IMLS-SLAM: scan-to-model matching based on 3D data

TL;DR

IMLS-SLAM introduces a low-drift, scan-to-model SLAM algorithm utilizing 3D LiDAR data, achieving high accuracy in autonomous driving scenarios without loop closure.

Contribution

The paper presents a novel scan-to-model matching SLAM method based solely on 3D LiDAR data, using IMLS surface representation for improved odometry accuracy.

Findings

0.40% drift over 4 km without loop closure

Ranked among top methods on KITTI benchmark

Achieved 0.69% global drift on KITTI dataset

Abstract

The Simultaneous Localization And Mapping (SLAM) problem has been well studied in the robotics community, especially using mono, stereo cameras or depth sensors. 3D depth sensors, such as Velodyne LiDAR, have proved in the last 10 years to be very useful to perceive the environment in autonomous driving, but few methods exist that directly use these 3D data for odometry. We present a new low-drift SLAM algorithm based only on 3D LiDAR data. Our method relies on a scan-to-model matching framework. We first have a specific sampling strategy based on the LiDAR scans. We then define our model as the previous localized LiDAR sweeps and use the Implicit Moving Least Squares (IMLS) surface representation. We show experiments with the Velodyne HDL32 with only 0.40% drift over a 4 km acquisition without any loop closure (i.e., 16 m drift after 4 km). We tested our solution on the KITTI benchmark with a Velodyne HDL64 and ranked among the best methods (against mono, stereo and LiDAR methods) with a global drift of only 0.69%.