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

TL;DR

ReactEMG introduces a masked modeling approach for real-time, stable, and low-latency intent detection from surface electromyography signals, enhancing human-machine interface responsiveness and stability across subjects.

Contribution

The paper presents a novel masked modeling training strategy for sEMG-based intent detection, enabling rapid, stable, and zero-shot gesture recognition without extensive calibration.

Findings

Achieves state-of-the-art accuracy in zero-shot conditions

Demonstrates low latency and stable gesture tracking

Outperforms baseline methods in real-time intent detection

Abstract

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/