首页|Recent Research from Tsinghua University Highlight Findings in Robotics and Automation (Poses As Queries: End-to-end Imageto-lidar Map Localization With Transformers)
Recent Research from Tsinghua University Highlight Findings in Robotics and Automation (Poses As Queries: End-to-end Imageto-lidar Map Localization With Transformers)
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
IEEE
Investigators publish new report on Robotics Robotics and Automation. According to news reporting originating from Beijing, People’s Republic of China, by NewsRx correspondents, research stated, “High-precision vehicle localization with commercial setups is a crucial technique for high-level autonomous driving tasks. As a newly emerged approach, monocular localization in LiDAR map achieves promising balance between cost and accuracy, but estimating pose by finding correspondences between such cross-modal sensor data is challenging, thereby damaging the localization accuracy.” Financial support for this research came from National Natural Science Foundation of China (NSFC). Our news editors obtained a quote from the research from Tsinghua University, “In this letter, we address the problem by proposing a novel Transformer-based neural network to register 2D images into 3D LiDAR map in an end-to-end manner. We first implicitly represent poses as high-dimensional feature vectors called pose queries and gradually optimize poses by interacting with the retrieved relevant information from cross-modal features using attention mechanism in a proposed POse Estimator Transformer (POET) module. Moreover, we apply a multiple hypotheses aggregation method that estimates the final poses by performing parallel optimization on multiple randomly initialized pose queries to reduce the network uncertainty.”
BeijingPeople’s Republic of ChinaAsiaRobotics and AutomationRoboticsTsinghua University
NETL
NSTL
IEEE
