DLO: Direct LiDAR Odometry for 2.5D Outdoor Environment

TL;DR

This paper introduces DLO, a direct LiDAR odometry method using 2.5D grid maps, achieving high accuracy and efficiency for outdoor autonomous vehicle localization, outperforming existing methods like 3D-NDT and LOAM.

Contribution

The paper presents a novel 2.5D LiDAR odometry approach that improves outdoor localization accuracy and efficiency over traditional 3D methods.

Findings

Outperforms 3D-NDT in outdoor environments

Outperforms LOAM in outdoor environments

Provides real-time, high-precision localization

Abstract

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.