A neural network for object recognition through sonar on a mobile robot

Author

Streilein, William W. ; Gaudiano, Paolo ; Carpenter, Gail A.

Author_Institution

Dept. of Cognitive & Neural Syst., Boston Univ., MA, USA

fYear

1998

fDate

14-17 Sep 1998

Firstpage

271

Lastpage

276

Abstract

A novel approach to sonar-based object recognition for use on an autonomous robot is described. An inexpensive Polaroid sonar, coupled with an A/D data acquisition board installed in a LINUX-based PC, provides full-echo sonar information to a fuzzy ARTMAP neural network classification system. Initial experimental results are described which illustrate recognition of five objects and generalization across distance. Findings suggest that typical indoor objects can be distinguished over a range of distances with high accuracy solely on the basis of information contained in the ultrasonic sonar echoes

Keywords

ART neural nets; analogue-digital conversion; data acquisition; fuzzy neural nets; microcomputer applications; mobile robots; neurocontrollers; object recognition; pattern classification; sonar target recognition; A/D data acquisition board; LINUX-based PC; Polaroid sonar; full-echo sonar information; fuzzy ARTMAP neural network classification system; mobile robot; sonar-based object recognition; ultrasonic sonar echoes; Data acquisition; Frequency; Fuzzy neural networks; Hardware; Laboratories; Linux; Mobile robots; Neural networks; Object recognition; Sonar detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control (ISIC), 1998. Held jointly with IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA), Intelligent Systems and Semiotics (ISAS), Proceedings

Conference_Location

Gaithersburg, MD

ISSN

2158-9860

Print_ISBN

0-7803-4423-5

Type

conf

DOI

10.1109/ISIC.1998.713673

Filename

713673