Skip to main content
SpringerLink
Log in

Learning Compositional Hierarchies of a Sensorimotor System

  • Conference paper
Book cover Advances in Intelligent Data Analysis XII (IDA 2013)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 8207))

Included in the following conference series:

Abstract

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.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ben Amor, H., Kroemer, O., Hillenbrand, U., Neumann, G., Peters, J.: Generalization of human grasping for multi-fingered robot hands. In: Proc. of 25th International Conference on Intelligent Robots and Systems, IROS 2012 (2012)

    Google Scholar 

  2. Bengio, Y.: Learning deep architectures for AI. Foundations and Trends in Machine Learning 2(1), 1–127 (2009)

    Article  MathSciNet  MATH  Google Scholar 

  3. Braun, D.A., Aertsen, A., Wolpert, D.M., Mehring, C.: Motor task variation induces structural learning. Current Biology 19(4), 352–357 (2009)

    Article  Google Scholar 

  4. Braun, D.A., Waldert, S., Aertsen, A., Wolpert, D.M., Mehring, C.: Structure learning in a sensorimotor association task. PLoS ONE 5(1) (January 2010)

    Google Scholar 

  5. Degallier, S., Righetti, L., Gay, S., Ijspeert, A.: Toward simple control for complex, autonomous robotic applications: combining discrete and rhythmic motor primitives. Auton. Robots 31(2-3), 155–181 (2011)

    Article  Google Scholar 

  6. Demiris, Y., Simmons, G.: Perceiving the unusual: Temporal properties of hierarchical motor representations for action perception. Neural Networks 19(3), 272–284 (2006)

    Article  MATH  Google Scholar 

  7. D’Souza, A., Vijayakumar, S., Schaal, S.: Learning inverse kinematics. In: Proceedings of the 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems, vol. 1, pp. 298–303 (2001)

    Google Scholar 

  8. Fidler, S., Boben, M., Leonardis, A.: Similarity-based cross-layered hierarchical representation for object categorization. In: Proc. of CVPR (2008)

    Google Scholar 

  9. Fuster, J.M.: Cortex and memory: Emergence of a new paradigm. J. Cognitive Neuroscience 21(11), 2047–2072 (2009)

    Article  Google Scholar 

  10. Green, C., Bavelier, D.: Enumeration versus multiple object tracking: the case of action video game players. Cognition 101(1), 217–245 (2006)

    Article  Google Scholar 

  11. Green, S.C., Bavelier, D.: Action video game modifies visual selective attention. Nature 423(6939) (2003)

    Google Scholar 

  12. Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  13. Hommel, B., Müsseler, J., Aschersleben, G., Prinz, W.: The Theory of Event Coding (TEC): A framework for perception and action planning. Behavioral and Brain Sciences 24(05), 849–878 (2002)

    Article  Google Scholar 

  14. Ijspeert, A., Nakanishi, J., Schaal, S.: Learning Attractor Landscapes for Learning Motor Primitives. In: Advances in Neural Information Processing Systems 15, NIPS 2002, pp. 1547–1554 (2002)

    Google Scholar 

  15. Jackson, P.L., Decety, J.: Motor cognition: a new paradigm to study self-other interactions. Curr. Opin. Neurobiol. 14(2), 259–263 (2004)

    Article  Google Scholar 

  16. Knoblich, G., Flach, R.: Predicting the effects of actions: interactions of perception and action. Psychol. Sci. 12(6), 467–472 (2001)

    Article  Google Scholar 

  17. Kober, J., Wilhelm, A., Oztop, E., Peters, J.: Reinforcement learning to adjust parametrized motor primitives to new situations. Autonomous Robots 33, 361–379 (2012)

    Article  Google Scholar 

  18. Krüger, V., Herzog, D., Baby, S., Ude, A., Kragic, D.: Learning actions from observations. IEEE Robot. Automat. Mag. 17(2), 30–43 (2010)

    Article  Google Scholar 

  19. McClelland, J.L., Rogers, T.T.: The parallel distributed processing approach to semantic cognition. Nat. Rev. Neurosci. 4(4), 310–322 (2003)

    Article  Google Scholar 

  20. Miall, R.C., Wolpert, D.M.: Forward models for physiological motor control. Neural Networks 9(8), 1265–1279 (1996)

    Article  MATH  Google Scholar 

  21. Nakanishi, J., Morimoto, J., Endo, G., Cheng, G., Schaal, S., Kawato, M.: Learning from demonstration and adaptation of biped locomotion. Robotics and Autonomous Systems 47, 79–91 (2004)

