ReactEMG: Stable, Low-Latency Intent Detection from sEMG via Masked Modeling

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Runsheng, Zhu, Xinyue, Chen, Ava, Xu, Jingxi, Winterbottom, Lauren, Nilsen, Dawn M., Stein, Joel, Ciocarlie, Matei
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909918660919296
author Wang, Runsheng
Zhu, Xinyue
Chen, Ava
Xu, Jingxi
Winterbottom, Lauren
Nilsen, Dawn M.
Stein, Joel
Ciocarlie, Matei
author_facet Wang, Runsheng
Zhu, Xinyue
Chen, Ava
Xu, Jingxi
Winterbottom, Lauren
Nilsen, Dawn M.
Stein, Joel
Ciocarlie, Matei
contents Surface electromyography (sEMG) signals show promise for effective human-machine interfaces, particularly in rehabilitation and prosthetics. However, challenges remain in developing systems that respond quickly to user intent, produce stable flicker-free output suitable for device control, and work across different subjects without time-consuming calibration. In this work, we propose a framework for EMG-based intent detection that addresses these challenges. We cast intent detection as per-timestep segmentation of continuous sEMG streams, assigning labels as gestures unfold in real time. We introduce a masked modeling training strategy that aligns muscle activations with their corresponding user intents, enabling rapid onset detection and stable tracking of ongoing gestures. In evaluations against baseline methods, using metrics that capture accuracy, latency and stability for device control, our approach achieves state-of-the-art performance in zero-shot conditions. These results demonstrate its potential for wearable robotics and next-generation prosthetic systems. Our project website, video, code, and dataset are available at: https://reactemg.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2506_19815
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReactEMG: Stable, Low-Latency Intent Detection from sEMG via Masked Modeling
Wang, Runsheng
Zhu, Xinyue
Chen, Ava
Xu, Jingxi
Winterbottom, Lauren
Nilsen, Dawn M.
Stein, Joel
Ciocarlie, Matei
Robotics
Surface electromyography (sEMG) signals show promise for effective human-machine interfaces, particularly in rehabilitation and prosthetics. However, challenges remain in developing systems that respond quickly to user intent, produce stable flicker-free output suitable for device control, and work across different subjects without time-consuming calibration. In this work, we propose a framework for EMG-based intent detection that addresses these challenges. We cast intent detection as per-timestep segmentation of continuous sEMG streams, assigning labels as gestures unfold in real time. We introduce a masked modeling training strategy that aligns muscle activations with their corresponding user intents, enabling rapid onset detection and stable tracking of ongoing gestures. In evaluations against baseline methods, using metrics that capture accuracy, latency and stability for device control, our approach achieves state-of-the-art performance in zero-shot conditions. These results demonstrate its potential for wearable robotics and next-generation prosthetic systems. Our project website, video, code, and dataset are available at: https://reactemg.github.io/
title ReactEMG: Stable, Low-Latency Intent Detection from sEMG via Masked Modeling
topic Robotics
url https://arxiv.org/abs/2506.19815