention and imagery , 1994, Behavioral and Brain Sciences.

[34]  Jun Tani,et al.  How Hierarchical Control Self-organizes in Artificial Adaptive Systems , 2005, Adapt. Behav..

[35]  Michael A. Arbib,et al.  Schema design and implementation of the grasp-related mirror neuron system , 2002, Biological Cybernetics.

[36]  E. Fetz,et al.  Responses of identified cells in postcentral cortex of awake monkeys during comparable active and passive joint movements. , 1980, Journal of neurophysiology.

[37]  Yoshihiko Nakamura,et al.  Imitation and primitive symbol acquisition of humanoids by the integrated mimesis loop , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[38]  Geoffrey E. Hinton,et al.  Distributed Representations , 1986, The Philosophy of Artificial Intelligence.

[39]  Masao Ito.  Bases and implications of learning in the cerebellum--adaptive control and internal model mechanism. , 2005, Progress in brain research.

[40]  Marco Iacoboni,et al.  Visuo-motor integration and control in the human posterior parietal cortex: Evidence from TMS and fMRI , 2006, Neuropsychologia.

[41]  Y. Sakurai,et al.  Dynamic Synchrony of Firing in the Monkey Prefrontal Cortex during Working-Memory Tasks , 2006, The Journal of Neuroscience.

[42]  J. Kelso,et al.  Elementary Coordination Dynamics , 1994 .

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

[44]  Yasuo Kuniyoshi,et al.  Stability and controllability in a rising motion: a global dynamics approach , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[45]  S. Swinnen.  Interlimb coordination : neural, dynamical, and cognitive constraints , 1994 .

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

[47]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[48]  M. Goldberg,et al.  Ventral intraparietal area of the macaque: anatomic location and visual response properties. , 1993, Journal of neurophysiology.

[49]  M. Kawato,et al.  A hierarchical neural-network model for control and learning of voluntary movement , 2004, Biological Cybernetics.

[50]  Michael A. Arbib,et al.  Perceptual Structures and Distributed Motor Control , 1981 .

[51]  Michael McCloskey,et al.  Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem , 1989 .

[52]  Jean-Arcady Meyer,et al.  Learning to Perceive the World as Articulated: An Approach for Hierarchical Learning in Sensory-Motor Systems , 1998 .

[53]  Jun Tani,et al.  On-line Imitative Interaction with a Humanoid Robot Using a Dynamic Neural Network Model of a Mirror System , 2004, Adapt. Behav..

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

[55]  R. Johansson,et al.  Evidence for the involvement of the posterior parietal cortex in coordination of fingertip forces for grasp stability in manipulation. , 2003, Journal of neurophysiology.

[56]  K. Doya,et al.  Memorizing oscillatory patterns in the analog neuron network , 1989, International 1989 Joint Conference on Neural Networks.

[57]  J. Assad,et al.  Dissociation of visual, motor and predictive signals in parietal cortex during visual guidance , 1999, Nature Neuroscience.

[58]  R. Tate,et al.  Error Types in Ideomotor Apraxia: A Qualitative Analysis , 1994, Brain and Cognition.