    Article  Google Scholar 

  22. Nishimoto, R., Tani, J.: Development process of functional hierarchy for actions and motor imagery. In: Proceedings of the 2009 IEEE 8th International Conference on Development and Learning, DEVLRN 2009, pp. 1–6. IEEE Computer Society, Washington, DC (2009)

    Chapter  Google Scholar 

  23. Peters, J., Schaal, S.: Reinforcement learning of motor skills with policy gradients. Neural Networks 21(4), 682–697 (2008)

    Article  Google Scholar 

  24. Prinz, W.: Perception and Action Planning. European Journal of Cognitive Psychology 9(2), 129–154 (1997)

    Article  MathSciNet  Google Scholar 

  25. Rauschecker, J.P.: An expanded role for the dorsal auditory pathway in sensorimotor control and integration. Hearing Research 271(1-2), 16–25 (2011)

    Article  Google Scholar 

  26. Rumelhart, D.E., McClelland, J.L.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Foundations, vol. 1. MIT Press (1986)

    Google Scholar 

  27. Sailer, U., Flanagan, J.R., Johansson, R.S.: Eye-hand coordination during learning of a novel visuomotor task. J. Neurosci. 25(39), 8833–8842 (2005)

    Article  Google Scholar 

  28. Schaal, S.: Learning robot control, 2nd edn., pp. 983–987. MIT press (2002)

    Google Scholar 

  29. Schaal, S.: Dynamic movement primitives - a framework for motor control in humans and humanoid robots. In: The International Symposium on Adaptive Motion of Animals and Machines (2003)

    Google Scholar 

  30. Schaal, S., Mohajerian, P., Ijspeert, A.: A.j.: Dynamics systems vs. optimal control — a unifying view. In: Progress in Brain Research, pp. 425–445 (2007)

    Google Scholar 

  31. Sperry, R.W.: Neurology and the mind-brain problem. American Scientist 40(2) (1952)

    Google Scholar 

  32. Tamosiunaite, M., Nemec, B., Ude, A., Wörgötter, F.: Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives. Robot. Auton. Syst. 59(11), 910–922 (2011)

    Article  Google Scholar 

  33. Tenenbaum, J.B., Kemp, C., Griffiths, T.L., Goodman, N.D.: How to grow a mind: statistics, structure, and abstraction. Science (New York) 331(6022), 1279–1285 (2011)

    Article  MathSciNet  MATH  Google Scholar 

  34. Ude, A., Gams, A., Asfour, T., Morimoto, J.: Task-specific generalization of discrete and periodic dynamic movement primitives. Trans. Rob. 26(5), 800–815 (2010)

    Article  Google Scholar 

  35. Wolpert, D.M., Diedrichsen, J.A., Flanagan, J.R.: Principles of sensorimotor learning. Nat. Rev. Neurosci. 12(12), 739–751 (2011)

    Google Scholar 

  36. Wolpert, D.M., Flanagan, J.R.: Motor learning. Current Biology 20(11), 467–472 (2010)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Computer and Information Science, AI Lab, University of Ljubljana, Tržaška 25, SI-1000, Ljubljana, Slovenia

    Jure Žabkar

  2. Intelligent Robotics Lab, School of Computer Science, University of Birmingham, UK

    Aleš Leonardis

  3. Centre for Computational Neuroscience and Cognitive Robotics, University of Birmingham, UK

    Aleš Leonardis

Authors
  1. Jure Žabkar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Aleš Leonardis
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. School of Information Systems, Computing and Mathematics, Brunel University, UB8 3PH, Uxbridge, Middlesex, UK

    Allan Tucker  & Stephen Swift  & 

  2. Faculty of Computer Science/IT, Ostfalia University of Applied Sciences, Am Exer 2, 38302, Wolfenbüttel, Germany

    Frank Höppner

  3. Faculty of Science, Department of Information and Computing Science, Buys Ballot Laboratory, Universiteit Utrecht, Princetonplein 5, 3584 CC, Utrecht, The Netherlands

    Arno Siebes

Rights and permissions

Reprints and permissions

Copyright information

© 2013 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Žabkar, J., Leonardis, A. (2013). Learning Compositional Hierarchies of a Sensorimotor System. In: Tucker, A., Höppner, F., Siebes, A., Swift, S. (eds) Advances in Intelligent Data Analysis XII. IDA 2013. Lecture Notes in Computer Science, vol 8207. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41398-8_39

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-41398-8_39

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-41397-1

  • Online ISBN: 978-3-642-41398-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation