MetaCoorNet:an improved generated residual network for grasping pose estimation  

作　　者：Hejia GAO Chuanfeng HE Junjie ZHAO Changyin SUN 

机构地区：[1]School of Artificial Intelligence,Anhui University,Hefei 230601,China [2]Engineering Research Center of Autonomous Unmanned System Technology,Ministry of Education,Hefei 230601,China [3]School of Automation,Southeast University,Nanjing 214135,China [4]Anhui Provincial Key Laboratory of Security Artificial Intelligence,Anhui University,Hefei 230601,China

出　　处：《Science China(Information Sciences)》2025年第3期238-253,共16页中国科学(信息科学)(英文版)

基　　金：supported in part by National Natural Science Foundation of China(Grant Nos.62388101,62303010);University Synergy Innovation Program of Anhui Province(Grant No.GXXT-2023-039);Anhui Provincial Key Research Program of Universities(Grant No.2022AH050087)。

摘　　要：Robotic grasping presents significant challenges due to variations in object properties,environmental complexities,and the demand for real-time operation.This study proposes the MetaCoorNet(MCN),which is a novel deep learning architecture specifically designed to address these challenges in robotic grasping pose estimation.By combining spatial and channel operators,the MetaCoor block is utilized to extract features efficiently.This architecture enhances feature selectivity by embedding location information into channel attention using a positional embedding technique within the coordinate attention mechanism.Consequently,the proposed MCN can focus on pertinent grasp-related regions.Furthermore,convolutional fusion blocks seamlessly integrate spatial and channel features,resulting in enhanced feature resolution and representation capabilities.This innovative design enables the proposed MCN to achieve state-of-the-art performance on the Cornell and Jacquard datasets,attaining accuracies of 98%and 91.2%,respectively.The effectiveness and robustness of MCN are further validated through real-world experiments conducted using a seven-degree-of-freedom Kinova manipulator.

关 键 词：generative ResNet meta light block coordinate attention feature resolution robot grasping 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置] TP18[自动化与计算机技术—控制科学与工程]