GEGLU-Transformer for IMU-to-EMG Estimation with Few-Shot Adaptation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mihailovic, Miroljub, Tonin, Luca, Tortora, Stefano, Menegatti, Emanuele
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914514399657984
author Mihailovic, Miroljub
Tonin, Luca
Tortora, Stefano
Menegatti, Emanuele
author_facet Mihailovic, Miroljub
Tonin, Luca
Tortora, Stefano
Menegatti, Emanuele
contents Reliable estimation of neuromuscular activation is a key enabler for adaptive and personalized control in wearable robotics. However, surface electromyography (EMG) remains difficult to deploy robustly outside laboratory settings due to electrode sensitivity, signal non-stationarity, and strong subject dependence. In this work, we propose an adaptive IMU-to-EMG learning framework that reconstructs continuous muscle activation envelopes from wearable inertial measurements across heterogeneous movement conditions. The approach combines a Transformer encoder with Gaussian Error Gated Linear Units (GEGLU-Transformer) to enhance cross-subject generalization and enable rapid subject-specific personalization. Under a strict leave-one-subject-out (LOSO) protocol on a multi-condition lower-limb biomechanics dataset, the proposed architecture achieves r = 0.706 +/- 0.139 and R^2 = 0.474 +/- 0.208 without subject-specific adaptation. With only 0.5% adaptation data, performance increases to r = 0.761 +/- 0.030 and R^2 = 0.559 +/- 0.047, demonstrating rapid adaptation and early performance saturation. These results support attention-based architectures combined with lightweight adaptation as a practical and scalable alternative to direct EMG sensing for real-world wearable robotic applications.
format Preprint
id arxiv_https___arxiv_org_abs_2604_25670
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GEGLU-Transformer for IMU-to-EMG Estimation with Few-Shot Adaptation
Mihailovic, Miroljub
Tonin, Luca
Tortora, Stefano
Menegatti, Emanuele
Robotics
Reliable estimation of neuromuscular activation is a key enabler for adaptive and personalized control in wearable robotics. However, surface electromyography (EMG) remains difficult to deploy robustly outside laboratory settings due to electrode sensitivity, signal non-stationarity, and strong subject dependence. In this work, we propose an adaptive IMU-to-EMG learning framework that reconstructs continuous muscle activation envelopes from wearable inertial measurements across heterogeneous movement conditions. The approach combines a Transformer encoder with Gaussian Error Gated Linear Units (GEGLU-Transformer) to enhance cross-subject generalization and enable rapid subject-specific personalization. Under a strict leave-one-subject-out (LOSO) protocol on a multi-condition lower-limb biomechanics dataset, the proposed architecture achieves r = 0.706 +/- 0.139 and R^2 = 0.474 +/- 0.208 without subject-specific adaptation. With only 0.5% adaptation data, performance increases to r = 0.761 +/- 0.030 and R^2 = 0.559 +/- 0.047, demonstrating rapid adaptation and early performance saturation. These results support attention-based architectures combined with lightweight adaptation as a practical and scalable alternative to direct EMG sensing for real-world wearable robotic applications.
title GEGLU-Transformer for IMU-to-EMG Estimation with Few-Shot Adaptation
topic Robotics
url https://arxiv.org/abs/2604.25670