Advancements in Myoelectric Robotic Hands and Prosthetic Limbs

Abstract

This paper presents a comprehensive review of the recent advancements in myoelectric robotic hands and prosthetic limbs, focusing on the integration of electromyography (EMG) signal processing, machine learning algorithms, and sensor technologies. The evolution of these technologies has significantly enhanced the functionality and user experience of prosthetic devices, enabling more intuitive control and improved adaptability to various tasks. Our analysis of 37 recent studies reveals that machine learning approaches have improved pattern recognition accuracy by <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$15-25 \%$</tex> compared to conventional methods, with convolutional neural networks achieving classification accuracy of up to 97.8 % for multi-gesture recognition. Sensor integration has reduced response times from 300 ms to under 100 ms, while providing force feedback with resolution of 0.1 N. We explore the methodologies employed in the development of advanced prosthetic systems, including the use of surface EMG for realtime muscle activity detection and the application of artificial intelligence for gesture recognition. Arduino-based platforms have reduced production costs by <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$60-70 \%$</tex> while maintaining functionality comparable to commercial alternatives. Additionally, we address the challenges faced in the field, such as the need for better signal interpretation, user training, and the development of cost-effective solutions. The findings underscore the potential of these innovations to transform the lives of individuals with upper limb amputations, with studies reporting <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{4 0 - 6 0 \%}$</tex> improvements in task completion rates and 30 % reductions in user fatigue, paving the way for future research and development in assistive technologies.