EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robotic Arm Trajectory Planning in Dynamic Environments Based on Self-Optimizing Replay Mechanism

Pengyao Xu, Chong Di, Jiandong Lv, Peng Zhao, Chao Chen, Ruotong Wang

Sensors · 29.07.2025 · 25 (15) · 4681

DOI: 10.3390/s25154681 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.07.2025. Verfasst von Pengyao Xu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shandong Provincial Natural Science Foundation project, National Natural Science Foundation of China, Qilu University of Technology (Shandong Academy of Sciences) Talent Research Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In complex dynamic environments, robotic arms face multiple challenges such as real-time environmental changes, high-dimensional state spaces, and strong uncertainties. Trajectory planning tasks based on deep reinforcement learning (DRL) suffer from difficulties in acquiring human expert strategies, low experience utilization (leading to slow convergence), and unreasonable reward function design. To address these issues, this paper designs a neural network-based expert-guided triple experience replay mechanism (NETM) and proposes an improved reward function adapted to dynamic environments. This replay mechanism integrates imitation learning’s fast data fitting with DRL’s self-optimization to expand limited expert demonstrations and algorithm-generated successes into optimized expert experiences. Experimental results show the expanded expert experience accelerates convergence: in dynamic scenarios, NETM boosts accuracy by over 30% and safe rate by 2.28% compared to baseline algorithms.

Schlagwörter

Stichwörter der Autor:innen

dynamic environmentexperience replay mechanismreward function designrobotic manipulation

Autor:innen und Institutionen

  • Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China.
  • College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China.

Förderung

  • Shandong Provincial Natural Science Foundation project
  • National Natural Science Foundation of China
  • Qilu University of Technology (Shandong Academy of Sciences) Talent Research Project
  • JiNan 20 new colleges and universities
  • Open project of the Key Laboratory of Computing Power Internet and Information Security of the Ministry of Education

Zitieren

APA

Xu, P., Di, C., Lv, J., Zhao, P., Chen, C., & Wang, R. (2025). Robotic Arm Trajectory Planning in Dynamic Environments Based on Self-Optimizing Replay Mechanism. Sensors, 25(15), 4681. https://doi.org/10.3390/s25154681

Vancouver

Xu P, Di C, Lv J, Zhao P, Chen C, Wang R. Robotic Arm Trajectory Planning in Dynamic Environments Based on Self-Optimizing Replay Mechanism. Sensors. 2025;25(15):4681. doi:10.3390/s25154681

BibTeX
@article{Xu2025,
  author = {Xu, Pengyao and Di, Chong and Lv, Jiandong and Zhao, Peng and Chen, Chao and Wang, Ruotong},
  title = {Robotic Arm Trajectory Planning in Dynamic Environments Based on Self-Optimizing Replay Mechanism},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {15},
  pages = {4681},
  doi = {10.3390/s25154681}
}
Kostenlos starten →