Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-A new study on Robotics is now available. Accordi ng to news reporting originating in Lulea, Sweden, by NewsRx journalists, resear ch stated, "In this article, we perform a novel and extended field evaluation of the state-of-the-art algorithmic frameworks' performance on global pose estimat ion. More specifically, we focus on relocalizing a mobile robot in a pre-built 3 D point cloud map of a large subterranean environment." Financial support for this research came from European Union (EU). The news reporters obtained a quote from the research from the Lulea University of Technology, "The evaluation is divided into two parts. The first part consist s of multiple simulations performed in two different Gazebo SubT worlds, where o ne is flat with various types of features, while another has uneven structure an d is more textured. The second part is an experimental evaluation and takes plac e in a real-world underground tunnel. In all evaluation tests, the robot's pose is selected in such a way that we can test the robustness, as well as the featur e extraction capability, of each algorithm. The evaluation is carried out using three ROS packages: a) hdl_global_localization using b oth BBS and FPFH+RANSAC, b) LIO-SAM_based_relocalizati on, and c) Fast-LIO-Localization."
NETL
NSTL