Bio-Inspired Auto-Adaptive Framework for Optimized Movement of Passive Knee Prosthesis

This research addresses the challenges faced by amputees who struggle with performing daily activities due to missing limbs. The objective is to create a bio-inspired framework that intelligently adapts to compensate for lost mobility for amputees wearing passive knee prostheses. The framework incorporates a comprehensive study of human movement plans, utilizing a mathematical model of a damping control mechanism of the prosthesis, sensors (IMUs, goniometer, EMG, and tactile), and empirical analysis of the functional role of the human brain (HBN) Vs machine brain (MBN) in daily life activities. In real-world testing, the framework successfully controlled the knee flexion angle for amputees within the normal range of motion (64° ± 6). Our deep learning architecture achieved a high classification accuracy of 94.44% for gait phase events, with an 81% testing accuracy for amputees. Empirical analysis revealed a functional distribution of 70% HBN involvement and 30% for the MBN (prosthetic control unit) contribution to biomechanical activities. The proposed framework demonstrated optimized movement, reducing hip hikes and fatigue, maintaining normal knee flexion, and achieving a 95% balance and fall prevention rate. This research presents a promising solution for enhancing the functionality of passive knee prostheses, significantly improving the quality of life for amputees.