A robust adaptive neural network control scheme for a class of uncertain nonlinear systems with unknown control
gain function and its signs is proposed based on backstepping sliding mode control design. The control scheme eliminates
the condition that a priori knowledge of the control gain function and its signs to be known by combination of Nussbaum
gain design technique and the approximation capability of neural networks. The controller singularity problem is avoided by
employing the integral Lyapunov functions, and the influence of modeling error and uncertain disturbances is minimized by
introducing the adaptive compensation term for the upper bound of both neural networks approximation error and uncertain
disturbances. By theoretical analysis, all the signals in the closed loop systems are guaranteed to be semi-globally uniformly
ultimately bounded. Finally, the simulation results show the effectiveness of the proposed method.