Reproduce “Real-Time Ground-Plane Refined LiDAR SLAM” 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
Fan Yang, Mengqing Jiang, Chenxi Xu
The authors refine ground-point selection in LeGO-LOAM, a LiDAR SLAM system, to preserve constraints on height, roll, and pitch while reducing misclassified surface points. Their method grows clusters from low scan rows using neighboring-point angles and labels sufficiently large clusters as ground. In a 669.930 m ATV run, drift falls from 18.354 (2.739%) to 6.367 (0.950%); robustness beyond these tests is not established.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.