Segmenting complex movements into a sequence of primitives remains a difficult problem with many applications in the robotics and vision communities. In this work, we show how the movement segmentation problem can be reduced to a sequential movement recognition problem. To this end, we reformulate the orig-inal Dynamic Movement Primitive (DMP) formulation as a linear dynamical sys-tem with control inputs. Based on this new formulation, we develop an Expecta-tion-Maximization algorithm to estimate the duration and goal position of a par-tially observed trajectory. With the help of this algorithm and the assumption that a library of movement primitives is present, we present a movement seg-mentation framework. We illustrate the usefulness of the new DMP formulation on the two applications of online movement recognition and movement segmen-tation.
| Author(s): | Meier, F. and Theodorou, E. and Stulp, F. and Schaal, S. |
| Book Title: | IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011) |
| Year: | 2011 |
| BibTeX Type: | Conference Paper (inproceedings) |
| Address: | Sept. 25-30, San Francisco, CA |
| URL: | http://www-clmc.usc.edu/publications/M/meier-IROS2011 |
| Cross Ref: | p10480 |
| Electronic Archiving: | grant_archive |
| Note: | clmc |
BibTeX
@inproceedings{Meier_IICIRS_2011,
title = {Movement segmentation using a primitive library},
booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011)},
abstract = {Segmenting complex movements into a sequence of primitives remains a difficult problem with many applications in the robotics and vision communities. In this work, we show how the movement segmentation problem can be reduced to a sequential movement recognition problem. To this end, we reformulate the orig-inal Dynamic Movement Primitive (DMP) formulation as a linear dynamical sys-tem with control inputs. Based on this new formulation, we develop an Expecta-tion-Maximization algorithm to estimate the duration and goal position of a par-tially observed trajectory. With the help of this algorithm and the assumption that a library of movement primitives is present, we present a movement seg-mentation framework. We illustrate the usefulness of the new DMP formulation on the two applications of online movement recognition and movement segmen-tation.},
address = {Sept. 25-30, San Francisco, CA},
year = {2011},
note = {clmc},
author = {Meier, F. and Theodorou, E. and Stulp, F. and Schaal, S.},
crossref = {p10480},
url = {http://www-clmc.usc.edu/publications/M/meier-IROS2011}
}