EMG-Controlled Robotic Prosthetic Arm With Neural Network Training

Abstract

The project consists of the creation of a roboticarm controlled remotely through a brace developed by ThalmicLabs, able to read the limb muscles’ biopotentials. This projectaims to create an economic alternative to non-invasive activeprostheses that exist today. Our prosthesis can perform the samefunctions but at a so much affordable price. In order to performall the functions of a normal joint, the arm has several elements.Strings that simulate tendons and allow the movement of thefingers, gears that allow the rotation of the wrist and motors,which can generate movement based on the data extractedfrom the bracelet. The bracelet is responsible for transmittinginformation from the hand to the robotic arm through a wirelessmodule that connects it with the computer, where the signal thatextracts the bracelet goes through a filtering process to keep theinformation that interests us and Transmit it through the USBport to a microcontroller, which will be in charge of movingthe engines according to the signals received. To avoid errors inthe measurement of the sensors, the information received fromthe bracelet is trained in the computer using a Neural Networkarchitecture before sending the information to the robotic arm.