A predictive network architecture for a robust and smooth robot docking behavior

Abstract

Robots and living beings exhibit latencies in their sensorimotor processing due to mechanical and electronic or neural processing delays. A reaction typically occurs to input stimuli of the past. This is critical not only when the environment changes (e.g. moving objects) but also when the agent itself moves. An agent that does not predict while moving may need to remain static between sensory input acquisition and output response to guarantee that the response is appropriate to the percept. We propose a biologically-inspired learning model of predictive sensorimotor integration to compensate for this latency. In this model, an Elman network is developed for sensory prediction and sensory filtering; a Continuous Actor-Critic Learning Automaton (CACLA) is trained for continuous action generation. For a robot docking experiment, this architecture improves the smoothness of the robot’s sensory input and therefore results in a faster and more accurate continuous approach behavior.

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

References

  1. [1]

    G. Foresti, IEEE Transactions on Circuits and Systems for Video Technology 9, 1045 (1999).

    Article  Google Scholar 

  2. [2]

    E. Goldstein, Sensation and Perception (Wadsworth Publishing Company, 2010).

    Google Scholar 

  3. [3]

    M. Bar, Journal of Cognitive Neuroscience 15, 600 (2003).

    Article  Google Scholar 

  4. [4]

    K. Kveraga, A. Ghuman, and M. Bar, Brain and Cognition 65, 145 (2007).

    Article  Google Scholar 

  5. [5]

    D. MacKay, Nature (1958).

    Google Scholar 

  6. [6]

    R. Nijhawan, Nature (1994).

    Google Scholar 

  7. [7]

    R. Nijhawan, Nature (1997).

    Google Scholar 

  8. [8]

    W. Li, V. Piëch, and C. Gilbert, Nature Neuroscience 7, 651 (2004).

    Article  Google Scholar 

  9. [9]

    L. Trainor, International Journal of Psychophysiology 83, 256 (2012).

    Article  Google Scholar 

  10. [10]

    J. Hirsch and C. Gilbert, The Journal of Neuroscience 11, 1800 (1991).

    Google Scholar 

  11. [11]

    Z. Kisvarday, E. Toth, M. Rausch, and U. Eysel, Cerebral Cortex 7, 605 (1997).

    Article  Google Scholar 

  12. [12]

    V. Lamme and P. Roelfsema, Trends in Neurosciences 23, 571 (2000).

    Article  Google Scholar 

  13. [13]

    G. Le Masson, S. Renaud-Le Masson, D. Debay, T. Bal, et al., Nature 417, 854 (2002).

    Article  Google Scholar 

  14. [14]

    C. Darrin, G. Christopher, U. Ale2, and G. Cheng, International Journal of Humanoid Robotics 1, 585 (2004).

    Article  Google Scholar 

  15. [15]

    L. Natale, F. Nori, G. Sandini, and G. Metta, in IEEE 6th International Conference on Development and Learning, ICDL (2007), pp. 324–329.

    Google Scholar 

  16. [16]

    S. Nishide, T. Ogata, J. Tani, K. Komatani, and H. Okuno, Advanced Robotics 22, 527 (2008).

    Google Scholar 

  17. [17]

    N. Pradhan, T. Burg, and S. Birchfield, in IEEE American Control Conference, ACC (2011), pp. 4628–4633.

    Google Scholar 

  18. [18]

    T. H. Hong, C. Rasmussen, T. Chang, and M. Shneier, in Proc. of SPIE Aeroscience Conference (2002), pp. 311–319.

    Google Scholar 

  19. [19]

    Y. Matsushita and J. Miura, Robotics and Autonomous Systems 59, 274 (2011).

    Article  Google Scholar 

  20. [20]

    J. Zhong, C. Weber, and S. Wermter, Artificial Neural Networks and Machine Learning, ICANN pp. 539–546 (2012).

    Google Scholar 

  21. [21]

    S. Chen, IEEE Transactions on Industrial Electronics 59, 4409 (2012), ISSN 0278-0046.

    Article  Google Scholar 

  22. [22]

