Skip to content

minwoo0611/HeLiOS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 

Repository files navigation

HeLiOS🌞: Heterogeneous LiDAR Place Recognition via Overlap-based Learning and Local Spherical Transformer

(Accepted) [IEEE ICRA 25] This repository is the official repository for for HeLiOS🌞 [Paper].

Minwoo Jung, Sangwoo Jung, Hyeonjae Gil, Ayoung Kim

Robust Perception and Mobile Robotics Lab (RPM)

Video.mp4

You can also check the video via Youtube link.

Abstract

distribution_hetero LiDAR place recognition is a crucial module in localization that matches the current location with previously observed environments. Most existing approaches in LiDAR place recognition dominantly focus on the spinning type LiDAR to exploit its large FOV for matching. However, with the recent emergence of various LiDAR types, the importance of matching data across different LiDAR types has grown significantly—a challenge that has been largely overlooked for many years. To address these challenges, we introduce HeLiOS, a deep network tailored for heterogeneous LiDAR place recognition, which utilizes small local windows with spherical transformers and optimal transport-based cluster assignment for robust global descriptors. Our overlap-based data mining and guided-triplet loss overcome the limitations of traditional distance-based mining and discrete class constraints. HeLiOS is validated on public datasets, demonstrating performance in heterogeneous LiDAR place recognition while including an evaluation for long-term recognition, showcasing its ability to handle unseen LiDAR types. We release the HeLiOS code as an open source for the robotics community.

Comparison Methods

You can check the comparison methods and some results in here

Code for HeLiOS will be availble after review process.

About

Heterogeneous LiDAR Place Recognition

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published