Advanced

Learning Basis Skills by Autonomous Segmentation of Humanoid Motion Trajectories

Lee, Sang Hyoung; Suh, Il Hong; Calinon, Sylvain and Johansson, Rolf LU (2012) 12th IEEE-RAS International Conference on Humanoid Robots In 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2012 p.112-119
Abstract
Manipulation tasks are characterized by continuous motion trajectories containing a set of key phases. In this paper, we propose a probabilistic method to autonomously segment the motion trajectories for estimating the key phases embedded in such a task. The autonomous segmentation process relies on principal component analysis to adaptively project into one of the low-dimensional subspaces, in which a Gaussian mixture model is learned based on Bayesian information criterion and expectation-maximization algorithms. The basis skills are estimated by a set of Gaussians approximating quasi-linear key phases, and those times spent calculated from the segmentation points between two consecutive Gaussians representing the local changes of... (More)
Manipulation tasks are characterized by continuous motion trajectories containing a set of key phases. In this paper, we propose a probabilistic method to autonomously segment the motion trajectories for estimating the key phases embedded in such a task. The autonomous segmentation process relies on principal component analysis to adaptively project into one of the low-dimensional subspaces, in which a Gaussian mixture model is learned based on Bayesian information criterion and expectation-maximization algorithms. The basis skills are estimated by a set of Gaussians approximating quasi-linear key phases, and those times spent calculated from the segmentation points between two consecutive Gaussians representing the local changes of dynamics and directions of the trajectories. The basis skills are then used to build novel motion trajectories with possible motion alternatives and optional parts. After sequentially reorganizing the basis skills, a Gaussian mixture regression process is used to retrieve smooth motion trajectories. Two experiments are presented to demonstrate the capability of the autonomous segmentation approach. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
12th IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2012
pages
112 - 119
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
12th IEEE-RAS International Conference on Humanoid Robots
external identifiers
  • scopus:84887278272
ISSN
2164-0572
DOI
10.1109/HUMANOIDS.2012.6651507
project
LCCC
ROSETTA
language
English
LU publication?
yes
id
86ed12bd-6424-44bc-a9a7-19b35c6bcb20 (old id 3364978)
date added to LUP
2013-01-18 09:29:40
date last changed
2017-06-11 04:20:46
@inproceedings{86ed12bd-6424-44bc-a9a7-19b35c6bcb20,
  abstract     = {Manipulation tasks are characterized by continuous motion trajectories containing a set of key phases. In this paper, we propose a probabilistic method to autonomously segment the motion trajectories for estimating the key phases embedded in such a task. The autonomous segmentation process relies on principal component analysis to adaptively project into one of the low-dimensional subspaces, in which a Gaussian mixture model is learned based on Bayesian information criterion and expectation-maximization algorithms. The basis skills are estimated by a set of Gaussians approximating quasi-linear key phases, and those times spent calculated from the segmentation points between two consecutive Gaussians representing the local changes of dynamics and directions of the trajectories. The basis skills are then used to build novel motion trajectories with possible motion alternatives and optional parts. After sequentially reorganizing the basis skills, a Gaussian mixture regression process is used to retrieve smooth motion trajectories. Two experiments are presented to demonstrate the capability of the autonomous segmentation approach.},
  author       = {Lee, Sang Hyoung and Suh, Il Hong and Calinon, Sylvain and Johansson, Rolf},
  booktitle    = {12th IEEE-RAS International Conference on Humanoid Robots (Humanoids), 2012},
  issn         = {2164-0572},
  language     = {eng},
  pages        = {112--119},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  title        = {Learning Basis Skills by Autonomous Segmentation of Humanoid Motion Trajectories},
  url          = {http://dx.doi.org/10.1109/HUMANOIDS.2012.6651507},
  year         = {2012},
}