EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robot End-Effectors Adaptive Design Method Based on Embedding Domain Knowledge into Reinforcement Learning

Yong Zhu, Taihua Zhang, Yao Lu, Liguo Yao

Sensors · 19.03.2026 · 26 (6) · 1933

DOI: 10.3390/s26061933 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.03.2026. Verfasst von Yong Zhu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical and Electrical Engineering, Guizhou Normal University, Guiyang 550025, China. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Taihua Zhang, National Natural Science Foundation, Science and Technology Platform Project of Guizhou Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing robot end-effectors design methods lack structured domain prior knowledge support and have insufficient interaction with the environment, making it difficult to guarantee the accuracy of the design results. An adaptive design method is proposed that deeply embeds domain knowledge of end effectors into the design process, treats key design parameters as environmental variables, and optimizes them adaptively through reinforcement learning algorithms in perception and feedback. In a simulation environment constructed by combining a knowledge graph, a two-finger translational gripper is used as an example robot end-effector to acquire target data via sensors, and reinforcement learning is used to adaptively optimize the gripper’s key parameters. Experiments are conducted on a simulation platform with three typical tasks, yielding the optimal parameter range. Compared to the proximal policy optimization (PPO) algorithm, which has no prior knowledge input, the knowledge graph embedding proximal policy optimization (KGPPO) algorithm improves the average reward for gripper length and gripper force by 63.96% and 43.09%, respectively, for grasping eggs. The KGPPO algorithm achieves the highest average reward and the best stability compared with other algorithms. Experiments show that this method can significantly improve the efficiency, stability, and accuracy of design parameter optimization.

Schlagwörter

Stichwörter der Autor:innen

adaptive designenvironmental interactionknowledge graphreinforcement learningrobot end-effector

Autor:innen und Institutionen

  • School of Mechanical and Electrical Engineering, Guizhou Normal University, Guiyang 550025, China.
  • Guizhou Key Laboratory of NewGen Cyberspace Security, Guizhou Normal University, Guiyang 550025, China.
  • Technical Engineering Center of Manufacturing Service and Knowledge Engineering, Guizhou Normal University, Guiyang 550025, China.

Förderung

  • Taihua Zhang
  • National Natural Science Foundation
  • Science and Technology Platform Project of Guizhou Province

Zitieren

APA

Zhu, Y., Zhang, T., Lu, Y., & Yao, L. (2026). Robot End-Effectors Adaptive Design Method Based on Embedding Domain Knowledge into Reinforcement Learning. Sensors, 26(6), 1933. https://doi.org/10.3390/s26061933

Vancouver

Zhu Y, Zhang T, Lu Y, Yao L. Robot End-Effectors Adaptive Design Method Based on Embedding Domain Knowledge into Reinforcement Learning. Sensors. 2026;26(6):1933. doi:10.3390/s26061933

BibTeX
@article{Zhu2026,
  author = {Zhu, Yong and Zhang, Taihua and Lu, Yao and Yao, Liguo},
  title = {Robot End-Effectors Adaptive Design Method Based on Embedding Domain Knowledge into Reinforcement Learning},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {6},
  pages = {1933},
  doi = {10.3390/s26061933}
}
Kostenlos starten →