LEARNING HIGH-LEVEL BEHAVIORS FROM DEMONSTRATION THROUGH SEMANTIC NETWORKS

Benjamin Fonooni, Thomas Hellström, Lars-Erik Janlert

2012

Abstract

In this paper we present an approach for high-level behavior recognition and selection integrated with a low-level controller to help the robot to learn new skills from demonstrations. By means of Semantic Network as the core of the method, the robot gains the ability to model the world with concepts and relate them to low-level sensory-motor states. We also show how the generalization ability of Semantic Networks can be used to extend learned skills to new situations.

Paper Citation

in Harvard Style

Fonooni B., Hellström T. and Janlert L. (2012). LEARNING HIGH-LEVEL BEHAVIORS FROM DEMONSTRATION THROUGH SEMANTIC NETWORKS . In Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-8425-95-9, pages 419-426. DOI: 10.5220/0003834304190426

in Bibtex Style

@conference{icaart12,
author={Benjamin Fonooni and Thomas Hellström and Lars-Erik Janlert},
title={LEARNING HIGH-LEVEL BEHAVIORS FROM DEMONSTRATION THROUGH SEMANTIC NETWORKS},
booktitle={Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2012},
pages={419-426},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003834304190426},
isbn={978-989-8425-95-9},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - LEARNING HIGH-LEVEL BEHAVIORS FROM DEMONSTRATION THROUGH SEMANTIC NETWORKS
SN - 978-989-8425-95-9
AU - Fonooni B.
AU - Hellström T.
AU - Janlert L.
PY - 2012
SP - 419
EP - 426
DO - 10.5220/0003834304190426