数字农科院2.0

Robot Dexterous Grasping in Cluttered Scenes Based on Single-View Point Cloud

文献类型： 外文期刊

作者： Zhao, Qingxing;Zheng, Minhua;Li, Zhaoxin;Huang, Shichang;Shi, Wen

作者机构：

关键词： Grasping;Point cloud compression;6-DOF;Vectors;Feature extraction;Measurement;Robustness;Grippers;Force;Training;Grasping pose detection;point cloud;6-DoF grasping;self-attention

期刊名称： IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING

ISSN： 1545-5955

年卷期： 2025 年 22 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Grasping is a basic but challenging task in intelligent robotic manipulation, and grasping pose detection is the key in this task. Most current work is shifting from 2D planar grasping to more flexible six-degree-of-freedom (6-DoF) grasping, and some significant progress has been made. However, there are still limitations such as low success rate and poor robustness in cluttered scenes. In this paper, we investigate 6-DoF grasping in cluttered scenes, and propose a cascaded multi-target learning network based on self-attention mechanism and multiscale sampling. The self-attention mechanism effectively improves the network's attention to the correct grasping pose, while multiscale sampling improves the network's adaptability to grasping objects of different sizes. In addition, we propose a dual-objective evaluation metric based on the force-closure metric and the center-of-mass distance metric, which can make a more reasonable and reliable evaluation of the grasping poses in the dataset. Our model is evaluated on large-scale benchmarks as well as the real robot system. The proposed method achieves state-of-the-art results on GraspNet-1Billion (8.8+AP), and shows 95.24% success rates in real cluttered scenes. Note to Practitioners-This paper presents a framework for 6-DoF grasping in cluttered scenes using single-view point clouds, improving success rates without requiring complete point clouds. By introducing a self-attention mechanism and multiscale sampling, the model adapts to varying object sizes and enhances focus on the correct grasping pose. A dual-objective evaluation metric based on force-closure and center-of-mass distance also refines dataset quality, balancing force and geometric criteria for more reliable grasping poses. This approach supports direct deployment in real-world robotic applications like automated sorting and assembly, with high robustness and efficiency in cluttered environments.

分类号：

  • 相关文献

[1]Design of a Novel End-Effector for Robotic Bag Removal of Shiitake Mushroom Logs. Ma, Shixin,Ding, Tianhang,Zhou, Fan,Wang, Jiaoling,Wang, Mingyou,Song, Weidong. 2025

[2]Complex Landscape Rice Extraction Using Integrated Sentinel-2 Spectral-Temporal-Spatial Imagery and a Hybrid Deep Learning Architecture. Liu, Tianjiao,Duan, Si-Bo,Liu, Niantang,Zhang, Youzhi,Chen, Jiankui,Zhang, Li,Li, Dong. 2025

[3]CMRNet: An Automatic Rapeseed Counting and Localization Method Based on the CNN-Mamba Hybrid Model. Li, Jie,Yang, Chenbo,Zhu, Chengyong,Qin, Tao,Tu, Jingmin,Wang, Binhui,Yao, Jian,Qiao, Jiangwei. 2025

[4]Requirements and Design of a Hand for LARMbot Humanoid. Wenshuo Gao,Marco Ceccarelli. 2022

[5]Babesia sp. BQ1 (Lintan): Molecular evidence of experimental transmission to sheep by Haemaphysalis qinghaiensis and Haemaphysalis longicornis. Guan, Guiquan,Moreau, Emmanuelle,Chauvin, Alain,Guan, Guiquan,Liu, Junlong,Hao, Xuefen,Ma, Miling,Luo, Jianxun,Yin, Hong.

[6]The New Method of Fruit Tree Characteristics Acquisition Using Electromagnetic Tracking Instrument. Wang, Jian,Wu, Ding-feng,Zhou, Guo-min,Qiu, Yun. 2011

[7]Protective immune responses in guinea pigs and swine induced by a suicidal DNA vaccine of the capsid gene of swine vesicular disease virus. Sun, Shi-Qi,Liu, Xiang-Tao,Guo, Hui-Chen,Yin, Shuang-Hui,Shang, You-Jun,Feng, Xia,Liu, Zai-Xin,Xie, Cling-Ge.

