Advertisement

Modular Neural Architectures for Robotics

  • J. L. Buessler
  • J. P. Urban
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 109)

Abstract

The learning of sensory-motor functions have motivated important research works that emphasize a major demand: the combination of multiple neural networks to implement complex functions. A review of a number of works presents some implementations in robotics, describing the purpose of the modular architecture, its structure, and the learning technique that was applied. The second part of the chapter presents an original approach to this problem of network training, proposed by our group. Based on a bi-directional architecture, multiple networks can be trained online with simple local learning rules, while the robotic systems interact with their environment.

Keywords

Neural Network Inverse Model Humanoid Robot Visual Servoing Modular Architecture 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Albus JS (1975) A New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC). Journal of Dynamic Systems, Measurement and Control 37 (3): 220–227CrossRefGoogle Scholar
  2. Atkeson C, Hale J, Pollick F, Riley M, Kotosaka S, Schaal S, Shibata T, Tevatia G, Ude A, Vijayakumar S, Kawato M (2000) Using Humanoid Robots to Study Human Behavior. IEEE Intelligent Systems, 15 (Special Issue on Humanoid Robotics): 46–56Google Scholar
  3. Barto AG (1991) Connectionist Learning for Control: an Overview. In: WT Miller, RS Sutton, PJ Werbos (eds). Neural Networks for Control,. Cambridge, MA: The MIT Press, pp 5–58Google Scholar
  4. Becker S (1996) Mutual Information Maximization: Models of Cortical Self-Organization. Network: Computation in Neural Systems, 7 (1): 7–31MATHCrossRefGoogle Scholar
  5. Bottou L, Gallinari P (1991) A Framework for the Cooperation of Learning Algorithms. Proceedings of the Advances in Neural Information Processing Systems, San Mateo, CA, Vol. 3, pp. 781–788. Morgan KaufmannGoogle Scholar
  6. Buessler JL, Kara R, Wira P, Kihl H, Urban JP (1999) Multiple Self-Organizing Maps to facilitate the Learning of Visuo-Motor Correlations. Proceedings of the IEEE SMC’99, Int. Conf. on Systems, Man and Cybernetics, TokyoGoogle Scholar
  7. Buessler J-L, Urban J-P (1998) Visually Guided Movements: Learning with Modular Neural Maps in Robotics. Neural Networks 11 (7–8): 1395–1415CrossRefGoogle Scholar
  8. Buessler J-L, Urban J-P (2000) Neurobiology Suggests the Design of Modular Architectures for Neural Control. Proceedings of the Int. Conf. on Intelligent Robots And Systems IROS 2000, Takamatsu, JapanGoogle Scholar
  9. Bullock D, Grossberg D, Guenther F (1996) Neural Network Modeling of Sensory-Motor Control in Animals. In H Zelaznik (ed), Advances in Motor Learning and Control, pp. 261–292. Champaigne, IL: Human Kinetics PressGoogle Scholar
  10. Bullock D, Grossberg S (1988) Neural Dynamics of Planned Arm Movements: Emergent Invariants and Speed-Accuracy Properties during Trajectory Formation. Psychological Review 95: 49–90Google Scholar
  11. Caelli T, Guan L, Wen W (1999) Modularity in Neural Computing. Proceedings of the IEEE 87 (9): 1497–1518CrossRefGoogle Scholar
  12. Caminiti R, Ferraina S, Mayer AB (1998) Visuomotor transformations: early cortical mechanisms of reaching. Current Opinion in Neurobiology 8: 753–761CrossRefGoogle Scholar
  13. Cardoso J-F, Laheld B (1996) Equivariant Adaptive Source Separation. IEEE Trans. on Signal Processing 44 (12): 3017–3030CrossRefGoogle Scholar
  14. De Sa VR, Balard DH (1998) Category Learning Through Multimedia Sensing. Neural Computation 10 (5): 1097–1117CrossRefGoogle Scholar
  15. Fogelman Soulié F (1997) Réseaux de neurones et statistiques: une introduction. In: S. Thiria, Y. Lechevallier, O Gascuel, S Canu (eds), Statistique et méthodes neuronales, pp 1–19. Paris: DunodGoogle Scholar
  16. Fukushima K (1990) Neural network models for visual pattern recognition. In: R Eckmiller, G Hartmann, G Hauske (eds), Parallel Processing in Neural Systems and Computers, pp. 351–356. Amsterdam: ElsevierGoogle Scholar
