Any Way You Look At It: Semantic Crossview Localization and Mapping with LiDAR

TL;DR

This paper introduces a real-time semantic cross-view localization and mapping method using LiDAR, IMU, and aerial imagery, achieving over 10-meter accuracy and robust global localization without GPS.

Contribution

It presents a novel approach combining semantic information from LiDAR and aerial images for global localization and mapping, capable of estimating map scale dynamically.

Findings

Achieves better than 10-meter localization accuracy.

Demonstrates robustness across challenging datasets.

Enables on-the-fly scale estimation of top-down maps.

Abstract

Currently, GPS is by far the most popular global localization method. However, it is not always reliable or accurate in all environments. SLAM methods enable local state estimation but provide no means of registering the local map to a global one, which can be important for inter-robot collaboration or human interaction. In this work, we present a real-time method for utilizing semantics to globally localize a robot using only egocentric 3D semantically labelled LiDAR and IMU as well as top-down RGB images obtained from satellites or aerial robots. Additionally, as it runs, our method builds a globally registered, semantic map of the environment. We validate our method on KITTI as well as our own challenging datasets, and show better than 10 meter accuracy, a high degree of robustness, and the ability to estimate the scale of a top-down map on the fly if it is initially unknown.