Human Locomotion Implicit Modeling Based Real-Time Gait Phase Estimation

2025-06-18

AI Summary

To address the degradation in accuracy and robustness of IMU-driven gait phase estimation under terrain transitions, this paper proposes a real-time algorithm based on implicit human motion modeling, tailored for adaptive lower-limb exoskeleton control. The method jointly models gait phase states and multi-channel IMU signals as coupled observations of human locomotion. It introduces a channel-masking reconstruction pretraining strategy and integrates temporal convolutional networks (TCNs) with Transformers to enable dynamic multi-scale temporal modeling and inter-channel interaction. Experimental results show a phase root-mean-square error (RMSE) of 2.73±1.07% on stable terrain and 3.22±1.30% during terrain transitions. Hardware validation confirms high-precision detection of gait cycles and key events, enabling continuous cross-terrain locomotion.

Technology Category

• Intelligent Robots: State Estimation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Gait phase estimation based on inertial measurement unit (IMU) signals facilitates precise adaptation of exoskeletons to individual gait variations. However, challenges remain in achieving high accuracy and robustness, particularly during periods of terrain changes. To address this, we develop a gait phase estimation neural network based on implicit modeling of human locomotion, which combines temporal convolution for feature extraction with transformer layers for multi-channel information fusion. A channel-wise masked reconstruction pre-training strategy is proposed, which first treats gait phase state vectors and IMU signals as joint observations of human locomotion, thus enhancing model generalization. Experimental results demonstrate that the proposed method outperforms existing baseline approaches, achieving a gait phase RMSE of $2.729 pm 1.071%$ and phase rate MAE of $0.037 pm 0.016%$ under stable terrain conditions with a look-back window of 2 seconds, and a phase RMSE of $3.215 pm 1.303%$ and rate MAE of $0.050 pm 0.023%$ under terrain transitions. Hardware validation on a hip exoskeleton further confirms that the algorithm can reliably identify gait cycles and key events, adapting to various continuous motion scenarios. This research paves the way for more intelligent and adaptive exoskeleton systems, enabling safer and more efficient human-robot interaction across diverse real-world environments.

Problem

• Estimating gait phase accurately from IMU signals
• Improving robustness during terrain changes
• Enhancing exoskeleton adaptation to gait variations

Innovation

• Implicit modeling neural network for gait estimation
• Temporal convolution and transformer fusion
• Channel-wise masked reconstruction pre-training