A ROBOTIC PLATFORM FOR AUTONOMY STUDIES

Sergio Ribeiro Augusto, Ademar Ferreira

2007

Abstract

This paper describes a mobile robotic platform and a software framework for applications and development of robotic experiments integrating teleoperation and autonomy. An application using supervised learning is developed in which the agent is trained by teleoperation. This allows the agent to learn the perception to action mapping from the teleoperator in real time, such that the task can be repeated in an autonomous way, with some generalization. A radial basis function network (RBF) trained by a sequential learning algorithm is used to learn the mapping. Experimental results are shown.

Paper Citation

in Harvard Style

Ribeiro Augusto S. and Ferreira A. (2007). A ROBOTIC PLATFORM FOR AUTONOMY STUDIES . In Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO, ISBN 978-972-8865-83-2, pages 390-395. DOI: 10.5220/0001622603900395

in Bibtex Style

@conference{icinco07,
author={Sergio Ribeiro Augusto and Ademar Ferreira},
title={A ROBOTIC PLATFORM FOR AUTONOMY STUDIES},
booktitle={Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO,},
year={2007},
pages={390-395},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001622603900395},
isbn={978-972-8865-83-2},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO,
TI - A ROBOTIC PLATFORM FOR AUTONOMY STUDIES
SN - 978-972-8865-83-2
AU - Ribeiro Augusto S.
AU - Ferreira A.
PY - 2007
SP - 390
EP - 395
DO - 10.5220/0001622603900395