A neurointerface with an adaptive fuzzy compensator for controlling nonholonomic mobile robots

Keigo Watanabe, Rafiuddin Syam, Kiyotaka Izumi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper describes an adaptive control for nonholonomic mobile robots, which are subjected to a suddenly changed disturbance due to the change of payloads. We adopts a control architecture based on a two-degrees-of-freedom design, where the feedforward controller is constructed by a neural network (NN) to acquire an inverse dynamical model of the robot, whereas the feedback controller is designed by two methods: one is a conventional PD compensator and the other is an adaptive fuzzy compensator. A concept of virtual master-slave robots is applied to obtain an inverse model of a nonholonomic robot. A compensator needs to be used to reduce the effect of the NN mapping errors or to suppress the effect of a sudden change of payloads. It is demonstrated by several simulations that the present approach Is effective for controlling a nonholonomic mobile robot in a navigation of trajectory tracking problem for the positions and azimuth.

Original languageEnglish
Title of host publication2005 IEEE Workshop on Advanced Robotics and its Social Impacts
Pages243-248
Number of pages6
Volume2005
DOIs
Publication statusPublished - 2005
Externally publishedYes
Event2005 IEEE Workshop on Advanced Robotics and its Social Impacts - Nagoya, Japan
Duration: Jun 12 2005Jun 15 2005

Other

Other2005 IEEE Workshop on Advanced Robotics and its Social Impacts
CountryJapan
CityNagoya
Period6/12/056/15/05

Fingerprint

Mobile robots
Robots
Neural networks
Controllers
Navigation
Trajectories
Feedback

Keywords

  • Fuzzy compensator
  • Inverse systems
  • Neural networks
  • Nonholonomic mobile robots

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Watanabe, K., Syam, R., & Izumi, K. (2005). A neurointerface with an adaptive fuzzy compensator for controlling nonholonomic mobile robots. In 2005 IEEE Workshop on Advanced Robotics and its Social Impacts (Vol. 2005, pp. 243-248). [1511659] https://doi.org/10.1109/ARSO.2005.1511659

A neurointerface with an adaptive fuzzy compensator for controlling nonholonomic mobile robots. / Watanabe, Keigo; Syam, Rafiuddin; Izumi, Kiyotaka.

2005 IEEE Workshop on Advanced Robotics and its Social Impacts. Vol. 2005 2005. p. 243-248 1511659.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Watanabe, K, Syam, R & Izumi, K 2005, A neurointerface with an adaptive fuzzy compensator for controlling nonholonomic mobile robots. in 2005 IEEE Workshop on Advanced Robotics and its Social Impacts. vol. 2005, 1511659, pp. 243-248, 2005 IEEE Workshop on Advanced Robotics and its Social Impacts, Nagoya, Japan, 6/12/05. https://doi.org/10.1109/ARSO.2005.1511659
Watanabe K, Syam R, Izumi K. A neurointerface with an adaptive fuzzy compensator for controlling nonholonomic mobile robots. In 2005 IEEE Workshop on Advanced Robotics and its Social Impacts. Vol. 2005. 2005. p. 243-248. 1511659 https://doi.org/10.1109/ARSO.2005.1511659
Watanabe, Keigo ; Syam, Rafiuddin ; Izumi, Kiyotaka. / A neurointerface with an adaptive fuzzy compensator for controlling nonholonomic mobile robots. 2005 IEEE Workshop on Advanced Robotics and its Social Impacts. Vol. 2005 2005. pp. 243-248
@inproceedings{284f68a1405c4f3698afc4d53a20e860,
title = "A neurointerface with an adaptive fuzzy compensator for controlling nonholonomic mobile robots",
abstract = "This paper describes an adaptive control for nonholonomic mobile robots, which are subjected to a suddenly changed disturbance due to the change of payloads. We adopts a control architecture based on a two-degrees-of-freedom design, where the feedforward controller is constructed by a neural network (NN) to acquire an inverse dynamical model of the robot, whereas the feedback controller is designed by two methods: one is a conventional PD compensator and the other is an adaptive fuzzy compensator. A concept of virtual master-slave robots is applied to obtain an inverse model of a nonholonomic robot. A compensator needs to be used to reduce the effect of the NN mapping errors or to suppress the effect of a sudden change of payloads. It is demonstrated by several simulations that the present approach Is effective for controlling a nonholonomic mobile robot in a navigation of trajectory tracking problem for the positions and azimuth.",
keywords = "Fuzzy compensator, Inverse systems, Neural networks, Nonholonomic mobile robots",
author = "Keigo Watanabe and Rafiuddin Syam and Kiyotaka Izumi",
year = "2005",
doi = "10.1109/ARSO.2005.1511659",
language = "English",
isbn = "0780389476",
volume = "2005",
pages = "243--248",
booktitle = "2005 IEEE Workshop on Advanced Robotics and its Social Impacts",

}

TY - GEN

T1 - A neurointerface with an adaptive fuzzy compensator for controlling nonholonomic mobile robots

AU - Watanabe, Keigo

AU - Syam, Rafiuddin

AU - Izumi, Kiyotaka

PY - 2005

Y1 - 2005

N2 - This paper describes an adaptive control for nonholonomic mobile robots, which are subjected to a suddenly changed disturbance due to the change of payloads. We adopts a control architecture based on a two-degrees-of-freedom design, where the feedforward controller is constructed by a neural network (NN) to acquire an inverse dynamical model of the robot, whereas the feedback controller is designed by two methods: one is a conventional PD compensator and the other is an adaptive fuzzy compensator. A concept of virtual master-slave robots is applied to obtain an inverse model of a nonholonomic robot. A compensator needs to be used to reduce the effect of the NN mapping errors or to suppress the effect of a sudden change of payloads. It is demonstrated by several simulations that the present approach Is effective for controlling a nonholonomic mobile robot in a navigation of trajectory tracking problem for the positions and azimuth.

AB - This paper describes an adaptive control for nonholonomic mobile robots, which are subjected to a suddenly changed disturbance due to the change of payloads. We adopts a control architecture based on a two-degrees-of-freedom design, where the feedforward controller is constructed by a neural network (NN) to acquire an inverse dynamical model of the robot, whereas the feedback controller is designed by two methods: one is a conventional PD compensator and the other is an adaptive fuzzy compensator. A concept of virtual master-slave robots is applied to obtain an inverse model of a nonholonomic robot. A compensator needs to be used to reduce the effect of the NN mapping errors or to suppress the effect of a sudden change of payloads. It is demonstrated by several simulations that the present approach Is effective for controlling a nonholonomic mobile robot in a navigation of trajectory tracking problem for the positions and azimuth.

KW - Fuzzy compensator

KW - Inverse systems

KW - Neural networks

KW - Nonholonomic mobile robots

UR - http://www.scopus.com/inward/record.url?scp=33746807742&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746807742&partnerID=8YFLogxK

U2 - 10.1109/ARSO.2005.1511659

DO - 10.1109/ARSO.2005.1511659

M3 - Conference contribution

AN - SCOPUS:33746807742

SN - 0780389476

SN - 9780780389472

VL - 2005

SP - 243

EP - 248

BT - 2005 IEEE Workshop on Advanced Robotics and its Social Impacts

ER -