Neural network-based kinematic inversion of industrial redundant robots using cooperative fuzzy hint for the joint limits avoidance

Samy F M Assal, Keigo Watanabe, Kiyotaka Izumi

Research output: Contribution to journalArticle

33 Citations (Scopus)

Abstract

In this paper, a neural network (NN)-based inverse kinematics problem of redundant manipulators subject to joint limits is presented. The Widrow-Hoff NN with an adaptive learning algorithm derived by applying Lyapunov stability theory is introduced. Since the inverse kinematics has an infinite number of joint angle vectors, a fuzzy neural network (FNN) is designed to provide an approximate value for that vector. This vector is fed into the NN as a hint input vector to guide the output of the NN within the self motion. This FNN is designed on the basis of cooperatively controlling each joint angle in the sense that it stops the motion on the critical axis at its limit at the expense of greater compensation from the most relaxed joint to accomplish the task. Physical constraints such as the joint velocity limits as well as the joint angle limits are incorporated into the method. Experiments are conducted for the PA-10 redundant manipulator to show the effectiveness of the proposed control system. A comparative study is carried out with the gradient projection method.

Original languageEnglish
Pages (from-to)593-603
Number of pages11
JournalIEEE/ASME Transactions on Mechatronics
Volume11
Issue number5
DOIs
Publication statusPublished - Oct 2006
Externally publishedYes

Fingerprint

Kinematics
Robots
Redundant manipulators
Neural networks
Inverse kinematics
Fuzzy neural networks
Adaptive algorithms
Learning algorithms
Control systems
Experiments

Keywords

  • Fuzzy neural network (FNN)
  • Inverse kinematics
  • Joint limits avoidance
  • Neural network (NN)
  • Redundant manipulators

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering
  • Mechanical Engineering

Cite this

Neural network-based kinematic inversion of industrial redundant robots using cooperative fuzzy hint for the joint limits avoidance. / Assal, Samy F M; Watanabe, Keigo; Izumi, Kiyotaka.

In: IEEE/ASME Transactions on Mechatronics, Vol. 11, No. 5, 10.2006, p. 593-603.

Research output: Contribution to journalArticle

@article{6768ed1263ce4e519e38e9929606c493,
title = "Neural network-based kinematic inversion of industrial redundant robots using cooperative fuzzy hint for the joint limits avoidance",
abstract = "In this paper, a neural network (NN)-based inverse kinematics problem of redundant manipulators subject to joint limits is presented. The Widrow-Hoff NN with an adaptive learning algorithm derived by applying Lyapunov stability theory is introduced. Since the inverse kinematics has an infinite number of joint angle vectors, a fuzzy neural network (FNN) is designed to provide an approximate value for that vector. This vector is fed into the NN as a hint input vector to guide the output of the NN within the self motion. This FNN is designed on the basis of cooperatively controlling each joint angle in the sense that it stops the motion on the critical axis at its limit at the expense of greater compensation from the most relaxed joint to accomplish the task. Physical constraints such as the joint velocity limits as well as the joint angle limits are incorporated into the method. Experiments are conducted for the PA-10 redundant manipulator to show the effectiveness of the proposed control system. A comparative study is carried out with the gradient projection method.",
keywords = "Fuzzy neural network (FNN), Inverse kinematics, Joint limits avoidance, Neural network (NN), Redundant manipulators",
author = "Assal, {Samy F M} and Keigo Watanabe and Kiyotaka Izumi",
year = "2006",
month = "10",
doi = "10.1109/TMECH.2006.882991",
language = "English",
volume = "11",
pages = "593--603",
journal = "IEEE/ASME Transactions on Mechatronics",
issn = "1083-4435",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - Neural network-based kinematic inversion of industrial redundant robots using cooperative fuzzy hint for the joint limits avoidance

AU - Assal, Samy F M

AU - Watanabe, Keigo

AU - Izumi, Kiyotaka

PY - 2006/10

Y1 - 2006/10

N2 - In this paper, a neural network (NN)-based inverse kinematics problem of redundant manipulators subject to joint limits is presented. The Widrow-Hoff NN with an adaptive learning algorithm derived by applying Lyapunov stability theory is introduced. Since the inverse kinematics has an infinite number of joint angle vectors, a fuzzy neural network (FNN) is designed to provide an approximate value for that vector. This vector is fed into the NN as a hint input vector to guide the output of the NN within the self motion. This FNN is designed on the basis of cooperatively controlling each joint angle in the sense that it stops the motion on the critical axis at its limit at the expense of greater compensation from the most relaxed joint to accomplish the task. Physical constraints such as the joint velocity limits as well as the joint angle limits are incorporated into the method. Experiments are conducted for the PA-10 redundant manipulator to show the effectiveness of the proposed control system. A comparative study is carried out with the gradient projection method.

AB - In this paper, a neural network (NN)-based inverse kinematics problem of redundant manipulators subject to joint limits is presented. The Widrow-Hoff NN with an adaptive learning algorithm derived by applying Lyapunov stability theory is introduced. Since the inverse kinematics has an infinite number of joint angle vectors, a fuzzy neural network (FNN) is designed to provide an approximate value for that vector. This vector is fed into the NN as a hint input vector to guide the output of the NN within the self motion. This FNN is designed on the basis of cooperatively controlling each joint angle in the sense that it stops the motion on the critical axis at its limit at the expense of greater compensation from the most relaxed joint to accomplish the task. Physical constraints such as the joint velocity limits as well as the joint angle limits are incorporated into the method. Experiments are conducted for the PA-10 redundant manipulator to show the effectiveness of the proposed control system. A comparative study is carried out with the gradient projection method.

KW - Fuzzy neural network (FNN)

KW - Inverse kinematics

KW - Joint limits avoidance

KW - Neural network (NN)

KW - Redundant manipulators

UR - http://www.scopus.com/inward/record.url?scp=33750419780&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750419780&partnerID=8YFLogxK

U2 - 10.1109/TMECH.2006.882991

DO - 10.1109/TMECH.2006.882991

M3 - Article

VL - 11

SP - 593

EP - 603

JO - IEEE/ASME Transactions on Mechatronics

JF - IEEE/ASME Transactions on Mechatronics

SN - 1083-4435

IS - 5

ER -