A Modified Hybrid Fuzzy Controller for Real-Time Mobile Robot Navigation

J. Hossen, S. Sayeed, A.k.m. Parvez Iqbal

Research output: Contribution to journalConference article

4 Citations (Scopus)

Abstract

The Fuzzy hybridization technique for intelligent systems have become of research interests in a variety of research areas over past the decades. There are limitations faced by all popular fuzzy systems architectures when they are applied to applications with a large number of inputs (Multi-sensors) systems. In this paper, proposes a modified hybrid fuzzy controller for multi-sensors (Large number of inputs) real-time mobile robot navigation. A modified hybrid fuzzy controller is constructed by the automatic generation of membership functions (MFs) and formed a minimal numbers of rules using hybrid fuzzy clustering algorithm (Combination of Fuzzy C-means and Subtractive clustering algorithm) and the modified apriori algorithm, respectively. The generated hybrid fuzzy controller is then adjusted by the least square method and the gradient descent algorithm towards better performance with a minimal set of rules. The performance is observed in an application for real-time mobile robot navigation has been found to be very impressive and competitive.

Original languageEnglish
Pages (from-to)449-454
Number of pages6
JournalProcedia Computer Science
Volume76
DOIs
Publication statusPublished - 01 Jan 2015
EventIEEE International Symposium on Robotics and Intelligent Sensors, IEEE IRIS 2015 - Langkawi, Malaysia
Duration: 18 Oct 201520 Oct 2015

Fingerprint

Mobile robots
Navigation
Clustering algorithms
Controllers
Sensor data fusion
Fuzzy clustering
Intelligent systems
Fuzzy systems
Membership functions
Sensors

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

@article{c22fcbf6c90f4afaaa581b062773a3c5,
title = "A Modified Hybrid Fuzzy Controller for Real-Time Mobile Robot Navigation",
abstract = "The Fuzzy hybridization technique for intelligent systems have become of research interests in a variety of research areas over past the decades. There are limitations faced by all popular fuzzy systems architectures when they are applied to applications with a large number of inputs (Multi-sensors) systems. In this paper, proposes a modified hybrid fuzzy controller for multi-sensors (Large number of inputs) real-time mobile robot navigation. A modified hybrid fuzzy controller is constructed by the automatic generation of membership functions (MFs) and formed a minimal numbers of rules using hybrid fuzzy clustering algorithm (Combination of Fuzzy C-means and Subtractive clustering algorithm) and the modified apriori algorithm, respectively. The generated hybrid fuzzy controller is then adjusted by the least square method and the gradient descent algorithm towards better performance with a minimal set of rules. The performance is observed in an application for real-time mobile robot navigation has been found to be very impressive and competitive.",
author = "J. Hossen and S. Sayeed and Iqbal, {A.k.m. Parvez}",
year = "2015",
month = "1",
day = "1",
doi = "10.1016/j.procs.2015.12.307",
language = "English",
volume = "76",
pages = "449--454",
journal = "Procedia Computer Science",
issn = "1877-0509",
publisher = "Elsevier BV",

}

A Modified Hybrid Fuzzy Controller for Real-Time Mobile Robot Navigation. / Hossen, J.; Sayeed, S.; Iqbal, A.k.m. Parvez.

In: Procedia Computer Science, Vol. 76, 01.01.2015, p. 449-454.

Research output: Contribution to journalConference article

TY - JOUR

T1 - A Modified Hybrid Fuzzy Controller for Real-Time Mobile Robot Navigation

AU - Hossen, J.

AU - Sayeed, S.

AU - Iqbal, A.k.m. Parvez

PY - 2015/1/1

Y1 - 2015/1/1

N2 - The Fuzzy hybridization technique for intelligent systems have become of research interests in a variety of research areas over past the decades. There are limitations faced by all popular fuzzy systems architectures when they are applied to applications with a large number of inputs (Multi-sensors) systems. In this paper, proposes a modified hybrid fuzzy controller for multi-sensors (Large number of inputs) real-time mobile robot navigation. A modified hybrid fuzzy controller is constructed by the automatic generation of membership functions (MFs) and formed a minimal numbers of rules using hybrid fuzzy clustering algorithm (Combination of Fuzzy C-means and Subtractive clustering algorithm) and the modified apriori algorithm, respectively. The generated hybrid fuzzy controller is then adjusted by the least square method and the gradient descent algorithm towards better performance with a minimal set of rules. The performance is observed in an application for real-time mobile robot navigation has been found to be very impressive and competitive.

AB - The Fuzzy hybridization technique for intelligent systems have become of research interests in a variety of research areas over past the decades. There are limitations faced by all popular fuzzy systems architectures when they are applied to applications with a large number of inputs (Multi-sensors) systems. In this paper, proposes a modified hybrid fuzzy controller for multi-sensors (Large number of inputs) real-time mobile robot navigation. A modified hybrid fuzzy controller is constructed by the automatic generation of membership functions (MFs) and formed a minimal numbers of rules using hybrid fuzzy clustering algorithm (Combination of Fuzzy C-means and Subtractive clustering algorithm) and the modified apriori algorithm, respectively. The generated hybrid fuzzy controller is then adjusted by the least square method and the gradient descent algorithm towards better performance with a minimal set of rules. The performance is observed in an application for real-time mobile robot navigation has been found to be very impressive and competitive.

UR - http://www.scopus.com/inward/record.url?scp=84962809864&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962809864&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2015.12.307

DO - 10.1016/j.procs.2015.12.307

M3 - Conference article

VL - 76

SP - 449

EP - 454

JO - Procedia Computer Science

JF - Procedia Computer Science

SN - 1877-0509

ER -