Force Myography based Torque Estimation in Human Knee and Ankle Joints

2024-09-17

arXiv.org

AI Summary

To address low accuracy and reliance on invasive or interference-prone signals (e.g., electromyography, EMG) for joint torque estimation in personalized exoskeleton control, this paper proposes an online knee–ankle dual-joint torque estimation method based on force myography (FMG). The approach fuses FMG signals with joint kinematics—specifically, joint angle and angular velocity—enabling, for the first time, FMG-based collaborative modeling of knee and ankle torques. Gaussian process regression (GPR) is employed to establish a robust, non-invasive model that circumvents EMG’s stringent requirements for skin contact quality and complex preprocessing. In isokinetic motion experiments involving two subjects, the FMG-based model reduces mean root-mean-square error (RMSE) by 32% at the knee and 28% at the ankle compared to a pure kinematic baseline, achieving torque estimation accuracy comparable to EMG-augmented models. The method offers distinct advantages in non-invasiveness, robustness to signal artifacts, and practical deployability.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Kernel Methods
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Online adaptation of exoskeleton control based on muscle activity sensing is a promising way to personalize exoskeletons based on the user's biosignals. While several electromyography (EMG) based methods have been shown to improve joint torque estimation, EMG sensors require direct skin contact and complex post-processing. In contrast, force myography (FMG) measures normal forces from changes in muscle volume due to muscle activity. We propose an FMG-based method to estimate knee and ankle joint torques by combining joint angles and velocities with muscle activity information. We learn a model for joint torque estimation using Gaussian process regression (GPR). The effectiveness of the proposed FMG-based method is validated on isokinetic motions performed by two subjects. The model is compared to a baseline model using only joint angle and velocity, as well as a model augmented by EMG data. The results show that integrating FMG into exoskeleton control improves the joint torque estimation for the ankle and knee and is therefore a promising way to improve adaptability to different exoskeleton users.

Problem

• Estimating knee and ankle joint torques using FMG
• Improving exoskeleton control with muscle activity data
• Comparing FMG-based torque estimation against EMG methods

Innovation

• FMG-based joint torque estimation method
• Gaussian process regression for modeling
• Integration of joint angles and velocities