Reproduce “COIN-LIO: Complementary Intensity-Augmented LiDAR Inertial Odometry” 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
Patrick Pfreundschuh, Helen Oleynikova, Cesar Cadena, Roland Siegwart, Olov Andersson
COIN-LIO combines LiDAR intensity images with geometric and inertial measurements to improve odometry in geometrically weak scenes. It filters intensity images and selects patches whose gradients complement directions poorly constrained by geometry. On the 179.71-meter TunnelD sequence it achieves 1.59% relative translational error, compared with FAST-LIO2’s 81.31%. It stays below the failure threshold across ten ENWIDE sequences, using high-resolution LiDARs.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.