Neural network learning from hint for the inverse kinematics problem of redundant arm subject to joint limits

Samy F M Assal, Keigo Watanabe, Kiyotaka Izumi

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

15 Citations (Scopus)

Abstract

A novel online inverse kinematics solution of redundant manipulator to avoid joint limits is presented. A Widrow-Hoff neural network (NN) with a learning algorithm derived by applying Lyapunov approach is introduced for this problem. Since the inverse kinematics has 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 based on cooperatively controlling each joint angle of the manipulator. The joint velocity limits as well as the joint limits are incorporated into this method. Experiments are conducted for the PA-10 redundant arm to demonstrate the efficacy of the proposed control system. A comparative study is made with the gradient projection method.

Original languageEnglish
Title of host publication2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
Pages821-826
Number of pages6
DOIs
Publication statusPublished - 2005
Externally publishedYes
EventIEEE IRS/RSJ International Conference on Intelligent Robots and Systems, IROS 2005 - Edmonton, AB, Canada
Duration: Aug 2 2005Aug 6 2005

Other

OtherIEEE IRS/RSJ International Conference on Intelligent Robots and Systems, IROS 2005
CountryCanada
CityEdmonton, AB
Period8/2/058/6/05

Fingerprint

Inverse kinematics
Neural networks
Fuzzy neural networks
Redundant manipulators
Learning algorithms
Manipulators
Control systems
Experiments

Keywords

  • Fuzzy neural network
  • Inverse kinematics
  • Joint limits avoidance
  • Neural network
  • Redundant manipulators

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Control and Systems Engineering

Cite this

Assal, S. F. M., Watanabe, K., & Izumi, K. (2005). Neural network learning from hint for the inverse kinematics problem of redundant arm subject to joint limits. In 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS (pp. 821-826). [1545082] https://doi.org/10.1109/IROS.2005.1545082

Neural network learning from hint for the inverse kinematics problem of redundant arm subject to joint limits. / Assal, Samy F M; Watanabe, Keigo; Izumi, Kiyotaka.

2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. 2005. p. 821-826 1545082.

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

Assal, SFM, Watanabe, K & Izumi, K 2005, Neural network learning from hint for the inverse kinematics problem of redundant arm subject to joint limits. in 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS., 1545082, pp. 821-826, IEEE IRS/RSJ International Conference on Intelligent Robots and Systems, IROS 2005, Edmonton, AB, Canada, 8/2/05. https://doi.org/10.1109/IROS.2005.1545082
Assal SFM, Watanabe K, Izumi K. Neural network learning from hint for the inverse kinematics problem of redundant arm subject to joint limits. In 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. 2005. p. 821-826. 1545082 https://doi.org/10.1109/IROS.2005.1545082
Assal, Samy F M ; Watanabe, Keigo ; Izumi, Kiyotaka. / Neural network learning from hint for the inverse kinematics problem of redundant arm subject to joint limits. 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. 2005. pp. 821-826
@inproceedings{a7cfba030a134b9e8dcf035a98f46a86,
title = "Neural network learning from hint for the inverse kinematics problem of redundant arm subject to joint limits",
abstract = "A novel online inverse kinematics solution of redundant manipulator to avoid joint limits is presented. A Widrow-Hoff neural network (NN) with a learning algorithm derived by applying Lyapunov approach is introduced for this problem. Since the inverse kinematics has 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 based on cooperatively controlling each joint angle of the manipulator. The joint velocity limits as well as the joint limits are incorporated into this method. Experiments are conducted for the PA-10 redundant arm to demonstrate the efficacy of the proposed control system. A comparative study is made with the gradient projection method.",
keywords = "Fuzzy neural network, Inverse kinematics, Joint limits avoidance, Neural network, Redundant manipulators",
author = "Assal, {Samy F M} and Keigo Watanabe and Kiyotaka Izumi",
year = "2005",
doi = "10.1109/IROS.2005.1545082",
language = "English",
isbn = "0780389123",
pages = "821--826",
booktitle = "2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS",

}

TY - GEN

T1 - Neural network learning from hint for the inverse kinematics problem of redundant arm subject to joint limits

AU - Assal, Samy F M

AU - Watanabe, Keigo

AU - Izumi, Kiyotaka

PY - 2005

Y1 - 2005

N2 - A novel online inverse kinematics solution of redundant manipulator to avoid joint limits is presented. A Widrow-Hoff neural network (NN) with a learning algorithm derived by applying Lyapunov approach is introduced for this problem. Since the inverse kinematics has 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 based on cooperatively controlling each joint angle of the manipulator. The joint velocity limits as well as the joint limits are incorporated into this method. Experiments are conducted for the PA-10 redundant arm to demonstrate the efficacy of the proposed control system. A comparative study is made with the gradient projection method.

AB - A novel online inverse kinematics solution of redundant manipulator to avoid joint limits is presented. A Widrow-Hoff neural network (NN) with a learning algorithm derived by applying Lyapunov approach is introduced for this problem. Since the inverse kinematics has 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 based on cooperatively controlling each joint angle of the manipulator. The joint velocity limits as well as the joint limits are incorporated into this method. Experiments are conducted for the PA-10 redundant arm to demonstrate the efficacy of the proposed control system. A comparative study is made with the gradient projection method.

KW - Fuzzy neural network

KW - Inverse kinematics

KW - Joint limits avoidance

KW - Neural network

KW - Redundant manipulators

UR - http://www.scopus.com/inward/record.url?scp=79957976749&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79957976749&partnerID=8YFLogxK

U2 - 10.1109/IROS.2005.1545082

DO - 10.1109/IROS.2005.1545082

M3 - Conference contribution

SN - 0780389123

SN - 9780780389120

SP - 821

EP - 826

BT - 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS

ER -