sEMG-Based Continues Motion Prediction of Shoulder exoskeleton Control Using the VGANet Model
Tongxin Jiang, Fuhai Zhang, Lei Yang, Tianyang Wu, Yili Fu
Abstract
Wearable exoskeleton robots play a crucial role in promoting upper limb function recovery. To enhance human-robot interaction and achieve precise control, continuous prediction of limb joint angles is required. This paper proposes a decoupled network model (VGANet) based on Variable Graph Convolutional Networks (V-GCN) and Temporal External Attention (TEA) for motion prediction in upper limb rehabilitation training. By establishing a mapping relationship between surface electromyography (sEMG) signals and upper limb movements, the model can predict future joint angles based on real-time sEMG signals. Experimental results demonstrate that this method can achieve continuous motion prediction for the shoulder joint and has been successfully applied to the control system of exoskeleton robots, providing an effective solution for the intelligent development of rehabilitation exoskeletons.
BibTeX
@inproceedings{iros2025_semgbasedcontinu,
title = {sEMG-Based Continues Motion Prediction of Shoulder exoskeleton Control Using the VGANet Model},
author = {Tongxin Jiang and Fuhai Zhang and Lei Yang and Tianyang Wu and Yili Fu},
booktitle = {IROS 2025},
year = {2025}
}