Publications
• Sorted by Date • Classified by Publication Type • Classified by Research Category • Sorted by First Author Last Name •
Freek Stulp, Wolfram Koska, Alexis Maldonado, and Michael Beetz. Seamless Execution of Action Sequences. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2007.
Download
Abstract
One of the most notable and recognizable features of robot motion is the abrupttransitions between actions in action sequences. In contrast, humans and animalsperform sequences of actions efficiently, and with seamless transitions betweensubsequent actions. This smoothness is not a goal in itself, but a side-effectof the evolutionary optimization of other performance measures.In this paper, we argue that such jagged motion is an inevitable consequence ofthe way human designers and planners reason about abstract actions. We thenpresent subgoal refinement, a procedure that optimizes action sequences. Subgoalrefinement determines action parameters that are not relevant to why the actionwas selected, and optimizes these parameters with respect to expected executionperformance. This performance is computed using action models, which are learnedfrom observed experience. We integrate subgoal refinement in an existingplanning system, and demonstrate how requiring optimal performance causes smoothmotion in three robotic domains.
BibTeX Entry
@InProceedings{stulp07seamless,
author = {Freek Stulp and Wolfram Koska and Alexis Maldonado and Michael Beetz},
title = {Seamless Execution of Action Sequences},
booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)},
year = {2007},
bib2html_pubtype = {Refereed Conference Paper},
bib2html_rescat = {Plan-based Robot Control, Robot Learning},
bib2html_groups = {IAS,AGILO},
bib2html_funding = {AGILO},
bib2html_keywords = {},
abstract = {
One of the most notable and recognizable features of robot motion is the abrupt
transitions between actions in action sequences. In contrast, humans and animals
perform sequences of actions efficiently, and with seamless transitions between
subsequent actions. This smoothness is not a goal in itself, but a side-effect
of the evolutionary optimization of other performance measures.
In this paper, we argue that such jagged motion is an inevitable consequence of
the way human designers and planners reason about abstract actions. We then
present subgoal refinement, a procedure that optimizes action sequences. Subgoal
refinement determines action parameters that are not relevant to why the action
was selected, and optimizes these parameters with respect to expected execution
performance. This performance is computed using action models, which are learned
from observed experience. We integrate subgoal refinement in an existing
planning system, and demonstrate how requiring optimal performance causes smooth
motion in three robotic domains.
}
}
Generated by bib2html.pl (written by Patrick Riley ) on Tue Oct 23, 2007 15:49:35 UTC

















