Reproduce “OpenStreetMap-based LiDAR Global Localization in Urban Environment without a Prior LiDAR Map” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Younghun Cho, Giseop Kim, Sangmin Lee, Jee-Hwan Ryu
The authors present a kidnapped-localization method using OpenStreetMap building outlines instead of a LiDAR map. It converts mapped and scanned buildings into angle-wise distance descriptors, screens candidates with rotation-invariant keys, and re-ranks them. On KITTI sequence 00, it reaches 48.34% top-one accuracy versus 47.90% for PointNetVLAD, but not at top five or top ten; performance depends on visible, distinctive buildings.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.