Desarrollo e implementación de un sistema de visión artificial y seguimiento de objetivos humanos por un cuadricóptero de exteriores utilizando Matlab

Abstract

For a person without physical limitation, it is easy to perform daily activities. However, it is difficult or impossible for a person who lost part of their limbs in this case a hand. With this antecedent and to improve the life quality of these people, in the present project it had been made the control over a commercial robotic hand by means of electromyogram signals (EMG) coming from the 8-channels of a commercial equipment (Myo armband). In this investigation, we determine the best EMG channel to facilitate the classification between open and closed hand, and so to control a robotic hand that it makes the same activity. An important contribution of this work is to determine the interpersonal variability that exists in each of the people. The project consists of several stages, which consist of developing the appropriate interface between the bracelet and the computer using communication libraries available on the web, analyzing the 8 EMG channels and discriminating the channel that contains the most appropriate signal that allows to perform the classification between open and closed hand, which will allow the activation of robotic hand. Finally, the corresponding tests were carried out to verify the correct functioning and performance of the project.