[8]Rapid and Simultaneous Measurement of Fat and Moisture Contents in Pork by Low-Field Nuclear Magnetic Resonance. Shuyue Tang,Yuhui Zhang,Wusun Li,Xiaoyan Tang,Xinyuan Huang. 2023

[9]Improved 3D point cloud segmentation for accurate phenotypic analysis of cabbage plants using deep learning and clustering algorithms. Ruichao Guo,Jilong Xie,Jiaxi Zhu,Ruifeng Cheng,Yi Zhang,Xihai Zhang,Xinjing Gong,Ruwen Zhang,Hao Wang,Fanfeng Meng. 2023

[10]Soybean yield estimation and lodging classification based on UAV multi-source data and self-supervised contrastive learning. Longyu Zhou,Yong Zhang,Haochong Chen,Guangyao Sun,Lei Wang,Mingxue Li,Xuhong Sun,Puyu Feng,Long Yan,Lijuan Qiu,Yinghui Li,Yuntao Ma. 2025

[11]Soybean yield estimation and lodging discrimination based on lightweight UAV and point cloud deep learning. Longyu Zhou,Dezhi Han,Guangyao Sun,Yaling Liu,Xiaofei Yan,Hongchang Jia,Long Yan,Puyu Feng,Yinghui Li,Lijuan Qiu,Yuntao Ma. 2025

[12]Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary Production. Yu, Ruiyang,Yao, Yunjun,Tang, Qingxin,Zhang, Xueyi,Shao, Changliang,Fisher, Joshua B.,Chen, Jiquan,Zhang, Xiaotong,Li, Yufu,Xu, Jia,Liu, Lu,Xie, Zijing,Ning, Jing,Fan, Jiahui,Zhang, Luna. 2025

[13]A Data-Driven Method for Direct Estimation of Global 8-Day 500-m Ecosystem Water Use Efficiency. Huang, Lingxiao,Sun, Yifei,Yao, Na,Liu, Meng. 2025

[14]Non-Contact Measurement of Pregnant Sows' Backfat Thickness Based on a Hybrid CNN-ViT Model. Li, Xuan,Yu, Mengyuan,Xu, Dihong,Zhao, Shuhong,Tan, Hequn,Liu, Xiaolei. 2023

[15]Crop Land Change Detection with MC&N-PSPNet. Yuxin Chen,Yulin Duan,Wen Zhang,Chang Wang,Qiangyi Yu,Xu Wang. 2024

[16]LOGOWheat: deep learning–based prediction of regulatory effects for noncoding variants in wheats. Lingpeng Kong,Hong Cheng,Kun Zhu,Bo Song. 2025

[17]Thermostability Improvement of a Streptomyces Xylanase by Introducing Proline and Glutamic Acid Residues. Wang, Kun,Luo, Huiying,Huang, Huoqing,Shi, Pengjun,Hua, Huifang,Wang, Caihong,Wang, Shuanghe,Yao, Bin,Tian, Jian,Turunen, Ossi.

[18]Reconstructing the transcription regulatory network to optimize resource allocation for robust biosynthesis. Xiaoyan Ma,Lianjie Ma,Yi Xin Huo. 2022

[19]Production Efficiency of Raw Milk and Its Determinants: Application of Combining Data Envelopment Analysis and Stochastic Frontier Analysis. Zetian Yu,Hao Liu,Hua Peng,Qiantong Xia,Xiaoxia Dong. 2023

[20]A Novel Approach Utilizing Domain Adversarial Neural Networks for the Detection and Classification of Selective Sweeps. Song, Hui,Chu, Jinyu,Li, Wangjiao,Li, Xinyun,Fang, Lingzhao,Han, Jianlin,Zhao, Shuhong,Ma, Yunlong. 2024

作者其他论文 更多>>