FP-Loc: Lightweight and Drift-free Floor Plan-assisted LiDAR Localization

TL;DR

This paper introduces FP-Loc, a lightweight LiDAR localization framework that uses floor plans and vertical structure detection to achieve accurate, drift-free, full 6-DoF positioning in various scenes.

Contribution

It presents a novel nearest neighbor data structure and a pose graph optimization method for efficient, accurate, and drift-free LiDAR localization using floor plans.

Findings

Demonstrates highly accurate long-term localization

Achieves drift-free results in multiple scenes

Efficient vertical structure element lookup

Abstract

We present a novel framework for floor plan-based, full six degree-of-freedom LiDAR localization. Our approach relies on robust ceiling and ground plane detection, which solves part of the pose and supports the segmentation of vertical structure elements such as walls and pillars. Our core contribution is a novel nearest neighbour data structure for an efficient look-up of nearest vertical structure elements from the floor plan. The registration is realized as a pair-wise regularized windowed pose graph optimization. Highly efficient, accurate and drift-free long-term localization is demonstrated on multiple scenes.