RF-LIO: Removal-First Tightly-coupled Lidar Inertial Odometry in High Dynamic Environments

TL;DR

RF-LIO is a dynamic SLAM system that effectively removes moving objects using adaptive multi-resolution range images and tightly-coupled lidar inertial odometry, significantly improving localization accuracy in high dynamic environments.

Contribution

The paper introduces RF-LIO, a novel SLAM framework that enhances dynamic environment mapping by first removing moving objects before pose estimation.

Findings

Achieves up to 90% improvement in trajectory accuracy over LOAM.

Outperforms LIO-SAM with 70% better accuracy in dynamic scenes.

Demonstrates robustness in high dynamic environments through extensive testing.

Abstract

Simultaneous Localization and Mapping (SLAM) is considered to be an essential capability for intelligent vehicles and mobile robots. However, most of the current lidar SLAM approaches are based on the assumption of a static environment. Hence the localization in a dynamic environment with multiple moving objects is actually unreliable. The paper proposes a dynamic SLAM framework RF-LIO, building on LIO-SAM, which adds adaptive multi-resolution range images and uses tightly-coupled lidar inertial odometry to first remove moving objects, and then match lidar scan to the submap. Thus, it can obtain accurate poses even in high dynamic environments. The proposed RF-LIO is evaluated on both self-collected datasets and open Urbanloco datasets. The experimental results in high dynamic environments demonstrate that, compared with LOAM and LIO-SAM, the absolute trajectory accuracy of the proposed RF-LIO can be improved by 90% and 70%, respectively. RF-LIO is one of the state-of-the-art SLAM systems in high dynamic environments.