Robotic Grasp Detection Using Structure Prior Attention and Multiscale Features
IEEE Transactions on Systems, Man, and Cybernetics: Systems · 2024-11 · 54 (11) · 7039-7053
DOI: 10.1109/tsmc.2024.3446841 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2024-11. Verfasst von Lu Chen und 7 weiteren Autor:innen. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Program of Shanxi Province, Science and Technology Innovation 2030-“New Generation of Artificial Intelligence” Major Program.
Abstract (Originalsprache)
Most available grasp detection methods tend to directly predict grasp configurations with deep neural networks, where all features are equally extracted and utilized, leading to the relative restriction of truly useful grasping features. Inspired by the observed three-section structure pattern revealed by human-labeled graspable rectangles, we first design a structure prior attention (SPA) module which uses two-dimensional encoding to enhance the local patterns and utilizes self-attention mechanism to reallocate distribution of grasping-specific features. Then, the proposed SPA module is integrated with fundamental feature extraction modules and residual connection to achieve the implicit and explicit feature fusion, which further serves as the building block of our proposed Unet-like grasp detection network. It takes RGBD images as input and outputs image-size feature maps, from which the grasp configurations can be determined. Extensive comparative experiments on the five public datasets prove our method’s superiority to other approaches in detection accuracy, achieving 99.2%, 96.1%, 98.0%, 86.7%, and 92.6% on the Cornell, Jacquard, Clutter, VMRD, and GraspNet datasets. With visual evaluation metrics and user study, the quality maps generated by our method possess more concentrative distribution of high-confidence grasps and clearer discrimination with backgrounds. In addition, its effectiveness is also verified by robotic grasping under real-world scenario, leading to higher success rate.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Program of Shanxi Province
- Science and Technology Innovation 2030-“New Generation of Artificial Intelligence” Major Program
- Science and Technology Major Project of Shanxi Province
- 1331 Engineering Project of Shanxi Province
Zitieren
APA
Chen, L., Niu, M., Yang, J., Qian, Y., Li, Z., Wang, K., Yan, T., & Huang, P. (2024). Robotic Grasp Detection Using Structure Prior Attention and Multiscale Features. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 54(11), 7039-7053. https://doi.org/10.1109/tsmc.2024.3446841
Vancouver
Chen L, Niu M, Yang J, Qian Y, Li Z, Wang K, et al. Robotic Grasp Detection Using Structure Prior Attention and Multiscale Features. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2024;54(11):7039-7053. doi:10.1109/tsmc.2024.3446841
BibTeX
@article{Chen2024,
author = {Chen, Lu and Niu, Mingdi and Yang, Jing and Qian, Yuhua and Li, Zhuomao and Wang, Keqi and Yan, Tao and Huang, Panfeng},
title = {Robotic Grasp Detection Using Structure Prior Attention and Multiscale Features},
journal = {IEEE Transactions on Systems, Man, and Cybernetics: Systems},
year = {2024},
volume = {54},
number = {11},
pages = {7039--7053},
doi = {10.1109/tsmc.2024.3446841}
}
EUVIMED