In this paper, a radical adaptive terminal sliding mode control method for a robotic arm with modeluncertainties and external disturbances is proposed in such a way that the singularity problem is completely dealt with.A radial basis function neural network (RBFNN) with an online weight tuning algorithm is employed to approximateunknown smooth nonlinear dynamic functions caused by the fact that there is no prior knowledge of the roboticdynamic model. Furthermore, a robust control law is utilized in order to eliminate total uncertainty composed ofmodel uncertainties, external disturbances, and the inevitable approximation errors resulting from the finite number ofthe hidden-layer neurons of the RBFNN. Thanks to this proposed controller, a desired performance is achieved wheretracking errors converge to zero within a finite time. In accordance with Lyapunov theory, the desired performanceand the stability of the whole closed loop control system are ensured to be achieved. Finally, comparative computersimulation results are illustrated to confirm the validity and efficiency of the proposed control method.