Feature Matching-Based Gait Phase Prediction for Obstacle Crossing Control of Powered Transfemoral Prosthesis

2025-10-28

AI Summary

To address insufficient active knee joint control accuracy in transfemoral prostheses during obstacle negotiation, this paper proposes a real-time control strategy driven by intact-side ankle inertial sensing and gait phase estimation. The method innovatively integrates a lightweight neural network—optimized via genetic algorithm—with a multi-scale feature matching strategy, achieving 100% gait phase recognition accuracy under 150 Hz high-frequency sampling. Concurrently, it predicts hip and knee joint angle errors with mean absolute percentage errors of only 8.71% and 6.78%, respectively. By effectively suppressing motion-induced sensor noise, the approach significantly enhances the obstacle-negotiation robustness and dynamic adaptability of powered transfemoral prostheses over complex terrain. Importantly, it eliminates reliance on residual-limb electromyographic signals, establishing a novel paradigm for intelligent, sensor-fusion–based prosthetic control.

Technology Category

• Intelligent Robots: State Estimation
• Natural Language Processing: Safety and Robustness
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Responsible Web: Algorithmic accountability and transparency on the web
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

For amputees with powered transfemoral prosthetics, navigating obstacles or complex terrain remains challenging. This study addresses this issue by using an inertial sensor on the sound ankle to guide obstacle-crossing movements. A genetic algorithm computes the optimal neural network structure to predict the required angles of the thigh and knee joints. A gait progression prediction algorithm determines the actuation angle index for the prosthetic knee motor, ultimately defining the necessary thigh and knee angles and gait progression. Results show that when the standard deviation of Gaussian noise added to the thigh angle data is less than 1, the method can effectively eliminate noise interference, achieving 100% accuracy in gait phase estimation under 150 Hz, with thigh angle prediction error being 8.71% and knee angle prediction error being 6.78%. These findings demonstrate the method's ability to accurately predict gait progression and joint angles, offering significant practical value for obstacle negotiation in powered transfemoral prosthetics.

Problem

• Predicting gait phases for powered transfemoral prosthesis obstacle crossing
• Optimizing neural networks to estimate thigh and knee joint angles
• Eliminating sensor noise interference for accurate prosthetic movement control

Innovation

• Inertial sensor on sound ankle guides obstacle crossing
• Genetic algorithm optimizes neural network for joint prediction
• Gait progression algorithm determines prosthetic actuation angles