Robot Cognition using Bayesian Symmetry Networks

Anshul Joshi, Thomas C. Henderson, Wenyi Wang

2014

Abstract

(Leyton, 2001) proposes a generative theory of shape, and general cognition, based on group actions on sets as defined by wreath products. This representation relates object symmetries to motor actions which produce those symmetries. Our position expressed here is that this approach provides a strong basis for robot cognition when: 1. sensory data and motor data are tightly coupled during analysis, 2. specific instances and general concepts are structured this way, and 3. uncertainty is characterized using a Bayesian framework. Our major contributions are (1) algorithms for symmetry detection and to realize wreath product analysis, and (2) a Bayesian characterization of the uncertainty in wreath product concept formation.

Paper Citation

in Harvard Style

Joshi A., C. Henderson T. and Wang W. (2014). Robot Cognition using Bayesian Symmetry Networks . In Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-015-4, pages 696-702. DOI: 10.5220/0004920606960702

in Bibtex Style

@conference{icaart14,
author={Anshul Joshi and Thomas C. Henderson and Wenyi Wang},
title={Robot Cognition using Bayesian Symmetry Networks},
booktitle={Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2014},
pages={696-702},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004920606960702},
isbn={978-989-758-015-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Robot Cognition using Bayesian Symmetry Networks
SN - 978-989-758-015-4
AU - Joshi A.
AU - C. Henderson T.
AU - Wang W.
PY - 2014
SP - 696
EP - 702
DO - 10.5220/0004920606960702