Abstract: An observer-based adaptive controller design approach using neural networks is proposed in this paper for the trajectory tracking of a robot with unknown dynamic nonlinearities, and the robot manipulator is assumed to have only joint angle position measurements. A linear observer is used to estimate the robot joint angle velocity, while the neural network is employed to further improve the control performance of the controlled system through approximating the revised dynamic nonlinearities of the robot. The observer- based neural network controller can gurarantee the uniformly ultimately bounded tracking errors and the observer errors and boundedness of the neural network weights. Main theoretic results for designing an adaptive controllerobserver for a robot using neural networks are given, and the control performance of the proposed controller is verified through simulation studies.