Multiresolutional intelligent controller for baby robot

Author

Albus, J. ; Lacaze, A. ; Meystel, A.

Author_Institution

Intelligent Syst. Div., US Dept. of Commerce, Boulder, CO, USA

fYear

1995

fDate

27-29 Aug 1995

Firstpage

203

Lastpage

208

Abstract

This paper presents an algorithm of unsupervised learning for applications in robotics. Minimum initial knowledge is presumed (“bootstrap knowledge”). The learning system uses the newly arrived information to extract rules of motion and construct the world representation. The concept of recursive generalization is explored as the main tool of rule extraction and knowledge organization. The experiment in learning is described based upon simulation of a 2D and a 3D mobile system

Keywords

generalisation (artificial intelligence); intelligent control; knowledge engineering; robots; 2D mobile system; 3D mobile system; baby robot; bootstrap knowledge; knowledge organization; minimum initial knowledge; multiresolutional intelligent controller; recursive generalization; rule extraction; unsupervised learning; world representation; Clustering algorithms; Decision making; Intelligent robots; Intelligent sensors; Intelligent systems; Learning systems; Orbital robotics; Pediatrics; Robot control; Robot sensing systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control, 1995., Proceedings of the 1995 IEEE International Symposium on

Conference_Location

Monterey, CA

ISSN

2158-9860

Print_ISBN

0-7803-2722-5

Type

conf

DOI

10.1109/ISIC.1995.525060

Filename

525060