Abstract
Convergence problems can occur in some practical situations when using Gaussian Mixture Model (GMM) based robot Learning from Demonstration (LfD). Theoretically, Expectation Maximization (EM) is a good technique for the estimation of parameters for GMM, but can suffer problems when used in a practical situation. The contribution of this paper is a more complete analysis of the theoretical problem which arise in a particular experiment. The research question that is answered in this paper is how can a partial solution be found for such practical problem. Simulation results and practical results for laboratory experiments verify the theoretical analysis. The two issues covered are repeated sampling on other models and the influence of outliers (abnormal data) on the policy/kernel generation in GMM LfD. Moreover, an analysis of the impact of repeated samples to the CHMM, and experimental results are also presented.
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
Ge, F., Moore, W., Antolovich, M., Gao, J.: Application of learning from demonstration to a mining tunnel inspection robot. In: 2011 First International Conference on Robot, Vision and Signal Processing (RVSP), pp. 32–35. IEEE (2011)
Archambeau, C., Lee, J.A., Verleysen, M.: On convergence problems of the em algorithm for finite gaussian mixtures. In: Proc. 11th European Symposium on Artificial Neural Networks, pp. 99–106 (2003)
Bilmes, J.: A gentle tutorial of the em algorithm and its application to parameter estimation for gaussian mixture and hidden markov models. Technical report (1998)
Neumaier, A.: Solving ill-conditioned and singular linear systems: A tutorial on regularization. SIAM Review 40, 636–666 (1998)
O’Dowd, R.J.: Ill-conditioning and pre-whitening in seismic deconvolution. Geophysical Journal International 101(2), 489–491 (1990)
Movellan, J.R.: Tutorial on Hidden Markov Models (2003), http://mplab.ucsd.edu/tutorials/hmm.pdf
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Ge, F., Moore, W., Antolovich, M. (2014). Convergence Problem in GMM Related Robot Learning from Demonstration. In: Prasath, R., O’Reilly, P., Kathirvalavakumar, T. (eds) Mining Intelligence and Knowledge Exploration. Lecture Notes in Computer Science(), vol 8891. Springer, Cham. https://doi.org/10.1007/978-3-319-13817-6_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-13817-6_7
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13816-9
Online ISBN: 978-3-319-13817-6
eBook Packages: Computer ScienceComputer Science (R0)