Towards Real-World Identification of Fatigued Muscle Groups Via Musculoskeletal Simulation
Jenishkumar Chauhan, Samarth Brahmbhatt, Vineet Vashista
AI summary
Problem
Current musculoskeletal fatigue diagnosis relies on invasive sensors or in-person clinical exams, leaving a gap for scalable, contactless real-world monitoring.
Approach
The method uses a physics-based musculoskeletal simulator to generate kinematic data under simulated fatigue conditions, then compares joint-wise motion deviations from real motion capture to pinpoint the impaired muscle group.
Key results
- Configured a general-purpose musculoskeletal simulator to bridge the sim-to-real gap for fatigue diagnosis
- Developed a 60-dimensional kinematic feature vector quantifying joint-wise healthy-to-fatigued deviations
- Reliably identified specific fatigued upper-limb muscle groups using real participant motion capture data
- Validated simulation-to-reality alignment by tuning fatigue factors to match real-world muscle activation ratios
Why it matters
Enables scalable, non-invasive remote monitoring of musculoskeletal fatigue for clinical screening, rehabilitation, and human-robot collaboration.
Abstract
Contactless diagnosis of musculoskeletal disorders can potentially improve population health as well as robot behaviours in collaborative settings. However, current diagnosis methods require an in-person physical examination in which a trained physician senses, through contact, the force applied by various muscles. Simulation tools exist, but their use for diagnosis with real data is under-explored. In this paper, we propose an algorithm for identifying which upper-limb muscle group is fatigued. Our algorithm compares the real-world free-space motion of the subject with that of a simulated musculoskeletal model, and is therefore contactless: preventing the need for invasive sensing or in-person assessment. Our algo- rithm simulates various fatigue conditions using a physics-based musculoskeletal model and extracts diagnostic motion features from both real and simulated data, which are compared for diagnosis. Experimental results on real data demonstrate that the proposed method can reliably distinguish between multiple muscle-groups of fatigue. Additionally, through comprehensive performance comparisons, we show how recent advanced mus- culoskeletal simulators can be properly configured to address the sim-to-real gap in the context of the fatigue diagnosis task. Our approach can potentially spur further research in remote and automated diagnosis, significantly lowering the barrier to large-scale and early detection.