EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Multi-Task Grasp Detection Network Based on Global Channel–Spatial Attention Mechanism for Industrial Workshop Environments

Shengze Zhang, Zhaochun Li, Yucheng Wang, Shuyou Wang

Sensors · 19.08.2026 · 26 (16) · 5257

DOI: 10.3390/s26165257 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.08.2026. Verfasst von Shengze Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Jiangsu Frontier Technology Research and Development Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To improve the accuracy and robustness of target grasp detection and classification for robotic manipulators in unstructured environments such as workshops, a multi-task grasp detection algorithm based on a global channel–spatial attention mechanism is proposed. Through the global channel attention module, the network is able to extract richer semantic information while reducing redundant feature information, thereby improving overall performance. The effectiveness of the proposed algorithm is validated on the Cornell dataset and a self-built dataset. The grasp prediction accuracy reaches 99.5% on the Cornell dataset, while on the self-built dataset the grasp detection accuracy reaches 98.5% and the object classification accuracy reaches 99.5%. To further verify the effectiveness of the algorithm, grasping experiments are conducted on an AUBO-i3 robotic manipulator. The results show that the average grasping accuracy reaches 95% for unseen daily items and common workshop objects, which is 8.75% higher than the baseline GGCNN network. These results indicate that the proposed algorithm can effectively perform grasping tasks for robotic manipulators in unstructured environments.

Schlagwörter

Stichwörter der Autor:innen

RGB-D 3D localizationeye-in-hand calibrationfeature reconstructionmulti-task learningrobotic manipulationworkshop object perception

Autor:innen und Institutionen

  • College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China.
  • Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China.

Förderung

  • National Natural Science Foundation of China
  • Jiangsu Frontier Technology Research and Development Program

Zitieren

APA

Zhang, S., Li, Z., Wang, Y., & Wang, S. (2026). A Multi-Task Grasp Detection Network Based on Global Channel–Spatial Attention Mechanism for Industrial Workshop Environments. Sensors, 26(16), 5257. https://doi.org/10.3390/s26165257

Vancouver

Zhang S, Li Z, Wang Y, Wang S. A Multi-Task Grasp Detection Network Based on Global Channel–Spatial Attention Mechanism for Industrial Workshop Environments. Sensors. 2026;26(16):5257. doi:10.3390/s26165257

BibTeX
@article{Zhang2026,
  author = {Zhang, Shengze and Li, Zhaochun and Wang, Yucheng and Wang, Shuyou},
  title = {A Multi-Task Grasp Detection Network Based on Global Channel–Spatial Attention Mechanism for Industrial Workshop Environments},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {16},
  pages = {5257},
  doi = {10.3390/s26165257}
}
Kostenlos starten →