  17. Gallinari (1995) Training of Modular Neural Net Sytems. In: MA Arbib (ed), Handbook of Brain Theory and Neural Networks, pp 582–585. Cambridge, MA: MIT PressGoogle Scholar
  18. Ghahramani Z (1995) Computation and Psychophysics of Sensorimotor Integration. Ph.D. Thesis, Massachusetts Institute of TechnologyGoogle Scholar
  19. Ghahramani Z, Hinton GE (2000) Variational Learning for Switching State-Space Models. Neural Computation 12 (4): 831–864CrossRefGoogle Scholar
  20. Ghahramani Z, Wolpert DM, Jordan MI (1997) Computational Models of Sensorimotor Integration. In: PGM a V Sanguineti (ed), Ghahramani Z, Wolpert DM, Jordan MI, pp 117–147. Elsevier PressGoogle Scholar
  21. Grossberg S, Kuperstein M (1986) Neural Dynamics of Sensory Motor Control. New York: Pergamon PressGoogle Scholar
  22. Haykin S (1994) Neural Networks: A Comprehensive Foundation. New York: Macmillan College Publishing Company, IncGoogle Scholar
  23. Jacobs RA, Jordan MI, Nowlan SJ, Hinton GE (1991) Adaptive Mixtures of Local Experts. Neural Computation, 3 (1): 79–87CrossRefGoogle Scholar
  24. Johansen TA, Murray-Smith R (1997) The Operating Regime Approach to Nonlinear Modelling and Control. In: R. Murray-Smith, T.A. Johansen (eds). Multiple Model Approaches to Modelling and Control. London, UK: Taylor and FrancisGoogle Scholar
  25. Kalaska JF (1995) Reaching Movements: Implications of Connectionist Models. In: MA Arbib (ed). Handbook of Brain Theory and Neural Networks Ed. 1995, pp 788–793. Cambridge, MA: MIT PressGoogle Scholar
  26. Kawato, Mitsuo, Uno, Yoji, Isobe, Michiaki (1987a) A Hierarchical Model for Voluntary Movement and its Application to Robotics. Proceedings of the IEEE Int. Conf. on Neural Networks, San-Diego CA, Vol. 4, pp 573–582Google Scholar
  27. Kawato M, Furukawa K, Suzuki R (1987b) A Hierarchical Neural Network Model for Control and Learning of Voluntary Movement. Biological Cyberbetics 57: 169–185MATHCrossRefGoogle Scholar
  28. Kohonen T (1982) Self-Organized Formation of Topologically Correct Feature Maps. Biological Cybernetics 46: 59–69MathSciNetCrossRefGoogle Scholar
  29. Kohonen T (1995) Self-Organizing Maps. Berlin: Springer-VerlagCrossRefGoogle Scholar
  30. Kun AL, Miller WT (1999) Control of Variable-Speed Gaits for a Biped Robot. IEEE Robotics and Automation Magazine 6 (3): 19–29CrossRefGoogle Scholar
  31. Kuperstein M (1988a) An Adaptative Neural Model for Mapping Invariant Target Position. Behavioral Neuroscience 102 (1): 148–162CrossRefGoogle Scholar
  32. Kuperstein M (1988b) Neural Model for Adaptive Hand-Eye Coordination for Single Postures. Sciences 239: 1308–1311CrossRefGoogle Scholar
  33. Lazzari S, Vercher J-L, Buizza A (1997) Manuo-ocular coordination in target tracking. I A model simulating human performance. Biological Cybernetics 77: 257–266Google Scholar
  34. LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 86 (11): 2278–2324CrossRefGoogle Scholar
  35. Littmann E, Drees A, Ritter H (1996) Visual gesture-based robot guidance with a modular neural system. In: D Touretzky, M Mozer, M Hasselmo (eds). Neural Information Processing Systems 8Google Scholar
  36. Massone LL (1993) A Biologically-Inspired Architecture for Reactive Motor Control. In: GA Bekey, KY Goldberg (eds), Neural networks in Robotics. Norwell, MA: Kluwer Academic PublishersGoogle Scholar
  37. Miall RC, Wolpert DM (1996) Forwards models for Physological motor Control. Neural Networks 9 (8): 1265–1279MATHCrossRefGoogle Scholar
  38. Miller WT, III (1994) Real-Time Neural Network Control of a Biped Walking Robot IEEE Control System 14 (1): 41–48Google Scholar
  39. Miyamoto H, Kawato M (1998) A tennis serve and upswing learning robot based on bidirectional theory. Neural Networks 11 (7–8): 1331–1344CrossRefGoogle Scholar
  40. Miyamoto H, Schaal S, Gomi, Wada, Kawato (1996) A Kendama Learning Robot Based on Bi-directional theory. Neural Networks 9 (8): 281–1302Google Scholar
  41. Moody J (1989) Fast Learning in Multi-Resolution Hierarchies. In: D Touretzky (ed), Advances in Neural Information Processing Systems, pp. 29–39. San Francisco: Morgan KauffmannGoogle Scholar
