CVAISep 15, 2018

DLO: Direct LiDAR Odometry for 2.5D Outdoor Environment

arXiv:1809.10199v125 citations
Originality Incremental advance
AI Analysis

This work addresses localization for autonomous vehicles, but it appears incremental as it adapts existing visual odometry techniques to LiDAR data.

The authors tackled the problem of real-time localization for autonomous vehicles in outdoor environments by proposing a direct LiDAR odometry method based on 2.5D grid maps, which outperformed 3D-NDT and LOAM in experiments.

For autonomous vehicles, high-precision real-time localization is the guarantee of stable driving. Compared with the visual odometry (VO), the LiDAR odometry (LO) has the advantages of higher accuracy and better stability. However, 2D LO is only suitable for the indoor environment, and 3D LO has less efficiency in general. Both are not suitable for the online localization of an autonomous vehicle in an outdoor driving environment. In this paper, a direct LO method based on the 2.5D grid map is proposed. The fast semi-dense direct method proposed for VO is employed to register two 2.5D maps. Experiments show that this method is superior to both the 3D-NDT and LOAM in the outdoor environment.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes