A 3D Printing Soft Prosthesis and an IoT Architecture for Controlling Gestures

Upper limb prosthesis have been evolving since 1967, progressing from mechanical prosthesis to robotic prosthesis, integrating electronics with emerging materials. This work aims to develop a low-cost integrated active upper limb prosthesis using additive manufacturing, controlled by the user with a myoelectric sensor to perform three hand gestures: power grip, two-fingered cup movement, and gripper actions. The prosthesis is based on the reduction of degrees of freedom, the analysis of five additive manufacturing materials, and the implementation of a neural network to control the gestures performed by the prosthesis. The precision obtained in the best model saved by the neural network was 91.25% and a recall of 90.75%. A key contribution of this work is the integration of soft 3D printing materials, which enhance object grasping by conforming to various shapes. In this case, grasping was achieved using a driven cable and a flex sensor in three gestures with different objects.