In this study, an optimal trajectory planning based on artificial neural networks and genetic algorithms was proposed for control of nuclear research reactors. The trajectory being followed by the reactor power is composed of three parts. In order to calculate periods of all parts of the trajectory, a period generator was designed based on a feedforward neural network. Period values of the trajectory used to train the artificial neural network were acquired by utilizing genetic algorithms. The contribution of the proposed trajectory to the reactor control system was investigated. Furthermore, the behavior of the controller with the proposed trajectory was tested for various initial and desired power levels, as well as under disturbance. It was seen that the controller could control the system successfully under all conditions within the acceptable error tolerance.