This work presents the development of a brain machine interface as an alternative communication channel to be used in Robotics. It encompasses the implementation of an electroencephalograph (EEG), as well as the development of all computational methods and necessary techniques to identify mental activities. The developed brain machine interface (BMI) is applied to activate the movements of a MA2000 robotic arm, associating four different mental activities to robotic arm commands. The interface is based on EEG signal analyses, which extract features that can be classified as specific mental activities. First, a signal preprocessing is performed from the EEG data, filtering noise, using a spatial filter to increase the scalp signal resolution, and extracting relevant features. Then, different classifier models are proposed, evaluated and compared. Finally, two implementations of the developed classifiers are proposed to improve the rate of successful commands to the robotic arm. In one of the implementations, a rate of successful commands up to 91% was obtained, with wrong commands as low as 1.25%, after 400 attempts to control the robotic arm.