Common Sensorimotor Representation for Self-initiated Imitation Learning
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.
KeywordsAction Space Mirror Neuron Central Pattern Generator Motif Discovery Perceptual Space
Unable to display preview. Download preview PDF.
- 1.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)Google Scholar
- 2.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)Google Scholar
- 3.Alissandrakis, A., Nehaniv, C.L., Dautenhahn, K.: Correspondence Mapping Induced State and Action Metrics for Robotic Imitation. Cybernetics 36(3), 1–9 (2006)Google Scholar
- 4.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)Google Scholar
- 10.Mohammad, Y., Nishida, T.: On comparing SSA-based change point discovery algorithms. In: IEEE/SICE SII 2011, pp. 938–945 (2011)Google Scholar
- 11.Mohammad, Y., Nishida, T.: Fluid imitation: Learning from unplanned demonstrations. International Journal of Social Robotics (in press, 2012)Google Scholar
- 13.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)Google Scholar
- 14.Spong, M.W., Hutchinson, S., Vidyasagar, M.: Robot Modeling and Control. Wiley (2005)Google Scholar