首页|Studies from Shanxi University Further Understanding of Robotics (Robotic Grasp Detection Using Structure Prior Attention and Multiscale Features)
Studies from Shanxi University Further Understanding of Robotics (Robotic Grasp Detection Using Structure Prior Attention and Multiscale Features)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Fresh data on Robotics are presented i n a new report. According to news reporting out of Taiyuan, People's Republic of China, by NewsRx editors, research stated, "Most available grasp detection meth ods tend to directly predict grasp configurations with deep neural networks, whe re All features are equAlly extracted and utilized, leading to the relative rest riction of truly useful grasping features. Inspired by the observed three-sectio n structure pattern revealed by human-labeled graspable rectangles, we first des ign a structure prior attention (SPA) module which uses two-dimensional encoding to enhance the local patterns and utilizes self-attention mechanism to reAlloca te distribution of grasping-specific features." Funders for this research include National Natural Science Foundation of China ( NSFC), Fundamental Research Program of Shanxi Province, Science and Technology I nnovation 2030-"New Generation of Artificial Intelligence" Major Program, Scienc e and Technology Major Project of Shanxi Province, The 1331 Engineering Project of Shanxi Province.
TaiyuanPeople's Republic of ChinaAsi aEmerging TechnologiesMachine LearningRoboticsRobotsShanxi University
NETL
NSTL
