Neural Architectures for Robot Intelligence

We argue that direct experimental approaches to elucidate the architecture of higher brains may benefit from insights gained from exploring the possibilities and limits of artificial control architectures for robot systems. We present some of our recent work that has been motivated by that view and that is centered around the study of various aspects of hand actions since these are intimately linked with many higher cognitive abilities. As examples, we report on the development of a modular system for the recognition of continuous hand postures based on neural nets, the use of vision and tactile sensing for guiding prehensile movements of a multifingered hand, and the recognition and use of hand gestures for robot teaching. Regarding the issue of learning, we propose to view real-world learning from the perspective of data-mining and to focus more strongly on the imitation of observed actions instead of purely reinforcement-based exploration. As a concrete example of such an effort we report on the status of an ongoing project in our laboratory in which a robot equipped with an attention system with a neurally inspired architecture is taught actions by using hand gestures in conjunction with speech commands. We point out some of the lessons learnt from this system, and discuss how systems of this kind can contribute to the study of issues at the junction between natural and artificial cognitive systems.

[1]  Helge J. Ritter,et al.  A system for various visual classification tasks based on neural networks , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[2]  Gregory Piatetsky-Shapiro,et al.  Advances in Knowledge Discovery and Data Mining , 2004, Lecture Notes in Computer Science.

[3]  M P Young,et al.  Brain structure-function relationships: advances from neuroinformatics. , 2000, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[4]  E. DeYoe,et al.  Concurrent processing in the primate visual cortex. , 1995 .

[5]  Kenji Doya,et al.  What are the computations of the cerebellum, the basal ganglia and the cerebral cortex? , 1999, Neural Networks.

[6]  Malcolm P. Young,et al.  Analysis and Modelling of the Organization of the Mammalian Cerebral Cortex , 1993 .

[7]  Helge J. Ritter,et al.  Visual recognition of continuous hand postures , 2002, IEEE Trans. Neural Networks.

[8]  Helge J. Ritter,et al.  Visual Checking of Grasping Positions of a Three-Fingered Robot Hand , 2001, ICANN.

[9]  J. van Leeuwen,et al.  Neural Networks: Tricks of the Trade , 2002, Lecture Notes in Computer Science.

[10]  Stefan Schaal,et al.  Overt visual attention for a humanoid robot , 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).

[11]  Bernhard Schölkopf,et al.  Introduction to support vector learning , 1999 .

[12]  Helge Ritter,et al.  Sonification of markov chain monte carlo simulations , 2001 .

[13]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[14]  Maja J. Matarić,et al.  Control and Imitation in Humanoids , 2000, AAAI 2000.

[15]  Helge Ritter,et al.  Listen to your Data: Model-Based Sonification for Data Analysis , 1999 .

[16]  Brian Scassellati,et al.  A Context-Dependent Attention System for a Social Robot , 1999, IJCAI.

[17]  Brian Scassellati.  Mechanisms of Shared Attention for a Humanoid Robot , 1998 .

[18]  Helge J. Ritter,et al.  Resolution-Based Complexity Control for Gaussian Mixture Models , 2001, Neural Computation.

[19]  Henrik I. Christensen,et al.  AUC robot camera head , 1992, Defense, Security, and Sensing.

[20]  Joseph A. Driscoll,et al.  A visual attention network for a humanoid robot , 1998, Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190).

[21]  Helge Ritter,et al.  Combining multiple neural nets for visual feature selection and classification , 1999 .

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

[23]  Helge J. Ritter,et al.  Crystallization sonification of high-dimensional datasets , 2005, TAP.

[24]  R. Brooks,et al.  The cog project: building a humanoid robot , 1999 .

[25]  Peter Bakker,et al.  Robot see, robot do: An overview of robot imitation , 1996 .

[26]  G. Peters.  Theories of Three-Dimensional Object Perception A Survey , 2000 .

[27]  H. Ritter,et al.  An Integrated System for Advanced Human-Computer Interaction , 1999 .

[28]  Ipke Wachsmuth,et al.  Collaborative Research Centre “Situated Artificial Communicators” at the University of Bielefeld, Germany , 2004, Artificial Intelligence Review.

[29]  Helge J. Ritter,et al.  Learning and Generalization in Cascade Network Architectures , 1996, Neural Computation.

[30]  D. Lewkowicz,et al.  A dynamic systems approach to the development of cognition and action. , 2007, Journal of cognitive neuroscience.

[31]  Steven S. Hsiao,et al.  Neural mechanisms of tactile form recognition , 1995 .

[32]  D I Perrett,et al.  Frameworks of analysis for the neural representation of animate objects and actions. , 1989, The Journal of experimental biology.

[33]  J. Daugman.  Two-dimensional spectral analysis of cortical receptive field profiles , 1980, Vision Research.

[34]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[35]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[36]  Ján Jockusch,et al.  Exploration based on neural networks with applications in manipulator control , 2000 .

[37]  Alex M. Andrew,et al.  Reinforcement Learning: : An Introduction , 1998 .

[38]  Helge J. Ritter,et al.  Guiding attention for grasping tasks by gestural instruction: the GRAVIS-robot architecture , 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).

[39]  David J. Willshaw,et al.  Scaling and brain connectivity , 1994, Nature.

[40]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[41]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[42]  Helge J. Ritter,et al.  Rapid learning with parametrized self-organizing maps , 1996, Neurocomputing.

[43]  Helge J. Ritter,et al.  A tactile sensor system for a three-fingered robot manipulator , 1997, Proceedings of International Conference on Robotics and Automation.

[44]  C. Breazeal,et al.  Challenges in building robots that imitate people , 2002 .

[45]  Thomas Hermann,et al.  Supplementary Material for "Crystallization Sonification of High-dimensional Datasets" , 2002 .

[46]  Sridhar Mahadevan,et al.  Automatic Programming of Behavior-Based Robots Using Reinforcement Learning , 1991, Artif. Intell..

[47]  Philip K. Maini,et al.  Experimental and Theoretical Advances in Biological Pattern Formation , 1993, NATO ASI Series.

[48]  Gernot A. Fink,et al.  A communication framework for heterogeneous distributed pattern analysis , 1995, Proceedings 1st International Conference on Algorithms and Architectures for Parallel Processing.

[49]  Helge Ritter,et al.  Learning to recognize 3D-Hand Postures from Perspective Pixel Images , 1992 .