Mathematically, the motion of a robot manipulator can be computed through the integration of kinematics, dynamics, and trajectories calculations. However, the calculations are complex and only can be applied if the configuration of the robot and the characteristics of the joint trajectories are known. This paper introduces the use of artificial neural networks (ANN) to overcome these shortcomings by solving nonlinear functions and adapting the characteristics of unknown trajectories. A virtual six-degree-of-freedom (DOF) robot manipulator is exploited as an example to show the robustness of the developed ANN topology.