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 experi-
ments 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.
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 experi-
ments 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.
| Original language | English |
|---|---|
| Title of host publication | Mining intelligence and knowledge exploration |
| Subtitle of host publication | Second International Conference, MIKE 2014, Cork, Ireland, December 10-12, 2014. Proceedings |
| Place of Publication | Switzerland |
| Publisher | Springer-Verlag London Ltd. |
| Pages | 62-71 |
| Number of pages | 10 |
| Volume | 8891 |
| ISBN (Electronic) | 978-3-319-13817-6 |
| ISBN (Print) | 978-3-319-13816-9 |
| DOIs | |
| Publication status | Published - 2014 |
| Event | 2nd International Conference on Mining Intelligence and Knowledge Exploration (MIKE 2014) - Cork, Ireland, Ireland Duration: 10 Dec 2014 → 12 Dec 2014 http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=37341©ownerid=69344 |
Publication series
| Name | |
|---|---|
| ISSN (Print) | 0302-9743 |
Conference
| Conference | 2nd International Conference on Mining Intelligence and Knowledge Exploration (MIKE 2014) |
|---|---|
| Country/Territory | Ireland |
| Period | 10/12/14 → 12/12/14 |
| Internet address |