Region-Aware Grasping for Stacked Workpieces: A 6D-Wise Label Self-Generation Method and Robust Evaluation Strategy
IEEE Transactions on Automation Science and Engineering · 2025 · 22 · 16899-16912
DOI: 10.1109/tase.2025.3580784 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Automation Science and Engineering, 2025. Verfasst von Xungao Zhong und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Fujian Province.
Abstract (Originalsprache)
The high-quality datasets and generalized network model combined with robust evaluation strategies serve as a significant benchmark for developing new policies for industrial bin-picking. In this paper, we propose the concept of region-aware grasping, a sim2real cutting-edge system to generate and evaluate 6D poses for robots to pick up novel workpieces from stacked environments. It consists of Region-Aware-Dataset, a large-scale synthetic point cloud grasp dataset; and Semantic-Graspnet, a 6D-wise affordance policy that predicts full 6D grasp pose for stacked workpieces. The introduced Semantic-Graspnet transforms the 6D pose prediction problem into semantic categorization via point cloud encoding and decoding. Meanwhile, we propose a robust evaluation strategy based on pose evaluation and mechanical grasping evaluation, which enhances the robot’s grasping success rate and sorting efficiency. In real industrial tasks, the robot achieves a grasp completion rate of 91.3% in cluttered scenes and 89.2% in densely stacked scenes, demonstrating state-of-the-art results in robotic picking-and-placing applications. Note to Practitioners—This work is inspired by the robotic universal AI technique, which holds an indispensable position in industrial as bin-picking tasks. Leveraging this technology, the robot can proficiently perform picking-and-placing for diverse workpieces. The prior robot grasping policies primarily centered on maximizing the optimization of grasp detection to ensure successful grasping. Nevertheless, limitations still exist regarding efficient datasets, generalized network models, and robust evaluation strategies. Therefore, in order to effectively curtail the development cycle of robot picking-and-placing applications, this paper puts forward a novel region-aware grasping policy for stacked workpieces. We have investigated an autonomous grasp label annotation method and constructed a large-scale synthetic point cloud grasp dataset. Subsequently, a semantic grasping prediction network model, Semantic-Graspnet, has been designed for 6D-wise affordance grasp prediction. More crucially, a proposed robust grasping evaluation strategy markedly improves the robot’s grasping performance. The developed technology even surpasses the state-of-the-art algorithms in multi-object stacked grasping. The innovative sim2real schema is well-suited for the rapid development of various workpieces sorting applications by robots.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Fujian Province
Zitieren
APA
Zhong, X., Gong, T., Yu, J., Luo, J., Zhou, C., Zhong, X., & Liu, Q. (2025). Region-Aware Grasping for Stacked Workpieces: A 6D-Wise Label Self-Generation Method and Robust Evaluation Strategy. IEEE Transactions on Automation Science and Engineering, 22, 16899-16912. https://doi.org/10.1109/tase.2025.3580784
Vancouver
Zhong X, Gong T, Yu J, Luo J, Zhou C, Zhong X, et al. Region-Aware Grasping for Stacked Workpieces: A 6D-Wise Label Self-Generation Method and Robust Evaluation Strategy. IEEE Transactions on Automation Science and Engineering. 2025;22:16899-16912. doi:10.1109/tase.2025.3580784
BibTeX
@article{Zhong2025,
author = {Zhong, Xungao and Gong, Tao and Yu, Junzhi and Luo, Jiaguo and Zhou, Chengxian and Zhong, Xunyu and Liu, Qiang},
title = {Region-Aware Grasping for Stacked Workpieces: A 6D-Wise Label Self-Generation Method and Robust Evaluation Strategy},
journal = {IEEE Transactions on Automation Science and Engineering},
year = {2025},
volume = {22},
pages = {16899--16912},
doi = {10.1109/tase.2025.3580784}
}
EUVIMED