Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Maximum Likelihood Estimation of Sensor and Action Model Functions on a Mobile Robot

Daniel Stronger and Peter Stone. Maximum Likelihood Estimation of Sensor and Action Model Functions on a Mobile Robot. In IEEE International Conference on Robotics and Automation, May 2008.
ICRA 2008

Download

[PDF]182.1kB  [postscript]902.7kB  

Abstract

In order for a mobile robot to accurately interpret its sensations and predict the effects of its actions, it must have accurate models of its sensors and actuators. These models are typically tuned manually, a brittle and laborious process. Autonomous model learning is a promising alternative to manual calibration, but previous work has assumed the presence of an accurate action or sensor model in order to train the other model. This paper presents an adaptation of the Expectation-Maximization (EM) algorithm to enable a mobile robot to learn both its action and sensor model functions, starting without an accurate version of either. The resulting algorithm is validated experimentally both on a Sony Aibo ERS-7 robot and in simulation.

BibTeX Entry

@InProceedings{ICRA08-stronger,
	author="Daniel Stronger and Peter Stone",
	title="Maximum Likelihood Estimation of Sensor and Action Model Functions on a Mobile Robot",
	booktitle="{IEEE} International Conference on Robotics and Automation",
	location="Pasadena, CA",
	month="May",
	year="2008",
	abstract="In order for a mobile robot to accurately interpret its sensations and
		predict the effects of its actions, it must have accurate models of
		its sensors and actuators.  These models are typically tuned manually,
		a brittle and laborious process.  Autonomous model learning is a
		promising alternative to manual calibration, but previous work has
		assumed the presence of an accurate action or sensor model in order to
		train the other model.  This paper presents an adaptation of the
		Expectation-Maximization (EM) algorithm to enable a mobile robot to
		learn both its action and sensor model functions, starting without an
		accurate version of either.  The resulting algorithm is validated
		experimentally both on a Sony Aibo ERS-7 robot and in simulation.",
	wwwnote={<a href="http://www.icra2008.org/">ICRA 2008</a>},
 }

Generated by bib2html.pl (written by Patrick Riley ) on Fri Aug 15, 2014 16:26:03