EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human–Robot Variable-Impedance Skill Transfer Learning Based on Dynamic Movement Primitives and a Vision System

Honghui Zhang iD, Fang Peng iD, Miaozhe Cai iD

Sensors · 10.09.2025 · 25 (18) · 5630

DOI: 10.3390/s25185630 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.09.2025. Verfasst von Honghui Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Zhongshan Institute, Zhongshan 528400, Chi…. Hauptthemen laut MEDLINE: Robotics, Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Social Public Welfare and Basic Research Project 361 of Zhongshan City, Bureau of Science and Technology of Zhongshan City (Social Public Welfare and Basic Research Project of Zhongshan City).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To enhance robotic adaptability in dynamic environments, this study proposes a multimodal framework for skill transfer. The framework integrates vision-based kinesthetic teaching with surface electromyography (sEMG) signals to estimate human impedance. We establish a Cartesian-space model of upper-limb stiffness, linearly mapping sEMG signals to end-point stiffness. For flexible task execution, dynamic movement primitives (DMPs) generalize learned skills across varying scenarios. An adaptive admittance controller, incorporating sEMG-modulated stiffness, is developed and validated on a UR5 robot. Experiments involving elastic-band stretching demonstrate that the system successfully transfers human impedance characteristics to the robot, enhancing stability, environmental adaptability, and safety during physical interaction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RoboticsLearningHumansElectromyographyMovementElectric Impedance

Stichwörter der Autor:innen

dynamic movement primitives (DMPs)imitation learningstiffness estimationsurface electromyography (sEMG)

Autor:innen und Institutionen

  • School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Zhongshan Institute, Zhongshan 528400, China.
  • School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.
  • Faculty of Applied Sciences, Macao Polytechnic University, Macau 999078, China.

ORCID-Profile: Honghui Zhang, Fang Peng, Miaozhe Cai

Förderung

  • the Social Public Welfare and Basic Research Project 361 of Zhongshan City
  • Bureau of Science and Technology of Zhongshan City (Social Public Welfare and Basic Research Project of Zhongshan City)

Zitieren

APA

Zhang, H., Peng, F., & Cai, M. (2025). Human–Robot Variable-Impedance Skill Transfer Learning Based on Dynamic Movement Primitives and a Vision System. Sensors, 25(18), 5630. https://doi.org/10.3390/s25185630

Vancouver

Zhang H, Peng F, Cai M. Human–Robot Variable-Impedance Skill Transfer Learning Based on Dynamic Movement Primitives and a Vision System. Sensors. 2025;25(18):5630. doi:10.3390/s25185630

BibTeX
@article{Zhang2025,
  author = {Zhang, Honghui and Peng, Fang and Cai, Miaozhe},
  title = {Human–Robot Variable-Impedance Skill Transfer Learning Based on Dynamic Movement Primitives and a Vision System},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {18},
  pages = {5630},
  doi = {10.3390/s25185630}
}
Kostenlos starten →