Implementation of a neural network based visual motor control algorithm for a 7 DOF redundant manipulator

Swagat Kumar, Laxmidhar Behera

Research output: Chapter in Book/Report/Conference proceedingChapter

6 Citations (Scopus)

Abstract

This paper deals with visual-motor coordination of a 7 dof robot manipulator for pick and place applications. Three issues are dealt with in this paper - finding a feasible inverse kinematic solution without using any orientation information, resolving redundancy at position level and finally maintaining the fidelity of information during clustering process thereby increasing accuracy of inverse kinematic solution. A 3-dimensional KSOM lattice is used to locally linearize the inverse kinematic relationship. The joint angle vector is divided into two groups and their effect on end-effector position is decoupled using a concept called function decomposition. It is shown that function decomposition leads to significant improvement in accuracy of inverse kinematic solution. However, this method yields a unique inverse kinematic solution for a given target point. A concept called sub-clustering in configuration space is suggested to preserve redundancy during learning process and redundancy is resolved at position level using several criteria. Even though the training is carried out off-line, the trained network is used online to compute the required joint angle vector in only one step. The accuracy attained is better than the current state of art. The experiment is implemented in real-time and the results are found to corroborate theoretical findings. © 2008 IEEE.
Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages1344-1351
Number of pages8
DOIs
Publication statusPublished - 26 Sep 2008
Event2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence) - Hong Kong, China
Duration: 18 Jun 2008 → …

Publication series

NameProceedings of the International Joint Conference on Neural Networks

Conference

Conference2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
CountryChina
CityHong Kong
Period18/06/08 → …

Fingerprint

Redundant manipulators
Inverse kinematics
Neural networks
Redundancy
Decomposition
End effectors
Manipulators
Robots
Experiments

Cite this

Kumar, S., & Behera, L. (2008). Implementation of a neural network based visual motor control algorithm for a 7 DOF redundant manipulator. In Proceedings of the International Joint Conference on Neural Networks (pp. 1344-1351). (Proceedings of the International Joint Conference on Neural Networks). https://doi.org/10.1109/IJCNN.2008.4633972
Kumar, Swagat ; Behera, Laxmidhar. / Implementation of a neural network based visual motor control algorithm for a 7 DOF redundant manipulator. Proceedings of the International Joint Conference on Neural Networks. 2008. pp. 1344-1351 (Proceedings of the International Joint Conference on Neural Networks).
@inbook{b1354f1f39724ec78100b686a95a6d1b,
title = "Implementation of a neural network based visual motor control algorithm for a 7 DOF redundant manipulator",
abstract = "This paper deals with visual-motor coordination of a 7 dof robot manipulator for pick and place applications. Three issues are dealt with in this paper - finding a feasible inverse kinematic solution without using any orientation information, resolving redundancy at position level and finally maintaining the fidelity of information during clustering process thereby increasing accuracy of inverse kinematic solution. A 3-dimensional KSOM lattice is used to locally linearize the inverse kinematic relationship. The joint angle vector is divided into two groups and their effect on end-effector position is decoupled using a concept called function decomposition. It is shown that function decomposition leads to significant improvement in accuracy of inverse kinematic solution. However, this method yields a unique inverse kinematic solution for a given target point. A concept called sub-clustering in configuration space is suggested to preserve redundancy during learning process and redundancy is resolved at position level using several criteria. Even though the training is carried out off-line, the trained network is used online to compute the required joint angle vector in only one step. The accuracy attained is better than the current state of art. The experiment is implemented in real-time and the results are found to corroborate theoretical findings. {\circledC} 2008 IEEE.",
author = "Swagat Kumar and Laxmidhar Behera",
year = "2008",
month = "9",
day = "26",
doi = "10.1109/IJCNN.2008.4633972",
language = "English",
isbn = "9781424418213",
series = "Proceedings of the International Joint Conference on Neural Networks",
pages = "1344--1351",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

Kumar, S & Behera, L 2008, Implementation of a neural network based visual motor control algorithm for a 7 DOF redundant manipulator. in Proceedings of the International Joint Conference on Neural Networks. Proceedings of the International Joint Conference on Neural Networks, pp. 1344-1351, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China, 18/06/08. https://doi.org/10.1109/IJCNN.2008.4633972

Implementation of a neural network based visual motor control algorithm for a 7 DOF redundant manipulator. / Kumar, Swagat; Behera, Laxmidhar.

Proceedings of the International Joint Conference on Neural Networks. 2008. p. 1344-1351 (Proceedings of the International Joint Conference on Neural Networks).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Implementation of a neural network based visual motor control algorithm for a 7 DOF redundant manipulator

AU - Kumar, Swagat

AU - Behera, Laxmidhar

PY - 2008/9/26

Y1 - 2008/9/26

N2 - This paper deals with visual-motor coordination of a 7 dof robot manipulator for pick and place applications. Three issues are dealt with in this paper - finding a feasible inverse kinematic solution without using any orientation information, resolving redundancy at position level and finally maintaining the fidelity of information during clustering process thereby increasing accuracy of inverse kinematic solution. A 3-dimensional KSOM lattice is used to locally linearize the inverse kinematic relationship. The joint angle vector is divided into two groups and their effect on end-effector position is decoupled using a concept called function decomposition. It is shown that function decomposition leads to significant improvement in accuracy of inverse kinematic solution. However, this method yields a unique inverse kinematic solution for a given target point. A concept called sub-clustering in configuration space is suggested to preserve redundancy during learning process and redundancy is resolved at position level using several criteria. Even though the training is carried out off-line, the trained network is used online to compute the required joint angle vector in only one step. The accuracy attained is better than the current state of art. The experiment is implemented in real-time and the results are found to corroborate theoretical findings. © 2008 IEEE.

AB - This paper deals with visual-motor coordination of a 7 dof robot manipulator for pick and place applications. Three issues are dealt with in this paper - finding a feasible inverse kinematic solution without using any orientation information, resolving redundancy at position level and finally maintaining the fidelity of information during clustering process thereby increasing accuracy of inverse kinematic solution. A 3-dimensional KSOM lattice is used to locally linearize the inverse kinematic relationship. The joint angle vector is divided into two groups and their effect on end-effector position is decoupled using a concept called function decomposition. It is shown that function decomposition leads to significant improvement in accuracy of inverse kinematic solution. However, this method yields a unique inverse kinematic solution for a given target point. A concept called sub-clustering in configuration space is suggested to preserve redundancy during learning process and redundancy is resolved at position level using several criteria. Even though the training is carried out off-line, the trained network is used online to compute the required joint angle vector in only one step. The accuracy attained is better than the current state of art. The experiment is implemented in real-time and the results are found to corroborate theoretical findings. © 2008 IEEE.

UR - http://www.mendeley.com/research/implementation-neural-network-based-visual-motor-control-algorithm-7-dof-redundant-manipulator

U2 - 10.1109/IJCNN.2008.4633972

DO - 10.1109/IJCNN.2008.4633972

M3 - Chapter

SN - 9781424418213

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 1344

EP - 1351

BT - Proceedings of the International Joint Conference on Neural Networks

ER -

Kumar S, Behera L. Implementation of a neural network based visual motor control algorithm for a 7 DOF redundant manipulator. In Proceedings of the International Joint Conference on Neural Networks. 2008. p. 1344-1351. (Proceedings of the International Joint Conference on Neural Networks). https://doi.org/10.1109/IJCNN.2008.4633972