Non-conventional integration of the fundamental elements of soft computing and traditional methods in adaptive robot control

J. Tar, I. Rudas, J. F. Bito, K. Kozlowski

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

Abstract

Traditional fuzzy controllers or artificial neural networks are constrained by standardized formal procedures and structural restrictions. While in general it is guaranteed that these approaches or their integration can solve a quite wide class of problems, their 'orthodox' application may result in too complicated control not exploiting the peculiarities of the given task under consideration. The aim of this paper is to demonstrate that via non-conventional integration of simple elements as classic PID/ST, regression analysis, saturated sigmoid transition functions, fuzzy sets and uniform structures obtained from the Lagrangian Classical Mechanics instead of the connection structure of a feedforward artificial neural networks can result in a simple and efficient adaptive control for robots involved in unknown environmental dynamic interaction. Due to their simplicity and reduced number of parameters real time tuning can be carried out in these structures. Most of the parameters is independent of the particular problem to be solved and neither 'scaling problems' nor 'network paralysis' occur during the learning phase. It is concluded that the different components of the control can successfully co-operate in finding the 'proper' system model even in the case of very rough initial model estimation and external interaction.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
Pages3531-3536
Number of pages6
Volume4
Publication statusPublished - 2000
EventICRA 2000: IEEE International Conference on Robotics and Automation - San Francisco, CA, USA
Duration: Apr 24 2000Apr 28 2000

Other

OtherICRA 2000: IEEE International Conference on Robotics and Automation
CitySan Francisco, CA, USA
Period4/24/004/28/00

Fingerprint

Intelligent robots
Soft computing
Neural networks
Fuzzy sets
Regression analysis
Mechanics
Tuning
Robots
Controllers

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering

Cite this

Tar, J., Rudas, I., Bito, J. F., & Kozlowski, K. (2000). Non-conventional integration of the fundamental elements of soft computing and traditional methods in adaptive robot control. In Proceedings - IEEE International Conference on Robotics and Automation (Vol. 4, pp. 3531-3536)

Non-conventional integration of the fundamental elements of soft computing and traditional methods in adaptive robot control. / Tar, J.; Rudas, I.; Bito, J. F.; Kozlowski, K.

Proceedings - IEEE International Conference on Robotics and Automation. Vol. 4 2000. p. 3531-3536.

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

Tar, J, Rudas, I, Bito, JF & Kozlowski, K 2000, Non-conventional integration of the fundamental elements of soft computing and traditional methods in adaptive robot control. in Proceedings - IEEE International Conference on Robotics and Automation. vol. 4, pp. 3531-3536, ICRA 2000: IEEE International Conference on Robotics and Automation, San Francisco, CA, USA, 4/24/00.
Tar J, Rudas I, Bito JF, Kozlowski K. Non-conventional integration of the fundamental elements of soft computing and traditional methods in adaptive robot control. In Proceedings - IEEE International Conference on Robotics and Automation. Vol. 4. 2000. p. 3531-3536
Tar, J. ; Rudas, I. ; Bito, J. F. ; Kozlowski, K. / Non-conventional integration of the fundamental elements of soft computing and traditional methods in adaptive robot control. Proceedings - IEEE International Conference on Robotics and Automation. Vol. 4 2000. pp. 3531-3536
@inproceedings{161016beb6a142399a5775a87d97fd12,
title = "Non-conventional integration of the fundamental elements of soft computing and traditional methods in adaptive robot control",
abstract = "Traditional fuzzy controllers or artificial neural networks are constrained by standardized formal procedures and structural restrictions. While in general it is guaranteed that these approaches or their integration can solve a quite wide class of problems, their 'orthodox' application may result in too complicated control not exploiting the peculiarities of the given task under consideration. The aim of this paper is to demonstrate that via non-conventional integration of simple elements as classic PID/ST, regression analysis, saturated sigmoid transition functions, fuzzy sets and uniform structures obtained from the Lagrangian Classical Mechanics instead of the connection structure of a feedforward artificial neural networks can result in a simple and efficient adaptive control for robots involved in unknown environmental dynamic interaction. Due to their simplicity and reduced number of parameters real time tuning can be carried out in these structures. Most of the parameters is independent of the particular problem to be solved and neither 'scaling problems' nor 'network paralysis' occur during the learning phase. It is concluded that the different components of the control can successfully co-operate in finding the 'proper' system model even in the case of very rough initial model estimation and external interaction.",
author = "J. Tar and I. Rudas and Bito, {J. F.} and K. Kozlowski",
year = "2000",
language = "English",
volume = "4",
pages = "3531--3536",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

}

TY - GEN

T1 - Non-conventional integration of the fundamental elements of soft computing and traditional methods in adaptive robot control

AU - Tar, J.

AU - Rudas, I.

AU - Bito, J. F.

AU - Kozlowski, K.

PY - 2000

Y1 - 2000

N2 - Traditional fuzzy controllers or artificial neural networks are constrained by standardized formal procedures and structural restrictions. While in general it is guaranteed that these approaches or their integration can solve a quite wide class of problems, their 'orthodox' application may result in too complicated control not exploiting the peculiarities of the given task under consideration. The aim of this paper is to demonstrate that via non-conventional integration of simple elements as classic PID/ST, regression analysis, saturated sigmoid transition functions, fuzzy sets and uniform structures obtained from the Lagrangian Classical Mechanics instead of the connection structure of a feedforward artificial neural networks can result in a simple and efficient adaptive control for robots involved in unknown environmental dynamic interaction. Due to their simplicity and reduced number of parameters real time tuning can be carried out in these structures. Most of the parameters is independent of the particular problem to be solved and neither 'scaling problems' nor 'network paralysis' occur during the learning phase. It is concluded that the different components of the control can successfully co-operate in finding the 'proper' system model even in the case of very rough initial model estimation and external interaction.

AB - Traditional fuzzy controllers or artificial neural networks are constrained by standardized formal procedures and structural restrictions. While in general it is guaranteed that these approaches or their integration can solve a quite wide class of problems, their 'orthodox' application may result in too complicated control not exploiting the peculiarities of the given task under consideration. The aim of this paper is to demonstrate that via non-conventional integration of simple elements as classic PID/ST, regression analysis, saturated sigmoid transition functions, fuzzy sets and uniform structures obtained from the Lagrangian Classical Mechanics instead of the connection structure of a feedforward artificial neural networks can result in a simple and efficient adaptive control for robots involved in unknown environmental dynamic interaction. Due to their simplicity and reduced number of parameters real time tuning can be carried out in these structures. Most of the parameters is independent of the particular problem to be solved and neither 'scaling problems' nor 'network paralysis' occur during the learning phase. It is concluded that the different components of the control can successfully co-operate in finding the 'proper' system model even in the case of very rough initial model estimation and external interaction.

UR - http://www.scopus.com/inward/record.url?scp=0033718126&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033718126&partnerID=8YFLogxK

M3 - Conference contribution

VL - 4

SP - 3531

EP - 3536

BT - Proceedings - IEEE International Conference on Robotics and Automation

ER -