In this section
@article{Chatzis:2012:10.1016/j.robot.2012.02.005,
author = {Chatzis, SP and Korkinof, D and Demiris, Y},
doi = {10.1016/j.robot.2012.02.005},
journal = {Robotics and Autonomous Systems},
pages = {789--802},
title = {A nonparametric Bayesian approach toward robot learning by demonstration},
url = {http://dx.doi.org/10.1016/j.robot.2012.02.005},
volume = {60},
year = {2012}
}
TY - JOUR
AB - In the past years, many authors have considered application of machine learning methodologies to effect robot learning by demonstration. Gaussian mixture regression (GMR) is one of the most successful methodologies used for this purpose. A major limitation of GMR models concerns automatic selection of the proper number of model states, i.e., the number of model component densities. Existing methods, including likelihood- or entropy-based criteria, usually tend to yield noisy model size estimates while imposing heavy computational requirements. Recently, Dirichlet process (infinite) mixture models have emerged in the cornerstone of nonparametric Bayesian statistics as promising candidates for clustering applications where the number of clusters is unknown a priori. Under this motivation, to resolve the aforementioned issues of GMR-based methods for robot learning by demonstration, in this paper we introduce a nonparametric Bayesian formulation for the GMR model, the Dirichlet process GMR model. We derive an efficient variational Bayesian inference algorithm for the proposed model, and we experimentally investigate its efficacy as a robot learning by demonstration methodology, considering a number of demanding robot learning by demonstration scenarios.
AU - Chatzis,SP
AU - Korkinof,D
AU - Demiris,Y
DO - 10.1016/j.robot.2012.02.005
EP - 802
PY - 2012///
SN - 0921-8890
SP - 789
TI - A nonparametric Bayesian approach toward robot learning by demonstration
T2 - Robotics and Autonomous Systems
UR - http://dx.doi.org/10.1016/j.robot.2012.02.005
UR - http://hdl.handle.net/10044/1/12610
VL - 60
ER -
