Constrained motion control of flexible manipulators based on a dynamic neural network

In this paper, a neural network approach is proposed for the motion control of a constrained flexible manipulator system, whereby both the contact force and the position of the end-effector contacting with a surface are controlled. The dynamic equations, vibration of the flexible link and constrained force are derived. The developed control scheme can adaptively estimate the dynamics of the manipulator by utilizing a dynamic recurrent neural network (DRNN) to approximate the underlying dynamics. Local stability of the system is discussed. The results confirm that the designed controller performs remarkably well.