Stable task space neurocontroller for robot manipulators without Jacobian matrix

This paper proposes a stable neurocontroller for set-point control of robot manipulators in task space without any a priori knowledge on the Jacobian matrix. A wavelet neural network (WNN) with task information feeding their activation functions and with on-line real-time learning is applied to approximate an unknown nonlinear function. The WNN generates control input signals designed using Lyapunov stability theory to guarantee that all the closed loop signals are uniformly ultimately bounded. Simulation results using a two degrees of freedom robot are presented to evaluate the proposed controller.