EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DRFW-TQC: Reinforcement Learning for Robotic Strawberry Picking with Dynamic Regularization and Feature Weighting

Anping Zheng, Zirui Fang, Zixuan Li, Hao Dong, Ke Li

AgriEngineering · 02.07.2025 · 7 (7) · 208

DOI: 10.3390/agriengineering7070208 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AgriEngineering, online erschienen am 02.07.2025. Verfasst von Anping Zheng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, University Synergy Innovation Program of Anhui Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Strawberry harvesting represents a labor-intensive agricultural operation where existing end-effector pose control algorithms frequently exhibit insufficient precision in fruit grasping, often resulting in unintended damage to target fruits. Concurrently, deep learning-based pose control algorithms suffer from inherent training instability, slow convergence rates, and inefficient learning processes in complex environments characterized by high-density fruit clusters and occluded picking scenarios. To address these challenges, this paper proposes an enhanced reinforcement learning framework DRFW-TQC that integrates Dynamic L2 Regularization for adaptive model stabilization and a Group-Wise Feature Weighting Network for discriminative feature representation. The methodology further incorporates a picking posture traction mechanism to optimize end-effector orientation control. The experimental results demonstrate the superior performance of DRFW-TQC compared to the baseline. The proposed approach achieves a 16.0% higher picking success rate and a 20.3% reduction in angular error with four target strawberries. Most notably, the framework’s transfer strategy effectively addresses the efficiency challenge in complex environments, maintaining an 89.1% success rate in eight-strawberry while reducing the timeout count by 60.2% compared to non-adaptive methods. These results confirm that DRFW-TQC successfully resolves the tripartite challenge of operational precision, training stability, and environmental adaptability in robotic fruit harvesting systems.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • University Synergy Innovation Program of Anhui Province
  • Anhui Provincial Quality Engineering Project of Higher Education Institutions
  • Anhui Agricultural University Introduction and Stabilization of Talents Research Funding

Zitieren

APA

Zheng, A., Fang, Z., Li, Z., Dong, H., & Li, K. (2025). DRFW-TQC: Reinforcement Learning for Robotic Strawberry Picking with Dynamic Regularization and Feature Weighting. AgriEngineering, 7(7), 208. https://doi.org/10.3390/agriengineering7070208

Vancouver

Zheng A, Fang Z, Li Z, Dong H, Li K. DRFW-TQC: Reinforcement Learning for Robotic Strawberry Picking with Dynamic Regularization and Feature Weighting. AgriEngineering. 2025;7(7):208. doi:10.3390/agriengineering7070208

BibTeX
@article{Zheng2025,
  author = {Zheng, Anping and Fang, Zirui and Li, Zixuan and Dong, Hao and Li, Ke},
  title = {DRFW-TQC: Reinforcement Learning for Robotic Strawberry Picking with Dynamic Regularization and Feature Weighting},
  journal = {AgriEngineering},
  year = {2025},
  volume = {7},
  number = {7},
  pages = {208},
  doi = {10.3390/agriengineering7070208}
}
Kostenlos starten →