SA-Grasp: A self-attention mechanism based lightweight grasp pose detection network
International Journal of Intelligent Robotics and Applications · 2026-06 · 10 (2) · 779-794
DOI: 10.1007/s41315-026-00527-w ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Intelligent Robotics and Applications, online erschienen am 31.03.2026. Verfasst von Quan-cheng Pu und 3 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Gefördert von: Anhui University of Technology youth Fund, National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
In response to the current convolutional neural network-based robotic arm grasp pose detection networks being susceptible to interference from redundant information, and the tendency to misjudge object contour areas as grasping execution poses , leading to low grasping success rates of robotic arms, this paper introduces SA-Grasp, a lightweight convolutional neural network for robotic arm grasping that integrates self-attention mechanism. It reduces interference from redundant information and improves grasping accuracy. SA-Grasp achieved high detection accuracies of 98.37% on Cornell and 96.33% on Jacquard datasets, with a fast detection time of 21 ms per image. In real-world tests, it demonstrated a 94.44% success rate across 180 grasping attempts on 9 unknown objects, demonstrating its reliability. SA-Grasp is a lightweight visual grasp pose detection network characterized by high grasping success rates and fast speeds, providing a new approach for the application of self-attention mechanism in the field of robotic arm visual grasping.
Förderung
- Anhui University of Technology youth Fund
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Pu, Q., Zhang, H., Yang, L., & Li, T. (2026). SA-Grasp: A self-attention mechanism based lightweight grasp pose detection network. International Journal of Intelligent Robotics and Applications, 10(2), 779-794. https://doi.org/10.1007/s41315-026-00527-w
Vancouver
Pu Q, Zhang H, Yang L, Li T. SA-Grasp: A self-attention mechanism based lightweight grasp pose detection network. International Journal of Intelligent Robotics and Applications. 2026;10(2):779-794. doi:10.1007/s41315-026-00527-w
BibTeX
@article{Pu2026,
author = {Pu, Quan-cheng and Zhang, Hui and Yang, Lu and Li, Tie-shan},
title = {SA-Grasp: A self-attention mechanism based lightweight grasp pose detection network},
journal = {International Journal of Intelligent Robotics and Applications},
year = {2026},
volume = {10},
number = {2},
pages = {779--794},
doi = {10.1007/s41315-026-00527-w}
}
EUVIMED