    V. Bonato, E. Marques, and G. Constantinides, Journal of Signal Processing Systems 56, 41 (2009), ISSN 1939-8018.

    Article  Google Scholar 

  23. [23]

    T. Klein, J. Jeka, T. Kiemel, and M. Lewis, Biological Cybernetics pp. 1–14 (2012).

    Google Scholar 

  24. [24]

    A. Schaefer, S. Udluft, and H. Zimmermann, Neurocomputing 71, 2481 (2008).

    Article  Google Scholar 

  25. [25]

    R. Möller, Journal of Theoretical Biology (2012).

    Google Scholar 

  26. [26]

    J. Hirel, P. Gaussier, and M. Quoy, in IEEE International Conference on Robotics and Biomimetics, ROBIO (2011), pp. 1627–1632.

    Google Scholar 

  27. [27]

    R. Saegusa, F. Nori, G. Sandini, G. Metta, and S. Sakka, in 7th IEEE-RAS International Conference on Humanoid Robots (2007), pp. 102–108.

    Google Scholar 

  28. [28]

    S. Thrun, Machine Learning 33, 41 (1998).

    MATH  Article  Google Scholar 

  29. [29]

    K. Cullen, Current Opinion in Neurobiology 14, 698 (2004).

    Article  Google Scholar 

  30. [30]

    N. Navarro-Guerrero, C. Weber, P. Schroeter, and S. Wermter, Robotics and Autonomous Systems (2012).

    Google Scholar 

  31. [31]

    Aldebaran, http://www.aldebaran-robotics.com (2009).

  32. [32]

    H. van Hasselt and M. Wiering, in IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, ADPRL (2007), pp. 272–279.

    Google Scholar 

  33. [33]

    R. Shadmehr, M. Smith, and J. Krakauer, Annual Review of Neuroscience 33, 89 (2010).

    Article  Google Scholar 

  34. [34]

    J. Izawa and R. Shadmehr, PLoS Computational Biology 7, e1002012 (2011).

    Article  Google Scholar 

  35. [35]

    D. Ballard, Pattern Recognition 13, 111 (1981).

    MATH  Article  Google Scholar 

  36. [36]

    W. Yan, C. Weber, and S. Wermter, in International Joint Conference on Neural Networks, IJCNN (2012), pp. 1–8.

    Google Scholar 

  37. [37]

    M. Spratling, Vision Research 48, 1391 (2008).

    Article  Google Scholar 

  38. [38]

    K. Rauss, S. Schwartz, and G. Pourtois, Neuroscience & Biobehavioral Reviews 35, 1237 (2011).

    Article  Google Scholar 

  39. [39]

    J. Anderson and L. Schooler, The Oxford Handbook of Memory. (2000).

    Google Scholar 

  40. [40]

    A. Alink, C. Schwiedrzik, A. Kohler, W. Singer, and L. Muckli, The Journal of Neuroscience 30, 2960 (2010).

    Article  Google Scholar 

  41. [41]

    M. Corbetta, G. Shulman, et al., Nature Reviews Neuroscience 3, 215 (2002).

    Article  Google Scholar 

  42. [42]

    O. Khatib, in Proc. IEEE International Conference on Robotics and Automation. (1985), vol. 2, pp. 500–505.

    Google Scholar 

  43. [43]

    L. Huang, Robotics and Autonomous Systems 57, 55 (2009).

    Article  Google Scholar 

  44. [44]

    R. Olberg, Current Opinion in Neurobiology 22, 267 (2011).

    Article  Google Scholar 

  45. [45]

    P. Hartono and S. Kakita, Memetic Computing 1, 305 (2009).

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Junpei Zhong.

About this article

Cite this article

Zhong, J., Weber, C. & Wermter, S. A predictive network architecture for a robust and smooth robot docking behavior. Paladyn 3, 172–180 (2012). https://doi.org/10.2478/s13230-013-0106-8

Download citation

Keywords

  • Sensorimotor integration
  • Continuous Actor-Critic Learning Automaton
  • Elman network
  • Sensory prediction