Exploring motion acquisition of manipulators with multiple degrees-of-redundancy using soft computing techniques

Samy F M Assal, Keigo Watanabe, Kiyotaka Izumi

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

5 Citations (Scopus)

Abstract

A back propagation neural network (NN) is presented for the inverse kinematic problem to obtain a position control system for manipulators with multiple degrees- of-redundancy, where information provided from a laser transducer at the end-effector is used for planning the trajectory. A fuzzy reasoning system is designed to generate an approximate joint angle vector, because the inverse kinematics in this problem has infinite number of solution vectors. This vector is fed into the NN as a hint input vector rather than as a training vector to limit and guide the searching space. Simulations are implemented on a four-link redundant planar manipulator to show that the present control system is capable of tracking the planned trajectory while avoiding the collision.

Original languageEnglish
Title of host publication2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Pages3086-3091
Number of pages6
Volume3
Publication statusPublished - 2004
Externally publishedYes
Event2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) - Sendai, Japan
Duration: Sep 28 2004Oct 2 2004

Other

Other2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
CountryJapan
CitySendai
Period9/28/0410/2/04

Fingerprint

Soft computing
Manipulators
Redundancy
Inverse kinematics
Trajectories
Neural networks
Control systems
Position control
End effectors
Backpropagation
Transducers
Planning
Lasers

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Assal, S. F. M., Watanabe, K., & Izumi, K. (2004). Exploring motion acquisition of manipulators with multiple degrees-of-redundancy using soft computing techniques. In 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (Vol. 3, pp. 3086-3091)

Exploring motion acquisition of manipulators with multiple degrees-of-redundancy using soft computing techniques. / Assal, Samy F M; Watanabe, Keigo; Izumi, Kiyotaka.

2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Vol. 3 2004. p. 3086-3091.

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

Assal, SFM, Watanabe, K & Izumi, K 2004, Exploring motion acquisition of manipulators with multiple degrees-of-redundancy using soft computing techniques. in 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). vol. 3, pp. 3086-3091, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Sendai, Japan, 9/28/04.
Assal SFM, Watanabe K, Izumi K. Exploring motion acquisition of manipulators with multiple degrees-of-redundancy using soft computing techniques. In 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Vol. 3. 2004. p. 3086-3091
Assal, Samy F M ; Watanabe, Keigo ; Izumi, Kiyotaka. / Exploring motion acquisition of manipulators with multiple degrees-of-redundancy using soft computing techniques. 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Vol. 3 2004. pp. 3086-3091
@inproceedings{d9b5036b64854ed993ab0f85ed1f6248,
title = "Exploring motion acquisition of manipulators with multiple degrees-of-redundancy using soft computing techniques",
abstract = "A back propagation neural network (NN) is presented for the inverse kinematic problem to obtain a position control system for manipulators with multiple degrees- of-redundancy, where information provided from a laser transducer at the end-effector is used for planning the trajectory. A fuzzy reasoning system is designed to generate an approximate joint angle vector, because the inverse kinematics in this problem has infinite number of solution vectors. This vector is fed into the NN as a hint input vector rather than as a training vector to limit and guide the searching space. Simulations are implemented on a four-link redundant planar manipulator to show that the present control system is capable of tracking the planned trajectory while avoiding the collision.",
author = "Assal, {Samy F M} and Keigo Watanabe and Kiyotaka Izumi",
year = "2004",
language = "English",
isbn = "0780384636",
volume = "3",
pages = "3086--3091",
booktitle = "2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",

}

TY - GEN

T1 - Exploring motion acquisition of manipulators with multiple degrees-of-redundancy using soft computing techniques

AU - Assal, Samy F M

AU - Watanabe, Keigo

AU - Izumi, Kiyotaka

PY - 2004

Y1 - 2004

N2 - A back propagation neural network (NN) is presented for the inverse kinematic problem to obtain a position control system for manipulators with multiple degrees- of-redundancy, where information provided from a laser transducer at the end-effector is used for planning the trajectory. A fuzzy reasoning system is designed to generate an approximate joint angle vector, because the inverse kinematics in this problem has infinite number of solution vectors. This vector is fed into the NN as a hint input vector rather than as a training vector to limit and guide the searching space. Simulations are implemented on a four-link redundant planar manipulator to show that the present control system is capable of tracking the planned trajectory while avoiding the collision.

AB - A back propagation neural network (NN) is presented for the inverse kinematic problem to obtain a position control system for manipulators with multiple degrees- of-redundancy, where information provided from a laser transducer at the end-effector is used for planning the trajectory. A fuzzy reasoning system is designed to generate an approximate joint angle vector, because the inverse kinematics in this problem has infinite number of solution vectors. This vector is fed into the NN as a hint input vector rather than as a training vector to limit and guide the searching space. Simulations are implemented on a four-link redundant planar manipulator to show that the present control system is capable of tracking the planned trajectory while avoiding the collision.

UR - http://www.scopus.com/inward/record.url?scp=14044277083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=14044277083&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780384636

VL - 3

SP - 3086

EP - 3091

BT - 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

ER -