Abstract
This paper presents our proposed approach for discovering new motor primitives in a database of demonstrated example movements. Example trajectory data is usually obtained from human demonstration or by kinesthetic guiding. It is then organized and clustered into a binary tree with transition graphs at every level. Each level presents a different granularity of example data. We show that new movements (or their parts) can be discovered through graph search, by exploiting the interdependencies between the movements encoded by the graph. By combining results with optimized interpolation new series of primitives can be found. A complete representation of new, not directly demonstrated, movements can be constructed by using new series of movements with statistical generalization techniques.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Breazeal, C., Scassellati, B.: Robots that imitate humans. Trends Cognitive Sci. 6(11), 481–487 (2002)
Calinon, S., D’halluin, F., Sauser, E.L., Caldwell, D.G., Billard, A.G.: Learning and reproduction of gestures by imitation: An approach based on Hidden Markov Model and Gaussian Mixture Regression. IEEE Robot. Autom. Mag. 17(2), 44–54 (2010)
Dillmann, R.: Teaching and learning of robot tasks via observation of human performance. Robotics and Autonomous Systems 47(2-3), 109–116 (2004)
Ijspeert, A.J., Nakanishi, J., Schaal, S.: Movement imitation with nonlinear dynamical systems in humanoid robots. In: Proc. IEEE Int. Conf. Robot. Autom., Washington, DC, pp. 1398–1403 (2002)
Kittler, J., Illingworth, J.: Minimum error thresholding. Pattern Recognition 19(1), 41–47 (1986)
Kovar, L., Gleicher, M., Pighin, F.: Motion graphs. ACM Transactions on Graphics 21(3), 473–482 (2002)
Kulić, D., Takano, W., Nakamura, Y.: Online segmentation and clustering from continuous observation of whole body motions. IEEE Trans. Robot. 25(5), 1158–1166 (2009)
Kulić, D., Takano, W., Nakamura, Y.: Incremental learning, clustering and hierarchy formation of whole body motion patterns using adaptive hidden Markov chains. Int. J. Robot. Res. 27(7), 761–784 (2008)
Lim, B., Ra, S., Park, F.C.: Movement Primitives, Principal Component Analysis, and the Efficient Generation of Natural Motions. In: Proceedings of the 2005 IEEE International Conference on Robotics and Automation, ICRA 2005, pp. 4630–4635 (2005)
MacQuuen, J.B.: Some methods for classification and analysis of multivariate observation. In: Proc. of the 5th Berkley Symposium on Mathematical Statistics and Probability, pp. 281–297 (1967)
Peters, J., Mülling, K., Kober, J., Nguyen-Tuong, D., Krömer, O.: Towards Motor Skill Learning for Robotics. In: Pradalier, C., Siegwart, R., Hirzinger, G. (eds.) Robotics Research. Springer Tracts in Advanced Robotics, vol. 70, pp. 469–482. Springer, Heidelberg (2011)
Powell, M.J.D.: The BOBYQA algorithm for bound constrained optimization without derivatives, Department of Applied Mathematics and Theoretical Physics, Cambridge England, technical report NA2009/06 (2009)
Rose, C., Cohen, M.F., Bodenheimer, B.: Verbs and adverbs: multidimensional motion interpolation. IEEE Computer Graphics and Applications 18(5), 32–40 (1998)
Safonova, A., Hodgins, J.K.: Construction and optimal search of interpolated motion graphs. ACM Transactions on Graphics 26(3) (2007)
Sidenbladh, H., Black, M.J., Sigal, L.: Implicit Probabilistic Models of Human Motion for Synthesis and Tracking. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part I. LNCS, vol. 2350, pp. 784–800. Springer, Heidelberg (2002)
Ude, A., Gams, A., Asfour, T., Morimoto, J.: Task-specific generalization of discrete and periodic dynamic movement primitives. IEEE Trans. Robotics and Autom. (5), 800–815 (2010)
Yamane, K., Yamaguchi, Y., Nakamura, Y.: Human motion database with a binary tree and node transition graphs. In: Presented at the Robot., Sci. Syst. Conf., Seattle, Washington (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Deniša, M., Ude, A. (2013). New Motor Primitives through Graph Search, Interpolation and Generalization. In: Lee, S., Yoon, KJ., Lee, J. (eds) Frontiers of Intelligent Autonomous Systems. Studies in Computational Intelligence, vol 466. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35485-4_11
Download citation
DOI: https://doi.org/10.1007/978-3-642-35485-4_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35484-7
Online ISBN: 978-3-642-35485-4
eBook Packages: EngineeringEngineering (R0)