Multi-Session, Localization-oriented and Lightweight LiDAR Mapping Using Semantic Lines and Planes

TL;DR

This paper introduces a lightweight, multi-session LiDAR mapping framework for urban environments that uses semantic lines and planes for efficient, consistent mapping and localization, validated through extensive experiments.

Contribution

The novel framework leverages lightweight line and plane representations with a coarse-to-fine approach, including a new bundle adjustment and global recognition method for multi-session map merging.

Findings

Successfully merges multi-session maps globally

Optimizes maps incrementally with high accuracy

Demonstrates efficiency and effectiveness on multiple datasets

Abstract

In this paper, we present a centralized framework for multi-session LiDAR mapping in urban environments, by utilizing lightweight line and plane map representations instead of widely used point clouds. The proposed framework achieves consistent mapping in a coarse-to-fine manner. Global place recognition is achieved by associating lines and planes on the Grassmannian manifold, followed by an outlier rejection-aided pose graph optimization for map merging. Then a novel bundle adjustment is also designed to improve the local consistency of lines and planes. In the experimental section, both public and self-collected datasets are used to demonstrate efficiency and effectiveness. Extensive results validate that our LiDAR mapping framework could merge multi-session maps globally, optimize maps incrementally, and is applicable for lightweight robot localization.