Obstacle and singularity avoidance for kinematically redundant manipulators based on neurodynamic optimization

Zhang, P; Yan, Z; Wang, J

Obstacle and singularity avoidance for kinematically redundant manipulators based on neurodynamic optimization

Zhang, P Yan, Z

Wang, J

Permalink

Publication Type:: Conference Proceeding
Citation:: 5th International Conference on Intelligent Control and Information Processing, ICICIP 2014 - Proceedings, 2015, pp. 460 - 465
Issue Date:: 2015-01-14

Closed Access

	Filename	Description	Size
	07010299.pdf	Published version	3.02 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, P	en_US
dc.contributor.author	Yan, Z https://orcid.org/0000-0003-3368-2100	en_US
dc.contributor.author	Wang, J	en_US
dc.date.issued	2015-01-14	en_US
dc.identifier.citation	5th International Conference on Intelligent Control and Information Processing, ICICIP 2014 - Proceedings, 2015, pp. 460 - 465	en_US
dc.identifier.isbn	9781479936489	en_US
dc.identifier.uri	http://hdl.handle.net/10453/121318
dc.description.abstract	© 2014 IEEE. With wide applications of kinematically redundant manipulators in robotics, obstacle and singularity avoidance emerge as critical issues to be addressed. Correspondingly, three problems have to be considered, including the determination of critical points on a given manipulator, the computation of joint velocities using inverse kinematics, and the analysis of singularity caused by configurations of manipulators. In this paper, these tasks are formulated as a convex quadratic programming (QP) subject to equality and inequality constraints with time-varying parameters where physical constraints such as joint physical limits are also incorporated directly into the formulation. To solve the QP problem in real time, a recurrent neural network called the improved dual neural network is applied, which has lower structural complexity compared with existing neural networks for solving this particular problem. The effectiveness of the proposed approaches is demonstrated by simulation results based on the Mitsubishi PA10-7C manipulator.	en_US
dc.relation.ispartof	5th International Conference on Intelligent Control and Information Processing, ICICIP 2014 - Proceedings	en_US
dc.relation.isbasedon	10.1109/ICICIP.2014.7010299	en_US
dc.title	Obstacle and singularity avoidance for kinematically redundant manipulators based on neurodynamic optimization	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

© 2014 IEEE. With wide applications of kinematically redundant manipulators in robotics, obstacle and singularity avoidance emerge as critical issues to be addressed. Correspondingly, three problems have to be considered, including the determination of critical points on a given manipulator, the computation of joint velocities using inverse kinematics, and the analysis of singularity caused by configurations of manipulators. In this paper, these tasks are formulated as a convex quadratic programming (QP) subject to equality and inequality constraints with time-varying parameters where physical constraints such as joint physical limits are also incorporated directly into the formulation. To solve the QP problem in real time, a recurrent neural network called the improved dual neural network is applied, which has lower structural complexity compared with existing neural networks for solving this particular problem. The effectiveness of the proposed approaches is demonstrated by simulation results based on the Mitsubishi PA10-7C manipulator.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/121318