  42. Morasso P, Baratto L, Capra R, Spada G (1999) Internal models in the control of posture. Neural Networks 12 (7–8): 1173–1180CrossRefGoogle Scholar
  43. Murino V (1998) Structured Neural Networks for Pattern Recognition. IEEE Trans. on Systems Man and Cybernetics 28 (4): 553–561CrossRefGoogle Scholar
  44. Narendra KS (1990) Adaptive Control Using Neural Networks. In: WT Miller, III, RS Sutton, PJ Werbos (eds), Neural Networks for Control, pp 115–142. Cambridge, MA: The MIT PressGoogle Scholar
  45. Narendra KS, Balakrishnan J, Ciliz MK (1995) Adaptation and Learning Using Multiple Models, Switching and tuning. IEEE Control System 15 (3): 37–51CrossRefGoogle Scholar
  46. Narendra KS, Mukhopadhyay S (1996) Intelligent Control Using Neural Networks. In: MM Gupta, NK Sinha (eds), Intelligent Control Systems. New York: IEEE PressGoogle Scholar
  47. Poggio T, Girosi F (1990) Networks for Approximation and Learning. Proceedings of the IEEE 78 (9): 1615–1441CrossRefGoogle Scholar
  48. Principe JC, Wang L, Motter MA (1998) Local Dynamic Modeling with Self-Organizing Maps and Applications to Nonlinear System Identification and Control. Proceedings of the IEEE 86 (11): 2240–2258CrossRefGoogle Scholar
  49. Rae R, Ritter HJ (1998) Recognition of Human Head Orientation Based on Artificial Neural Networks. IEEE Trans. on Neural Networks 9 (2): 257–265CrossRefGoogle Scholar
  50. Riley M, Ude A, Atkeson CG (2000) Methods for Motion Generation and Interaction with a Humanoid Robot: Case Studies of Dancing and Catching. Proceedings of the Workshop on Interactive Robotics and Entertainment, CMU Pittsburg, pp 35–42. AAAI PressGoogle Scholar
  51. Ritter H, Schulten K (1988) Extending Kohonen’s Self-Organizing Mapping Algorithm to Learn Ballistic Movements. In: R Eckmiller, C von der Malsburg (eds), Neural Computers F41: 393–406. Berlin: Springer-VerlagGoogle Scholar
  52. Ritter HJ, Martinetz TM, Schulten KJ (1992) Neural Computation and Self-Organizing Maps. Reading, MA: Addison-WesleyMATHGoogle Scholar
  53. Ritter HJ, Schulten KJ (1986) Topology-Conserving Mappings for Learning Motor Tasks. Proceedings of the International Conference on Neural Networks for Computing, Snowbird, Utah, pp 376–380. American Institute of PhysicsGoogle Scholar
  54. Rosenbaum DA (1991) Human Motor Control. San Diego, CA: Academic pressGoogle Scholar
  55. Sharkey AJC, Sharkey NE (1997) Combining Diverse Neural Nets. The Knowledge Engineering Review 12 (3): 231–247CrossRefGoogle Scholar
  56. Srinivasa N, Sharma R (1997) SOIM: A Self-Organizing Invertible Map with Application in Active Vision. IEEE Trans. on Neural Networks 8 (3): 758–773CrossRefGoogle Scholar
  57. Srinivasa N, Sharma R (1998) Efficient Learning of VAM-Based Representation of 3D Targets and its Active Vision Applications. Neural Networks 11 (1): 153–171CrossRefGoogle Scholar
  58. Suganthan PN (1999) Hierarchical Overlapped SOM’s for Pattern Classification. IEEE Trans. on Neural Networks 10 (1): 193–196CrossRefGoogle Scholar
  59. van der Smagt P, Groen F (1995) Approximation with neural networks: Between local and global approximation. Proceedings of the ICNN’95 (International Conference on Neural Networks), Perth, Australia, Vol. II, pp 1060–1064Google Scholar
  60. Wada Y, Kawato M (1993) A Neural Network Model for Arm Trajectory Formation Using Forward and Inverse Dynamics Models. Neural Networks 6 (7): 919–932CrossRefGoogle Scholar
  61. Walter J, Ritter H (1995) Investment Learning with Hierarchical PSOM. In: DS Touretzky (ed), Advances in Neural Information Processing Systems 8:570–576. Bradford MIT Press, 1996Google Scholar
  62. Widrow B, Lehr MA (1990) 30 Years of Adaptative Neural Networks: Perceptron, Madaline and Backpropagation. Proceedings of the IEEE 78(9):1415–1441Google Scholar
  63. Widrow B, Walach E (1996) Adaptive Inverse Control. Upper Saddle River, NJ: Prentice Hall PressGoogle Scholar
  64. Wolpert DM, Kawato, M (1998) Multiple Paired Forward and Inverse Models for Motor Control. Neural Networks 11 (7–8): 1317–1330CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • J. L. Buessler
    • 1
  • J. P. Urban
    • 1
  1. 1.Trop Research GroupMulhouseFrance

Personalised recommendations