|
Freek Stulp, Andreas Fedrizzi, and Michael Beetz. Action-Related Place-Based Mobile Manipulation. In International Conference
on Intelligent Robots and Systems (IROS), 2009.
|
|
|
[PDF]1.9MB
|
|
|
In mobile manipulation, the position to which the robot navigates has a large influence on the ease with which a subsequent
manipulation action can be performed. Whether a manipulation action succeeds depends on many factors, such as the robot's
hardware configuration, the controllers the robot uses to achieve navigation and manipulation, the task context, and uncertainties
in state estimation. In this paper, we present `\arpplace', an action-related place which takes these factors, and the context
in which the actions are performed into account. Through experience-based learning, the robot first learns a so-called generalized
success model, which discerns between positions from which manipulation succeeds or fails. On-line, this model is used
to compute a \arpplace, a probability distribution that maps positions to a predicted probability of successful manipulation,
and takes the uncertainty in the robot and object's position into account. In an empirical evaluation, we demonstrate that
using \arpplaces for least-commitment navigation improves the success rate of subsequent manipulation tasks substantially.
|
|
|
@InProceedings{stulp09actionrelated,
title = {Action-Related Place-Based Mobile Manipulation},
author = {Freek Stulp and Andreas Fedrizzi and Michael Beetz},
booktitle = {International Conference on Intelligent Robots and Systems (IROS)},
year = {2009},
abstract = {In mobile manipulation, the position to which the robot navigates has a large influence on the ease with which a subsequent manipulation action can be performed. Whether a manipulation action succeeds depends on many factors, such as the robot's hardware configuration, the controllers the robot uses to achieve navigation and manipulation, the task context, and uncertainties in state estimation. In this paper, we present `\arpplace', an action-related place which takes these factors, and the context in which the actions are performed into account. Through experience-based learning, the robot first learns a so-called \emph{generalized success model}, which discerns between positions from which manipulation succeeds or fails. On-line, this model is used to compute a \arpplace, a probability distribution that maps positions to a predicted probability of successful manipulation, and takes the uncertainty in the robot and object's position into account. In an empirical evaluation, we demonstrate that using \arpplace{}s for least-commitment navigation improves the success rate of subsequent manipulation tasks substantially. },
bib2html_pubtype = {Refereed Conference Paper},
bib2html_rescat = {Action-Related Places for Mobile Manipulation}
}
|
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein
are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the
terms and constraints.
Generated by
bib2html.pl
(written by Patrick Riley
) on
Mon Jul 20, 2015 21:50:11 |