Peter Stone's Selected Publications

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


Towards Autonomous Sensor and Actuator Model Induction on a Mobile Robot

Daniel Stronger and Peter Stone. Towards Autonomous Sensor and Actuator Model Induction on a Mobile Robot. Connection Science, 18(2):97–119, 2006. Special Issue on Developmental Robotics.
Connection Science Journal. Contains material that was previously published in an ICRA-2005 paper.

Download

[PDF]372.6kB  [postscript]1.4MB  

Abstract

This article presents a novel methodology for a robot to autonomously induce models of its actions and sensors called ASAMI (Autonomous Sensor and Actuator Model Induction). While previous approaches to model learning rely on an independent source of training data, we show how a robot can induce action and sensor models without any well-calibrated feedback. Specifically, the only inputs to the ASAMI learning process are the data the robot would naturally have access to: its raw sensations and knowledge of its own action selections. From the perspective of developmental robotics, our robot's goal is to obtain self-consistent internal models, rather than to perform any externally defined tasks. Furthermore, the target function of each model-learning process comes from within the system, namely the most current version of another internal system model. Concretely realizing this model-learning methodology presents a number of challenges, and we introduce a broad class of settings in which solutions to these challenges are presented. ASAMI is fully implemented and tested, and empirical results validate our approach in a robotic testbed domain using a Sony Aibo ERS-7 robot.

BibTeX Entry

@Article{CSJ06,
	Author="Daniel Stronger and Peter Stone",
	title="Towards Autonomous Sensor and Actuator Model Induction on a Mobile Robot",
	journal="Connection Science",
	note="Special Issue on Developmental Robotics.",
	volume="18",number="2",year="2006",
	pages="97--119",
	abstract={
	          This article presents a novel methodology for a
	          robot to autonomously induce models of its actions
	          and sensors called ASAMI (Autonomous Sensor and
	          Actuator Model Induction).  While previous
	          approaches to model learning rely on an independent
	          source of training data, we show how a robot can
	          induce action and sensor models without any
	          well-calibrated feedback.  Specifically, the only
	          inputs to the ASAMI learning process are the data
	          the robot would naturally have access to: its raw
	          sensations and knowledge of its own action
	          selections.  From the perspective of developmental
	          robotics, our robot's goal is to obtain
	          self-consistent internal models, rather than to
	          perform any externally defined tasks.  Furthermore,
	          the target function of each model-learning process
	          comes from within the system, namely the most
	          current version of another internal system model.
	          Concretely realizing this model-learning methodology
	          presents a number of challenges, and we introduce a
	          broad class of settings in which solutions to these
	          challenges are presented.  ASAMI is fully
	          implemented and tested, and empirical results
	          validate our approach in a robotic testbed domain
	          using a Sony Aibo ERS-7 robot.
                 },
	wwwnote={<a href="http://www.tandf.co.uk/journals/titles/09540091.asp">Connection Science Journal</a>. Contains material that was previously published in an <a href="http://www.cs.utexas.edu/~pstone/Papers/2005icra/actsense.pdf">ICRA-2005 paper</a>.},
}	

Generated by bib2html.pl (written by Patrick Riley ) on Wed Mar 05, 2014 13:23:01