Estimating Human Muscular Fatigue in Dynamic Collaborative Robotic Tasks with Learning-Based Models
Feras Kiki, Pouya Pourakbarian Niaz, Alireza Madani, Cagatay Basdogan
AI summary
Problem
Existing data-driven fatigue estimation methods often treat fatigue as a discrete classification problem, failing to capture its continuous physiological progression needed for timely intervention in dynamic physical human–robot interaction tasks.
Approach
The authors trained subject-specific machine learning and deep learning regression models to predict the fraction of cycles to fatigue using frequency/time-domain sEMG features and spectrograms from cyclic collaborative robotic movements.
Key results
- CNN achieved lowest RMSE (20.8%) for fatigue progression estimation
- Random Forest, XGBoost, and Linear Regression followed with RMSEs of 23.3%, 24.8%, and 26.9%
- Successful generalization to unseen vertical and circular movement tasks
- Strong correlation with subjective fatigue ratings
Why it matters
Provides a robust, real-time fatigue tracking framework to enhance safety, ergonomics, and adaptive control in collaborative robotics, rehabilitation, and sports training.
Abstract
Assessing human muscle fatigue is critical for opti- mizing performance in physical human–robot interaction (pHRI) tasks and mitigating safety risks for the human operator. This paper presents a data-driven framework for estimating muscle fatigue in dynamic pHRI tasks using surface electromyography (sEMG) sensors attached to the human arm. Subject-specific machine learning (ML) regression models were developed to estimate fatigue levels during cyclic (i.e., repetitive) pHRI tasks. Specifically, Random Forest, XGBoost, and Linear Regression models were trained to estimate the fraction of cycles to fatigue (FCF) using three frequency-domain and one time-domain EMG features. Their performance was compared with a convolutional neural network (CNN) model that processes spectrogram rep- resentations of filtered EMG signals. Unlike most earlier data- driven approaches that primarily formulated fatigue estimation as a classification problem, our method models the progression toward fatigue through regression, enabling tracking of gradual physiological changes rather than discrete states, which is critical for timely intervention and adaptive control in dynamic pHRI tasks. Experiments were conducted with ten participants who interacted with a collaborative robot driven by an admittance controller, performing lateral (left-right) cyclic movements of the end effector until the muscular exhaustion. The results demonstrate that the root mean square error (RMSE) of FCF estimation across participants was 20.8 ± 4.3%, 23.3 ± 3.8%, 24.8 ± 4.5%, and 26.9 ± 6.1% for the CNN, Random Forest, XGBoost, and Linear Regression models, respectively. To examine cross-task generalization in this investigational study, additional experiments were performed with one participant who executed vertical (up–down) and circular repetitive movements. Models trained solely on the lateral-movement data were directly tested on these unseen tasks. The results indicate that the proposed ML/DL models are robust to variations in movement direction, arm kinematics, and muscle recruitment patterns, while the Linear Regression model performed poorly.