Reliable Vertical Ground Reaction Force Estimation with Smart Insole During Walking

2025-01-13

AI Summary

Existing wearable-based methods for estimating vertical ground reaction force (vGRF) and its characteristic peaks—loading and push-off phases—under free-living gait exhibit severe signal drift, poor cross-subject generalizability, and insufficient accuracy. To address these limitations, this work proposes the first cross-subject robust vGRF estimation framework that fuses center-of-pressure (COP) spatial trajectory sequences with multi-dimensional inertial measurement unit (IMU) time-series signals for full-cycle vGRF modeling. We employ multimodal time-series regression using artificial neural networks (ANN), random forests, and bidirectional long short-term memory (Bi-LSTM) networks. Within-subject evaluation yields an RMSE of 0.024 body weight (BW) (r = 0.997); cross-subject RMSE is 0.044 BW, peak estimation error remains below 0.044 BW, and temporal latency is under 2.3% of the gait cycle. The framework significantly enhances both practical deployability and generalization capability across diverse users.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Biometrics, Face, Gesture & Pose
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

The vertical ground reaction force (vGRF) and its characteristic weight acceptance and push-off peaks measured during walking are important for gait and biomechanical analysis. Current wearable vGRF estimation methods suffer from drifting errors or low generalization performances, limiting their practical application. This paper proposes a novel method for reliably estimating vGRF and its characteristic peaks using data collected from the smart insole, including inertial measurement unit data and the newly introduced center of the pressed sensor data. These data were fused with machine learning algorithms including artificial neural networks, random forest regression, and bi-directional long-short-term memory. The proposed method outperformed the state-of-the-art methods with the root mean squared error, normalized root mean squared error, and correlation coefficient of 0.024 body weight (BW), 1.79% BW, and 0.997 in intra-participant testing, and 0.044 BW, 3.22% BW, and 0.991 in inter-participant testing, respectively. The difference between the reference and estimated weight acceptance and push-off peak values are 0.022 BW and 0.017 BW with a delay of 1.4% and 1.8% of the gait cycle for the intra-participant testing and 0.044 BW and 0.025 BW with a delay of 1.5% and 2.3% of the gait cycle for the inter-participant testing. The results indicate that the proposed vGRF estimation method has the potential to achieve accurate vGRF measurement during walking in free living environments.

Problem

• Wearable Devices
• Vertical Ground Reaction Force (vGRF)
• Accuracy and Applicability

Innovation

• Smart Insoles
• Multi-sensor Data Fusion
• Advanced AI Algorithms