首页|Findings from Tsinghua University Update Understanding of Robotics (Fusednet: End-to-end Mobile Robot Relocalization In Dynamic Large-scale Scene)
Findings from Tsinghua University Update Understanding of Robotics (Fusednet: End-to-end Mobile Robot Relocalization In Dynamic Large-scale Scene)
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 DailyNews Daily News - A new study on Robotics is now availab le. According to news reporting from Shenzhen,People’s Republic of China, by Ne wsRx journalists, research stated, “To improve robot relocalizationaccuracy in both static and dynamic environments, we introduce a novel network, FusedNet, wh ichincorporates a cross-attention to fuse global and local image features for e nd-to-end relocalization.”Financial support for this research came from Guangdong Natural Science Fund-Gen eral Programme.The news correspondents obtained a quote from the research from Tsinghua Univers ity, “This approachrelies solely on a monocular camera sensor that is fixed on the mobile robot, and directly predicts theabsolute pose from the input RGB ima ge. Additionally, we have collected a mobile robot relocalizationdataset, terme d moBotReloc, consisting of dynamic large-scale scenes, using the Unity 3D simul ationplatform and a real mobile robot.”According to the news reporters, the research concluded: “Through extensive expe riments on 7Scenesand moBotReloc, we demonstrate that FusedNet achieves signifi cant accuracy in 6-DoF camera relocalizationin static scenes, and exhibits supe rior relocalization performance in dynamic large-scale scenes formobile robot a pplications, outperforming existing end-to-end methods that rely solely on a sin gle globalor local feature.”
ShenzhenPeople’s Republic of ChinaAsiaEmerging TechnologiesMachine LearningRobotRoboticsTsinghua University
NETL
NSTL
