EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

6D Pose Estimation of Industrial Parts Based on Point Cloud Geometric Information Prediction for Robotic Grasping

Qinglei Zhang, Cuige Xue, Jiyun Qin, Jianguo Duan, Ying Zhou

Entropy · 26.11.2024 · 26 (12) · 1022

DOI: 10.3390/e26121022 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 26.11.2024. Verfasst von Qinglei Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: China Institute of FTZ Supply Chain, Shanghai Maritime University, Shanghai 201306, China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In industrial robotic arm gripping operations within disordered environments, the loss of physical information on the object’s surface is often caused by changes such as varying lighting conditions, weak surface textures, and sensor noise. This leads to inaccurate object detection and pose estimation information. A method for industrial object pose estimation using point cloud data is proposed to improve pose estimation accuracy. During the feature extraction process, both global and local information are captured by integrating the appearance features of RGB images with the geometric features of point clouds. Integrating semantic information with instance features effectively distinguishes instances of similar objects. The fusion of depth information and RGB color channels enriches spatial context and structure. A cross-entropy loss function is employed for multi-class target classification, and a discriminative loss function enables instance segmentation. A novel point cloud registration method is also introduced to address re-projection errors when mapping 3D keypoints to 2D planes. This method utilizes 3D geometric information, extracting edge features using point cloud curvature and normal vectors, and registers them with models to obtain accurate pose information. Experimental results demonstrate that the proposed method is effective and superior on the LineMod and YCB-Video datasets. Finally, objects are grasped by deploying a robotic arm on the grasping platform.

Schlagwörter

Stichwörter der Autor:innen

3D point cloudappearance edge matchingdeep learningneural networkpose estimationrobotic arm grasping

Autor:innen und Institutionen

  • China Institute of FTZ Supply Chain, Shanghai Maritime University, Shanghai 201306, China.
  • Logistics Engineering College, Shanghai Maritime University, Shanghai 201306, China.

Zitieren

APA

Zhang, Q., Xue, C., Qin, J., Duan, J., & Zhou, Y. (2024). 6D Pose Estimation of Industrial Parts Based on Point Cloud Geometric Information Prediction for Robotic Grasping. Entropy, 26(12), 1022. https://doi.org/10.3390/e26121022

Vancouver

Zhang Q, Xue C, Qin J, Duan J, Zhou Y. 6D Pose Estimation of Industrial Parts Based on Point Cloud Geometric Information Prediction for Robotic Grasping. Entropy. 2024;26(12):1022. doi:10.3390/e26121022

BibTeX
@article{Zhang2024,
  author = {Zhang, Qinglei and Xue, Cuige and Qin, Jiyun and Duan, Jianguo and Zhou, Ying},
  title = {6D Pose Estimation of Industrial Parts Based on Point Cloud Geometric Information Prediction for Robotic Grasping},
  journal = {Entropy},
  year = {2024},
  volume = {26},
  number = {12},
  pages = {1022},
  doi = {10.3390/e26121022}
}
Kostenlos starten →