DESIGNED FOR LIMB LOSS: AN ARTIFICIAL INTELLIGENCE-BASED BIONIC PROSTHETIC ARM TRANSITION FROM SIMULATION TO REALITY

Limb or organ loss of human remains challenging especially in the world of incessant reliance on touch-based screens and tasks. Thereby, patients can barely withstand and cope with the augmenting restrictions that they encounter due to this loss. Modern means and technologies, such as advanced and artificial parts reduced restrictions on patients with disabilities or a lost limb or organ. Hand prostheses, for instance, provided a powerful tool for improving the functional capabilities of human limbs, thereby improving the quality of life of the user. However, patients using prosthetic arms are still encountering numerous problems, such as, suffering from intact limb and back pain, the high cost of prosthesis systems and hardships related to the performance of the prosthesis, poor control and updating difficulties. Based on the aforementioned problems, the objective was to design a 3D bionic arm which is made of heavy duty plastic with low weight. The aim was to use servo motors instead of stepper motors to maintain less delay and less weight. The aim was also to design an Artificial Intelligence (AI) based-bionic arm program that can be feasibly modified for future purposes, such as adding new gestures and optimizing the system’s control. The new design comprised 3D printing arm, controlling the design, testing motors and EMG sensors, choosing cost-effective parts, simulating and finalizing the real prototype. In conjunction with direct performing motor mechanisms and a full-scale model of a bionic prosthesis, the development was intended for medical rehabilitation of the upper limbs. Experimental results included, the development of a real AI-based system to customize gestures controlled using Neural Network. Results also included maintaining accurate and clean readings of the EMG sensor. Moreover, the new bionic prosthesis arm insured no delay in performance which mimics the normal function of the hand. Results also showed that our design surpassed available designs in its cost-effectiveness, provided that in several other specifications it was comparable. The design was flexible and AI-based controlled. As a future prospect, more algorithms can be tested and more gestures can be tested in the new AI-based design.