Adaptive neural network control for uncertain robotic manipulators with output constraint using integral-barrier Lyapunov functions

In this paper, an adaptive neural network (NN) output tracking control approach is presented for uncertain robotic manipulators with the output constraint. Integral-barrier Lyapunov functions (iBLF) are adopted to prevent the output from violating the given constraint. And adaptive neural networks, which are capable of approximating the arbitrary continuous function at any precision, are employed in handling uncertainties and disturbances. By appropriately choosing design parameters, the proposed method can guarantee the semi-global uniformly ultimate boundedness of the output error, and all signals of the closed-loop system remain bounded. The effectiveness and performance of the proposed control method are illustrated through a numerical simulation example.