Search papers, labs, and topics across Lattice.
This paper introduces LF-GICP, a parameter-free LiDAR odometry method that effectively addresses the challenges of geometric degeneracy in environments like tunnels and corridors without the need for environment-specific tuning. By utilizing a voxel-normal localizability field and two novel statistics to detect anisotropy and information absence, LF-GICP achieves superior performance, evidenced by the lowest relative translation error on the KITTI dataset and improved results in challenging environments. The method's robustness is highlighted by its ability to generalize across different sensor types without requiring re-tuning, marking a significant advancement in LiDAR odometry techniques.
LF-GICP achieves the lowest translation error on the KITTI dataset while generalizing across multiple sensor types, all without parameter tuning.
Scan-to-map LiDAR odometry drifts unboundedly along the unobservable axes of geometrically degenerate environments like tunnels and corridors, and existing degeneracy handling requires environment-specific parameter tuning. This paper presents a parameter-free approach. We show that in voxelized GICP the Gauss--Newton (GN) Hessian masks translational degeneracy, because covariance regularization keeps the translation block artificially well-conditioned. We bypass this with a regularization-free voxel-normal localizability field and two of its statistics: a normalized fraction $f_0$ detecting directional anisotropy, and an absolute per-voxel mass $\lambda_0$ distinguishing information absence (tunnels) from dilution (dense open scenes). A temporal-median gate combines both to trigger Fisher-information correspondence weighting. Calibrated once by fixed rules on two short sequences and then frozen, LF-GICP achieves the lowest KITTI relative translation error ($0.865\%$) under an identical evaluation protocol against re-run baselines, outperforms them on GEODE tunnels and MulRan, leads the HeLiPR mean, and generalizes across four sensor types without re-tuning. We further demonstrate empirically that straight, uniform tunnels remain unobservable along their axis for LiDAR-only registration.
