Bionic soft robotic glove with EMG-based gesture and grip strength synchronized prediction for grasping assistance

• Published in: Biomedical signal processing and control Vol. 112; p. 108516
• Main Authors: Zhang, Jing, Zhu, Aibin, Bao, Bingsheng, Li, Meng, Zhang, Yu, Wang, Jing, Wu, Xinyu, Zheng, Chunli, Li, Xiao
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.02.2026
• Subjects: EMG; Gesture recognition; Grip strength estimation; Tendon-sheath mechanism; Transfer learning; Wearable robotic glove; Wearable robotic glove; Tendon-sheath mechanism; Transfer learning; Grip strength estimation; EMG; Gesture recognition
• ISSN: 1746-8094
• DOI: 10.1016/j.bspc.2025.108516

Wearable hand-assistive robotics play an important role in aiding elderly patients with hand dysfunction, where accurate gesture recognition and grip strength estimation are essential for natural human–robot interaction. However, few studies have tackled both tasks simultaneously. Inspired by the biological tendon-muscle system, this work introduces a soft robotic glove actuated by tendon-sheath artificial muscles. The system features an EMG-based controller that provides real-time assistance by jointly predicting hand gestures and grip strength using a GRU-based domain-adversarial neural network with a composite loss function, enabling combined classification and regression from shared EMG features. The model achieved 92.12% gesture classification accuracy and an R2 of 0.935 within subjects, and 79.43% accuracy with an R2 of 0.80 across subjects. Real-time testing with an unseen user further confirmed the model’s robustness, achieving 80.94% accuracy and an R2 of 0.86. The soft robotic glove also significantly reduced forearm flexor muscle activity by up to 46.9% during grasping tasks, demonstrating effective assistance. Overall, this EMG-driven soft robotic glove offers personalized, adaptive, and precise hand support, showing strong potential to enhance autonomy and quality of life for elderly users. •Bionic actuator mimics muscle–tendon biomechanics for natural movement.•Joint-free soft robotic glove enhances comfort and portability.•EMG-based GRU-DANN model predicts gestures and grip strength simultaneously.•Significantly reduces forearm flexor muscle effort during grasping tasks.