Title :
Motion control of two-link flexible-joint robot, using backstepping, neural networks, and indirect method
Author :
Chatlatanagulchai, Withit ; Meckl, Peter H.
Author_Institution :
Sch. of Mech. Eng., Purdue Univ., West Lafayette, IN
Abstract :
We present a state-feedback control of a two-link flexible-joint robot. The control algorithm does not require the mathematical model representing the robot. Three-layer neural networks approximate the unknown plant functions. The neural network weights are adapted on-line. We use backstepping control structure together with variable structure control to provide robustness to all uncertainties. We have included experimental results to show the effectiveness of the control algorithm
Keywords :
flexible manipulators; manipulator kinematics; motion control; neurocontrollers; robust control; state feedback; variable structure systems; backstepping control structure; indirect method; motion control; neural network; plant function; robustness; state-feedback control; two-link flexible-joint robot; variable structure control; Actuators; Backstepping; Control design; Mathematical model; Motion control; Neural networks; Robots; Robust control; Torque; Uncertainty;
Conference_Titel :
Control Applications, 2005. CCA 2005. Proceedings of 2005 IEEE Conference on
Conference_Location :
Toronto, Ont.
Print_ISBN :
0-7803-9354-6
DOI :
10.1109/CCA.2005.1507192
