eduzhai > Applied Sciences > Engineering >

Kinematic Resolutions of Redundant Robot Manipulators using Integration-Enhanced RNNs

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 7 pages

Abstract: Recently, a time-varying quadratic programming (QP) framework that describesthe tracking operations of redundant robot manipulators is introduced to handlethe kinematic resolutions of many robot control tasks. Based on thegeneralization of such a time-varying QP framework, two schemes, i.e., theRepetitive Motion Scheme and the Hybrid Torque Scheme, are proposed. However,measurement noises are unavoidable when a redundant robot manipulator isexecuting a tracking task. To solve this problem, a novel integration-enhancedrecurrent neural network (IE-RNN) is proposed in this paper. Associating withthe aforementioned two schemes, the tracking task can be accurately completedby IE-RNN. Both theoretical analyses and simulations results prove that theresidual errors of IE-RNN can converge to zero under different kinds ofmeasurement noises. Moreover, practical experiments are elaborately made toverify the excellent convergence and strong robustness properties of theproposed IE-RNN.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...