Grasping is one of the most important abilities needed for future service robots. Given the task of picking up an object from betweem clutter, traditional robotics approaches would determine a suitable grasping point and then use a movement planner to reach the goal. The planner would require precise and accurate information about the environment and long computation times, both of which may not always be available. Therefore, methods for executing grasps are required, which perform well with information gathered from only standard stereo vision, and make only a few necessary assumptions about the task environment. We propose techniques that reactively modify the robots learned motor primitives based on information derived from Early Cognitive Vision descriptors. The proposed techniques employ non-parametric potential fields centered on the Early Cognitive Vision descriptors to allow for curving hand trajectories around objects, and finger motions that adapt to the objects local geometry. The methods were tested on a real robot and found to allow for easier imitation learning of human movements and give a considerable improvement to the robots performance in grasping tasks.
| Author(s): | Kroemer, O. and Detry, R. and Piater, J. and Peters, J. |
| Journal: | Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics (ICINCO 2010) |
| Pages: | 47-54 |
| Year: | 2010 |
| Month: | June |
| Day: | 0 |
| Editors: | Filipe, J. , J. Andrade-Cetto, J.-L. Ferrier |
| Publisher: | SciTePress |
| Bibtex Type: | Conference Paper (inproceedings) |
| Address: | Lisboa, Portugal |
| Event Name: | 7th International Conference on Informatics in Control, Automation and Robotics (ICINCO 2010) |
| Event Place: | Funchal, Madeira, Portugal |
| Digital: | 0 |
| Electronic Archiving: | grant_archive |
| ISBN: | 978-989-8425-01-0 |
| Language: | en |
| Organization: | Max-Planck-Gesellschaft |
| School: | Biologische Kybernetik |
| Links: | |
BibTex
@inproceedings{6436,
title = {Grasping with Vision Descriptors and Motor Primitives},
journal = {Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics (ICINCO 2010)},
abstract = {Grasping is one of the most important abilities needed for future service robots. Given the task of picking up
an object from betweem clutter, traditional robotics approaches would determine a suitable grasping point and
then use a movement planner to reach the goal. The planner would require precise and accurate information
about the environment and long computation times, both of which may not always be available. Therefore,
methods for executing grasps are required, which perform well with information gathered from only standard
stereo vision, and make only a few necessary assumptions about the task environment. We propose techniques
that reactively modify the robots learned motor primitives based on information derived from Early Cognitive
Vision descriptors. The proposed techniques employ non-parametric potential fields centered on the Early
Cognitive Vision descriptors to allow for curving hand trajectories around objects, and finger motions that
adapt to the objects local geometry. The methods were tested on a real robot and found to allow for easier
imitation learning of human movements and give a considerable improvement to the robots performance in
grasping tasks.},
pages = {47-54},
editors = {Filipe, J. , J. Andrade-Cetto, J.-L. Ferrier},
publisher = {SciTePress },
organization = {Max-Planck-Gesellschaft},
school = {Biologische Kybernetik},
address = {Lisboa, Portugal},
month = jun,
year = {2010},
slug = {6436},
author = {Kroemer, O. and Detry, R. and Piater, J. and Peters, J.},
month_numeric = {6}
}