Data-Centric Neuromotor Interfaces for Portable Human-Machine Interaction
2026-08-31 • Robotics
Robotics
AI summaryⓘ
The authors created a smart, flexible system that reads muscle signals to understand hand movements. They built a wireless device with special sensors that collect clear muscle data and used a small, efficient computer model to recognize 34 different gestures with over 94% accuracy. This model is lightweight enough to work quickly on small, portable devices, making it practical for everyday use. Their work shows an effective way to combine good data and simple algorithms for reliable, real-world human-machine interaction.
surface electromyography (sEMG)neuromotor interfacewearable electronicsedge computinggesture recognitionflexible sensorsphysiological signalsdata-centric paradigmmachine learning modelhuman-machine interaction
Authors
Jiaxuan Li, Di Wu, Jianhua Liu, Yuxin Zhao, Jinnuo Li, Xiao Zhang, Zhenzhi Ying, Changsheng Dai, Xiang Li, Liming Shu
Abstract
Dexterous human-machine interaction requires intuitive and expressive interfaces that can be efficiently deployed on constrained edge devices. Flexible material-based neuromotor interfaces hold considerable promise, as they decode human movement intention into natural control. Although emerging flexible electronic skins enable wearable high-fidelity data acquisition, practical deployment inevitably involves trade-offs between computational resources and portability. We present a data-centric paradigm where physiological features yield fundamental separability, providing sufficient discriminative cues for recognition. A wireless, high-bandwidth system developed for collecting various electrophysiological signals, when integrated with muscle-specific electrodes, forms a surface electromyography-based interface. Exploiting highly separable data, a 2,210-parameter model achieves 94.36% accuracy across 34 gestures and can be rapidly deployed on edge devices, establishing a new thousand-parameter benchmark for dexterous decoding. The underlying data-algorithm interactions in the data-centric paradigm are further clarified, demonstrating its feasibility in real-world scenarios. This study provides a principled and validated pathway for practical deployment of reliable neuromotor interfaces.