EUVIMEDEUVIMED entdecken
Crossref

Electromyography-Driven Dynamic Arm Force Estimation Model for Human–Robot Interaction

Hanlei Sun, Keting Li, Ningbo Yu, Jianda Han

IEEE Transactions on Instrumentation and Measurement · 2026 · 75 · 1-14

DOI: 10.1109/tim.2026.3671916 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2026. Verfasst von Hanlei Sun und 3 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Postdoctoral Fellowship Program of the China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electromyography (EMG) provides a natural and intuitive interface for human–robot interaction (HRI). However, the complexity of muscle activation patterns induced by dynamic arm movements continues to hinder the accuracy of existing EMG-driven dynamic arm force estimation models. To address these limitations and enhance both estimation precision and interaction performance in dynamic HRI scenarios, a novel EMG-driven dynamic force estimation model and a tailored training methodology are proposed. To account for the dual effects of arm posture on EMG signal amplitude and intermuscle coordination, an arm posture-based EMG signal compensation module is introduced. This module compensates for motion-induced distortions in the EMG–force relationship, thereby improving the accuracy of dynamic force estimation. Furthermore, to reduce nonlinear interference caused by noise, electrode displacement, and limited data coverage in dynamic tasks, a universal model meta-learning (UMML)-based training algorithm is developed. This approach enhances both the generalization capability and training efficiency of the model. The proposed dynamic force estimation framework is integrated into a robotic control system and validated through real-world HRI trajectory tracking experiments employing an adaptive admittance control strategy. Experimental results show that, compared to state-of-the-art force estimation methods, the proposed approach achieves significant improvements in model convergence, estimation accuracy, and interaction performance. These results validate the feasibility of the proposed model as an effective interface for multidimensional, dynamic HRI.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Postdoctoral Fellowship Program of the China Postdoctoral Science Foundation

Zitieren

APA

Sun, H., Li, K., Yu, N., & Han, J. (2026). Electromyography-Driven Dynamic Arm Force Estimation Model for Human–Robot Interaction. IEEE Transactions on Instrumentation and Measurement, 75, 1-14. https://doi.org/10.1109/tim.2026.3671916

Vancouver

Sun H, Li K, Yu N, Han J. Electromyography-Driven Dynamic Arm Force Estimation Model for Human–Robot Interaction. IEEE Transactions on Instrumentation and Measurement. 2026;75:1-14. doi:10.1109/tim.2026.3671916

BibTeX
@article{Sun2026,
  author = {Sun, Hanlei and Li, Keting and Yu, Ningbo and Han, Jianda},
  title = {Electromyography-Driven Dynamic Arm Force Estimation Model for Human–Robot Interaction},
  journal = {IEEE Transactions on Instrumentation and Measurement},
  year = {2026},
  volume = {75},
  pages = {1--14},
  doi = {10.1109/tim.2026.3671916}
}
Kostenlos starten →