Direct-adaptive neurocontrol of robots with unknown nonlinearities and velocity feedback

Tsu Tian Lee*, Sisil Kumarawadu, Jau Woei Perng

*此作品的通信作者

研究成果: Conference article同行評審

5 引文 斯高帕斯(Scopus)

摘要

A neural network (NN) adaptive tracking controller for rigid revolute robots is presented that requires position measurements only. The controller is synthesized using a computed torque like control part of which a modified version of the nonlinear part of Lagrangian dynamics is learnt online by a neural estimator that needs no off-line training phase. Therefore, the implementation of the control algorithm needs a reasonable knowledge of the inertia matrix alone. The combined neurocontroller-linear observer scheme can guarantee the uniform ultimate bounds (UUB) of the tracking errors and the observer errors under fairly general conditions on the controller-observer gains.

原文English
頁(從 - 到)2073-2077
頁數5
期刊Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
3
出版狀態Published - 2005
事件IEEE Systems, Man and Cybernetics Society, Proceedings - 2005 International Conference on Systems, Man and Cybernetics - Waikoloa, HI, United States
持續時間: 10 10月 200512 10月 2005

指紋

深入研究「Direct-adaptive neurocontrol of robots with unknown nonlinearities and velocity feedback」主題。共同形成了獨特的指紋。

引用此