• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Peggy Fidelman and Peter Stone.
Learning Ball Acquisition on a Physical Robot. In 2004 International Symposium on Robotics and Automation (ISRA),
August 2004.
ISRA 2004
Some videos
of the robot referenced in the paper.
[PDF]103.6kB [postscript]1.4MB
For a robot to learn to improve its performance based entirely on real-world environmental feedback, the robot's behavior specification and learning algorithm must be constructed so as to enable data-efficient learning. Building upon previous work enabling a quadrupedal robot to learn a fast walk with all of the training done on the physical robot and with no human intervention \citeAAAI04, we demonstrate the ability of the same robot to learn a more high-level, goal-oriented task using the same methodology. In particular, we enable the robot to learn to capture (or ``grasp'') a ball. The learning occurs over about three hours of robot run time and generates a behavior that is significantly better than a baseline hand-coded behavior. Our method is fully implemented and tested on a Sony Aibo ERS-7 robot.
@InProceedings(ISRA2004-chinpinch, author="Peggy Fidelman and Peter Stone", title="Learning Ball Acquisition on a Physical Robot", booktitle="2004 International Symposium on Robotics and Automation (ISRA)", month="August",year="2004", abstract={ For a robot to learn to improve its performance based entirely on real-world environmental feedback, the robot's behavior specification and learning algorithm must be constructed so as to enable data-efficient learning. Building upon previous work enabling a quadrupedal robot to learn a fast walk with all of the training done on the physical robot and with no human intervention~\cite{AAAI04}, we demonstrate the ability of the same robot to learn a more high-level, goal-oriented task using the same methodology. In particular, we enable the robot to learn to \emph{capture} (or ``grasp'') a ball. The learning occurs over about three hours of robot run time and generates a behavior that is significantly better than a baseline hand-coded behavior. Our method is fully implemented and tested on a Sony Aibo ERS-7 robot. }, wwwnote={<a href="http://www.mecamex.net/isra/">ISRA 2004</a><br>Some <a href="http://www.cs.utexas.edu/users/AustinVilla/legged/learned-acquisition/">videos of the robot</a> referenced in the paper.}, bit2html_ignore=1 )
Generated by bib2html.pl (written by Patrick Riley ) on Thu May 04, 2006 22:25:16