Visual motor control of a 7DOF redundant manipulator using redundancy preserving learning network

Swagat Kumar, P. Premkumar, Ashish Dutta, Laxmidhar Behera

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

This paper deals with the design and implementation of a visual kinematic control scheme for a redundant manipulator. The inverse kinematic map for a redundant manipulator is a one-to-many relation problem; i.e. for each Cartesian position, multiple joint angle vectors are associated. When this inverse kinematic relation is learnt using existing learning schemes, a single inverse kinematic solution is achieved, although the manipulator is redundant. Thus a new redundancy preserving network based on the self-organizing map (SOM) has been proposed to learn the one-to-many relation using sub-clustering in joint angle space. The SOM network resolves redundancy using three criteria, namely lazy arm movement, minimum angle norm and minimum condition number of image Jacobian matrix. The proposed scheme is able to guide the manipulator end-effector towards the desired target within 1-mm positioning accuracy without exceeding physical joint angle limits. A new concept of neighbourhood has been introduced to enable the manipulator to follow any continuous trajectory. The proposed scheme has been implemented on a seven-degree-of-freedom (7DOF) PowerCube robot manipulator successfully with visual position feedback only. The positioning accuracy of the redundant manipulator using the proposed scheme outperforms existing SOM-based algorithms.
Original languageEnglish
Pages (from-to)795-810
Number of pages16
JournalRobotica
Volume28
Issue number6
DOIs
Publication statusPublished - 31 Oct 2010

Fingerprint

Redundant Manipulator
Redundant manipulators
Motor Control
Inverse kinematics
Redundancy
Self organizing maps
Inverse Kinematics
Manipulators
Self-organizing Map
Manipulator
One to many
Angle
Positioning
Jacobian matrices
End effectors
Robot Manipulator
Jacobian matrix
Kinematics
Condition number
Cartesian

Keywords

  • Inverse kinematics
  • Redundancy resolution
  • Self-organizing map
  • Sub-clustering
  • Visual motor control

Cite this

Kumar, Swagat ; Premkumar, P. ; Dutta, Ashish ; Behera, Laxmidhar. / Visual motor control of a 7DOF redundant manipulator using redundancy preserving learning network. In: Robotica. 2010 ; Vol. 28, No. 6. pp. 795-810.
@article{3dd9cb1c209149929c5600b6b55ed935,
title = "Visual motor control of a 7DOF redundant manipulator using redundancy preserving learning network",
abstract = "This paper deals with the design and implementation of a visual kinematic control scheme for a redundant manipulator. The inverse kinematic map for a redundant manipulator is a one-to-many relation problem; i.e. for each Cartesian position, multiple joint angle vectors are associated. When this inverse kinematic relation is learnt using existing learning schemes, a single inverse kinematic solution is achieved, although the manipulator is redundant. Thus a new redundancy preserving network based on the self-organizing map (SOM) has been proposed to learn the one-to-many relation using sub-clustering in joint angle space. The SOM network resolves redundancy using three criteria, namely lazy arm movement, minimum angle norm and minimum condition number of image Jacobian matrix. The proposed scheme is able to guide the manipulator end-effector towards the desired target within 1-mm positioning accuracy without exceeding physical joint angle limits. A new concept of neighbourhood has been introduced to enable the manipulator to follow any continuous trajectory. The proposed scheme has been implemented on a seven-degree-of-freedom (7DOF) PowerCube robot manipulator successfully with visual position feedback only. The positioning accuracy of the redundant manipulator using the proposed scheme outperforms existing SOM-based algorithms.",
keywords = "Inverse kinematics, Redundancy resolution, Self-organizing map, Sub-clustering, Visual motor control",
author = "Swagat Kumar and P. Premkumar and Ashish Dutta and Laxmidhar Behera",
year = "2010",
month = "10",
day = "31",
doi = "10.1017/S026357470999049X",
language = "English",
volume = "28",
pages = "795--810",
journal = "Robotica",
issn = "0263-5747",
publisher = "Cambridge University Press",
number = "6",

}

Visual motor control of a 7DOF redundant manipulator using redundancy preserving learning network. / Kumar, Swagat; Premkumar, P.; Dutta, Ashish; Behera, Laxmidhar.

In: Robotica, Vol. 28, No. 6, 31.10.2010, p. 795-810.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Visual motor control of a 7DOF redundant manipulator using redundancy preserving learning network

AU - Kumar, Swagat

AU - Premkumar, P.

AU - Dutta, Ashish

AU - Behera, Laxmidhar

PY - 2010/10/31

Y1 - 2010/10/31

N2 - This paper deals with the design and implementation of a visual kinematic control scheme for a redundant manipulator. The inverse kinematic map for a redundant manipulator is a one-to-many relation problem; i.e. for each Cartesian position, multiple joint angle vectors are associated. When this inverse kinematic relation is learnt using existing learning schemes, a single inverse kinematic solution is achieved, although the manipulator is redundant. Thus a new redundancy preserving network based on the self-organizing map (SOM) has been proposed to learn the one-to-many relation using sub-clustering in joint angle space. The SOM network resolves redundancy using three criteria, namely lazy arm movement, minimum angle norm and minimum condition number of image Jacobian matrix. The proposed scheme is able to guide the manipulator end-effector towards the desired target within 1-mm positioning accuracy without exceeding physical joint angle limits. A new concept of neighbourhood has been introduced to enable the manipulator to follow any continuous trajectory. The proposed scheme has been implemented on a seven-degree-of-freedom (7DOF) PowerCube robot manipulator successfully with visual position feedback only. The positioning accuracy of the redundant manipulator using the proposed scheme outperforms existing SOM-based algorithms.

AB - This paper deals with the design and implementation of a visual kinematic control scheme for a redundant manipulator. The inverse kinematic map for a redundant manipulator is a one-to-many relation problem; i.e. for each Cartesian position, multiple joint angle vectors are associated. When this inverse kinematic relation is learnt using existing learning schemes, a single inverse kinematic solution is achieved, although the manipulator is redundant. Thus a new redundancy preserving network based on the self-organizing map (SOM) has been proposed to learn the one-to-many relation using sub-clustering in joint angle space. The SOM network resolves redundancy using three criteria, namely lazy arm movement, minimum angle norm and minimum condition number of image Jacobian matrix. The proposed scheme is able to guide the manipulator end-effector towards the desired target within 1-mm positioning accuracy without exceeding physical joint angle limits. A new concept of neighbourhood has been introduced to enable the manipulator to follow any continuous trajectory. The proposed scheme has been implemented on a seven-degree-of-freedom (7DOF) PowerCube robot manipulator successfully with visual position feedback only. The positioning accuracy of the redundant manipulator using the proposed scheme outperforms existing SOM-based algorithms.

KW - Inverse kinematics

KW - Redundancy resolution

KW - Self-organizing map

KW - Sub-clustering

KW - Visual motor control

UR - https://www.cambridge.org/core/services/aop-cambridge-core/content/view/2A1426687ED03067184E8E111B8FB1AA/S026357470999049Xa.pdf/visual_motor_control_of_a_7dof_redundant_manipulator_using_redundancy_preserving_learning_network.pdf

UR - http://www.mendeley.com/research/visual-motor-control-7dof-redundant-manipulator-using-redundancy-preserving-learning-network-1

U2 - 10.1017/S026357470999049X

DO - 10.1017/S026357470999049X

M3 - Article

VL - 28

SP - 795

EP - 810

JO - Robotica

JF - Robotica

SN - 0263-5747

IS - 6

ER -