Estimating Human Muscular Fatigue in Dynamic Collaborative Robotic Tasks with Learning-Based Models
Authors: Feras Kiki, Pouya P. Niaz, Alireza Madani, Cagatay Basdogan
Organizations: F. Kiki, P. P. Niaz, A. Madani, and C. Basdogan (corresponding author) are with the Robotics and Mechatronics Laboratory (RML) and the KUIS AI Center, Koc University, Sariyer, Istanbul 34450, Turkey.
Assessing human muscle fatigue is critical for optimizing performance and safety in physical human-robot interaction(pHRI). This work presents a data-driven framework to estimate fatigue in dynamic, cyclic pHRI using arm-mounted surface electromyography(sEMG). Subject-specific machine-learning regression models(Random Forest, XGBoost, and Linear Regression predict the fraction of cycles to fatigue(FCF) from three frequency-domain and one time-domain EMG features, and are benchmarked against a convolutional neural network(CNN) that ingests spectrograms of filtered EMG. Framing fatigue estimation as regression (rather than classification) captures continuous progression toward fatigue, supporting earlier detection, timely intervention, and adaptive robot control. In experiments with ten participants, a collaborative robot under admittance control guided repetitive lateral (left-right) end-effector motions until muscular fatigue. Average FCF RMSE across participants was 20.8+/-4.3% for the CNN, 23.3+/-3.8% for Random Forest, 24.8+/-4.5% for XGBoost, and 26.9+/-6.1% for Linear Regression. To probe cross-task generalization, one participant additionally performed unseen vertical (up-down) and circular repetitions; models trained only on lateral data were tested directly and largely retained accuracy, indicating robustness to changes in movement direction, arm kinematics, and muscle recruitment, while Linear Regression deteriorated. Overall, the study shows that both feature-based ML and spectrogram-based DL can estimate remaining work capacity during repetitive pHRI, with the CNN delivering the lowest error and the tree-based models close behind. The reported transfer to new motion patterns suggests potential for practical fatigue monitoring without retraining for every task, improving operator protection and enabling fatigue-aware shared autonomy, for safer fatigue-adaptive pHRI control.
Figures & tables
Fig. 1: Our approach to estimating human muscular fatigue in cyclic pHRI tasks employs learning-based regression models that predict the fraction of cycles to fatigue (FCF) from sEMG measurements.
Fig. 2: The participants of our pHRI experiments were asked to perform cyclic and continuous movements along the X-axis. The end-effector position (first row), human force (second row), and surface EMG signals recorded from the LD (third row) and PD (fourth row) muscles until the onset of fatigue for a representative participant. The vertical dotted lines in the plots are used to separate the cycles.
Fig. 3: Relative change in the maximum values of MNF, MDF, TP, and RMS amplitude with respect to the initial cycle plotted against the fraction of cycle to fatigue (FCF). Each row represents one feature, while the left and right columns are for the data collected from the LD and PD muscles. In each plot, a dot represents a feature for a cycle, and the data of each participant is represented by a unique color. The dashed lines in each plot represent the individual linear fits for each participant, while the solid line depicts the linear fit for the average across all participants to illustrate the general trend.
Fig. 4: a. Subjective level of fatigue perceived by the participants (SRF) was evaluated using Borg CR10 score. b. The fraction of cycles to fatigue (FCF) versus SRF. Each dot in the plot represents an SRF value of a participant recorded for a cycle. Data for each participant is represented by a unique color in the plot. The dashed lines represent the individual linear fits for each participant, while the solid line depicts the linear fit for the average across all participants to illustrate the general trend.
Fig. 5: Bar plots illustrating the mean RMSE values of each participant for the primary task, averaged across all trials, for the different regression models.
Fig. 6: Mean RMSE values for participant S1 in cross-task experiments. Panels (a,c) correspond to models trained on 6 lateral trials and tested on vertical and circular tasks, while panels (b,d) correspond to models trained on 18 lateral trials and tested on the same tasks.
We present FatigueFormer, a semi-end-to-end framework that deliberately combines saliency-guided feature separation with deep temporal modeling to learn interpretable and generalizable muscle fatigue dynamics from surface electromyography (sEMG). Unlike prior approaches that struggle to maintain robustness across varying Maximum Voluntary Contraction (MVC) levels due to signal variability and low SNR, FatigueFormer employs parallel Transformer-based sequence encoders to separately capture static and temporal feature dynamics, fusing their complementary representations to improve performance stability across low- and high-MVC conditions. Evaluated on a self-collected dataset spanning 30 participants across four MVC levels (20-80%), it achieves state-of-the-art accuracy and strong generalization under mild-fatigue conditions. Beyond performance, FatigueFormer enables attention-based visualization of fatigue dynamics, revealing how feature groups and time windows contribute differently across varying MVC levels, offering interpretable insight into fatigue progression.
Muscle fatigue detection plays an important role in physical rehabilitation. Previous researches have demonstrated that sEMG offers superior sensitivity in detecting muscle fatigue compared to other biological signals. However, features extracted from sEMG may vary during dynamic contractions and across different subjects, which causes unstability in fatigue detection. To address these challenges, this research proposes a novel neural network comprising an Inception-attention module as a feature extractor, a fatigue classifier and a domain classifier equipped with a gradient reversal layer. The integrated domain classifier encourages the network to learn subject-invariant common fatigue features while minimizing subject-specific features. Furthermore, a supervised contrastive loss function is also employed to enhance the generalization capability of the model. Experimental results demonstrate that the proposed model achieved outstanding performance in three-class classification tasks, reaching 93.54% accuracy, 92.69% recall and 92.69% F1-score, providing a robust solution for cross-subject muscle fatigue detection, offering significant guidance for rehabilitation training and assistance.
Zitao Lin, Chang Zhu, Wei Meng
School of Information Engineering, Wuhan University of Technology, Wuhan 430070, China
Investigating the impact of fatigue on human physiological function and motor behavior is crucial for developing biomechanics and medical applications aimed at mitigating fatigue, reducing injury risk, and creating sophisticated ergonomic designs, as well as for producing physically-plausible 3D animation sequences. While the former has a prominent position in state-of-the-art literature, fatigue-driven motion generation is still an underexplored area. In this study, we present FatigueFusion, a deep-learning architecture for the fusion of fatigue features within a latent representation space, enabling the creation of a variation of novel fatigued movements, intermediate fatigued states, and progressively fatigued motions. Unlike existing approaches that focus on imitating the effects of fatigue accumulation in motion patterns, our framework incorporates algorithmic and data-driven modules to impose subject-specific temporal and spatial fatigue features on nonfatigued motions, while leveraging PINN-based techniques to simulate fatigue intensity. Since all motion modulation tasks are taking place in latent space, FatigueFusion offers an end-to-end architecture that operates directly on non-fatigued joint angle sequences and control parameters, allowing seamless integration into any motion synthesis pipeline, without relying on fatigue input data. Overall, our framework can be employed for various fatigue-driven synthesis tasks, such as fatigue profile transfer and fusion, while it also provides a solution for accurate rendering of the human fatigue state in both animation and simulation pipelines.
Iliana Loi, Konstantinos Moustakas
Department of Electrical and Computer Engineering, University of Patras, Patras, 26504 Greece