Abstract
Internal representation is an important design decision in any imitation learning system. Actions and perceptual spaces were separate in classical AI due to the standard sense-process-act loop. Recently another representation that combines the two spaces into what we call a common sensorimotor space was inspired by the discovery of mirror neurons in animals and humans. The justification of this move is usually biological plausibility. This paper reports on a series of experiments comparing these two alternatives for self-initiated imitation tasks. The results of these experiments show that using a common sensorimotor representation allows the system to achieve higher accuracy and sensitivity. This is shown to be true (for our scenarios) even when the dimensionality of the common sensorimotor representation is higher than the dimensionality of the separate perceptual space. It also allows for an easier behavior generation mechanism and ensures reproducibility of learned behavior by the learner.
Keywords
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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ajallooeian, M., Ahmadabadi, M.N., Araabi, B.N., Moradi, H.: An Imitation Model based on Central Pattern Generator with application in Robotic Marionette Behavior Learning. In: IEEE IROS, pp. 4199–4205 (2009)
Alippi, C., Roveri, M.: An adaptive CUSUM-based test for signal change detection. In: 2006 IEEE International Symposium on Circuits and Systems, p. 4 (2006)
Alissandrakis, A., Nehaniv, C.L., Dautenhahn, K.: Correspondence Mapping Induced State and Action Metrics for Robotic Imitation. Cybernetics 36(3), 1–9 (2006)
Antonelo, E.A., Schrauwen, B., Stroobandt, D.: Imitation Learning of an Intelligent Navigation System for Mobile Robots using Reservoir Computing. In: 10th Barazelian Symposium on Neural Networks, pp. 93–98 (2008)
Brooks, R.A.: Intelligence without representation. Artificial Intelligence 47, 139–159 (1991)
Dufay, B., Latombe, J.C.: An approach to automatic robot programming based on inductive learning. International Journal of Robotics Research 3(4), 3–20 (1984)
Iacoboni, M.: Imitation, empathy, and mirror neurons. Annual Review of Psychology 60, 653–670 (2009)
Mohammad, Y., Nishida, T.: Constrained motif discovery in time series. New Generation Computing 27(4), 319–346 (2009)
Mohammad, Y., Nishida, T.: Robust Singular Spectrum Transform. In: Chien, B.-C., Hong, T.-P., Chen, S.-M., Ali, M. (eds.) IEA/AIE 2009. LNCS, vol. 5579, pp. 123–132. Springer, Heidelberg (2009)
Mohammad, Y., Nishida, T.: On comparing SSA-based change point discovery algorithms. In: IEEE/SICE SII 2011, pp. 938–945 (2011)
Mohammad, Y., Nishida, T.: Fluid imitation: Learning from unplanned demonstrations. International Journal of Social Robotics (in press, 2012)
Moskvina, V., Zhigljavsky, A.: An algorithm based on singular spectrum analysis for change-point detection. Communications in Statistics.Simulation and Computation 32(4), 319–352 (2003)
Nagai, Y., Rohlfing, K.J.: Can Motionese Tell Infants and Robots. What to imitate? In: 4th Inter. Symp. on Imitation in Animals and Artifacts, pp. 299–306 (2007)
Spong, M.W., Hutchinson, S., Vidyasagar, M.: Robot Modeling and Control. Wiley (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mohammad, Y., Ohmoto, Y., Nishida, T. (2012). Common Sensorimotor Representation for Self-initiated Imitation Learning. In: Jiang, H., Ding, W., Ali, M., Wu, X. (eds) Advanced Research in Applied Artificial Intelligence. IEA/AIE 2012. Lecture Notes in Computer Science(), vol 7345. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31087-4_40
Download citation
DOI: https://doi.org/10.1007/978-3-642-31087-4_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31086-7
Online ISBN: 978-3-642-31087-4
eBook Packages: Computer ScienceComputer Science (R0)