EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Decoupled Detection and Category-Level 6D Pose Estimation for Robot Grasping

Chia-Tse Lai, Chen-Chien Hsu, Shao-Kang Huang, Yin-Tien Wang

Electronics · 17.04.2026 · 15 (8) · 1706

DOI: 10.3390/electronics15081706 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 17.04.2026. Verfasst von Chia-Tse Lai und 3 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

6D object pose estimation is an essential component for robotic grasping. Most existing deep learning-based approaches focus on instance-level pose estimation, which requires prior object models and consequently limits their applicability on unseen objects in real-world scenarios. In contrast, category-level 6D pose estimation adopts Normalized Object Coordinate Space (NOCS) maps to represent intra-class object geometry, enabling pose prediction without relying on predefined object models and thus improving generalization to unseen instances. However, the original NOCS-based category-level framework typically trains NOCS prediction and object classification in a joint manner, which introduces NOCS regression error among inter-class instances with similar appearances, thereby degrading pose estimation accuracy. To address this issue, we integrate the YOLOv8 object detection with SegFormer and propose a novel Category-Level SegFormer for 6D Object Pose Estimation (CLSF-6DPE). By decoupling object classification from NOCS regression through independent learning branches, the proposed framework significantly improves pose estimation performance. Furthermore, we validate the practical feasibility of CLSF-6DPE by integrating it with a robotic gripper via the Robot Operating System (ROS) in a Real-World grasping setup. Experimental results on the CAMERA and Real-World datasets demonstrate that the proposed method achieves mAP scores of 93.8% and 81.1%, respectively. Overall, the proposed method provides a modular and effective solution for category-level pose estimation in real-world robotic grasping applications.

Förderung

  • National Science and Technology Council

Zitieren

APA

Lai, C., Hsu, C., Huang, S., & Wang, Y. (2026). Decoupled Detection and Category-Level 6D Pose Estimation for Robot Grasping. Electronics, 15(8), 1706. https://doi.org/10.3390/electronics15081706

Vancouver

Lai C, Hsu C, Huang S, Wang Y. Decoupled Detection and Category-Level 6D Pose Estimation for Robot Grasping. Electronics. 2026;15(8):1706. doi:10.3390/electronics15081706

BibTeX
@article{Lai2026,
  author = {Lai, Chia-Tse and Hsu, Chen-Chien and Huang, Shao-Kang and Wang, Yin-Tien},
  title = {Decoupled Detection and Category-Level 6D Pose Estimation for Robot Grasping},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {8},
  pages = {1706},
  doi = {10.3390/electronics15081706}
}
Kostenlos starten →