Articulated robot manipulators are commonly used in industrial settings due to their ability to execute complex movements and handle heavy loads. To ensure successful task completion, it is crucial to have precise trajectory tracking control for these manipulators. However, the manipulator’s dynamics are highly complex and nonlinear. Additionally, the manipulator’s performance is significantly affected by unknown disturbances. To overcome these, a neural network controller (NNC) is utilized to achieve the desired trajectory. The NNC possesses the ability to learn and adapt to complex and nonlinear systems. To train the NN, data from a PID controller is collected under two conditions: normal condition and with external torque disturbance. The NN is trained using the nntool Matlab toolbox. The proposed NNC’s robustness is analyzed by introducing an external torque disturbance. The controller’s performance is evaluated using metrics root mean square error (RMSE) and integral absolute error (IAE). The results demonstrate that the proposed controller is effective in external disturbance rejection.