A dual neural network for redundancy resolution of kinematically redundant manipulators subject to joint limits and joint velocity limits

Yunong Zhang, Jun Wang, Youshen Xia

Research output: Contribution to journalArticlepeer-review

217 Citations (Scopus)

Abstract

In this paper, a recurrent neural network called the dual neural network is proposed for online redundancy resolution of kinematically redundant manipulators. Physical constraints such as joint limits and joint velocity limits, together with the drift-free criterion as a secondary task, are incorporated into the problem formulation of redundancy resolution. Compared to other recurrent neural networks, the dual neural network is piecewise linear and has much simpler architecture with only one layer of neurons. The dual neural network is shown to be globally (exponentially) convergent to optimal solutions. The dual neural network is simulated to control the PA10 robot manipulator with effectiveness demonstrated.

Original languageEnglish
Pages (from-to)658-667
Number of pages10
JournalIEEE Transactions on Neural Networks
Volume14
Issue number3
DOIs
Publication statusPublished - May 2003
Externally publishedYes

Keywords

  • Drift-free
  • Dual neural network
  • Joint limits
  • Joint velocity limits
  • Kinematically redundant manipulators

Fingerprint

Dive into the research topics of 'A dual neural network for redundancy resolution of kinematically redundant manipulators subject to joint limits and joint velocity limits'. Together they form a unique fingerprint.

Cite this