![[2602.15684] Estimating Human Muscular Fatigue in Dynamic Collaborative Robotic Tasks with Learning-Based Models](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.15684] Estimating Human Muscular Fatigue in Dynamic Collaborative Robotic Tasks with Learning-Based Models
Summary
This article presents a data-driven framework for estimating human muscular fatigue during collaborative robotic tasks using machine learning models, enhancing safety and performance in human-robot interactions.
Why It Matters
As robotics increasingly integrates into collaborative environments, understanding human fatigue is crucial for optimizing safety and efficiency. This research provides a foundation for developing adaptive robotic systems that can respond to human fatigue levels, potentially transforming human-robot collaboration.
Key Takeaways
- The study introduces a framework to estimate human muscular fatigue using surface electromyography (sEMG).
- Machine learning models, including CNNs and tree-based methods, effectively predict fatigue levels with varying degrees of accuracy.
- The research highlights the importance of framing fatigue estimation as a regression problem for continuous monitoring.
- Results indicate robustness in fatigue estimation across different movement patterns without the need for retraining.
- The findings suggest potential applications in fatigue-aware robotic systems for improved operator safety.
Computer Science > Robotics arXiv:2602.15684 (cs) [Submitted on 17 Feb 2026] Title:Estimating Human Muscular Fatigue in Dynamic Collaborative Robotic Tasks with Learning-Based Models Authors:Feras Kiki, Pouya P. Niaz, Alireza Madani, Cagatay Basdogan View a PDF of the paper titled Estimating Human Muscular Fatigue in Dynamic Collaborative Robotic Tasks with Learning-Based Models, by Feras Kiki and 3 other authors View PDF HTML (experimental) Abstract: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...
