EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human-like Dexterous Grasping Through Reinforcement Learning and Multimodal Perception

Wen Qi iD, Haoyu Fan, Cankun Zheng, Hang Su iD, Samer Alfayad

Biomimetics · 18.03.2025 · 10 (3) · 186

DOI: 10.3390/biomimetics10030186 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomimetics, online erschienen am 18.03.2025. Verfasst von Wen Qi und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Future Technology, South China University of Technology, Guangzhou 511442, China. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Nature Science Foundation of China, Guangdong Provincial Key Laboratory of Human Digital Twin.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dexterous robotic grasping with multifingered hands remains a critical challenge in non-visual environments, where diverse object geometries and material properties demand adaptive force modulation and tactile-aware manipulation. To address this, we propose the Reinforcement Learning-Based Multimodal Perception (RLMP) framework, which integrates human-like grasping intuition through operator-worn gloves with tactile-guided reinforcement learning. The framework’s key innovation lies in its Tactile-Driven DCNN architecture—a lightweight convolutional network achieving 98.5% object recognition accuracy using spatiotemporal pressure patterns—coupled with an RL policy refinement mechanism that dynamically correlates finger kinematics with real-time tactile feedback. Experimental results demonstrate reliable grasping performance across deformable and rigid objects while maintaining force precision critical for fragile targets. By bridging human teleoperation with autonomous tactile adaptation, RLMP eliminates dependency on visual input and predefined object models, establishing a new paradigm for robotic dexterity in occlusion-rich scenarios.

Schlagwörter

Stichwörter der Autor:innen

hand gesture recognitionhuman-robot interactionmultimodal perceptionreinforcement learningtactile feedback

Autor:innen und Institutionen

  • School of Future Technology, South China University of Technology, Guangzhou 511442, China.
  • The IBISC Laboratory, UEVE, University of Paris-Saclay, 91000 Evry, France.

ORCID-Profile: Wen Qi, Hang Su

Förderung

  • National Nature Science Foundation of China
  • Guangdong Provincial Key Laboratory of Human Digital Twin

Zitieren

APA

Qi, W., Fan, H., Zheng, C., Su, H., & Alfayad, S. (2025). Human-like Dexterous Grasping Through Reinforcement Learning and Multimodal Perception. Biomimetics, 10(3), 186. https://doi.org/10.3390/biomimetics10030186

Vancouver

Qi W, Fan H, Zheng C, Su H, Alfayad S. Human-like Dexterous Grasping Through Reinforcement Learning and Multimodal Perception. Biomimetics. 2025;10(3):186. doi:10.3390/biomimetics10030186

BibTeX
@article{Qi2025,
  author = {Qi, Wen and Fan, Haoyu and Zheng, Cankun and Su, Hang and Alfayad, Samer},
  title = {Human-like Dexterous Grasping Through Reinforcement Learning and Multimodal Perception},
  journal = {Biomimetics},
  year = {2025},
  volume = {10},
  number = {3},
  pages = {186},
  doi = {10.3390/biomimetics10030186}
}
Kostenlos starten →