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

2025-01-31

AI Summary

This work addresses the challenge of sharing place representations across heterogeneous LiDAR types (e.g., rotating, solid-state, MEMS) in long-term localization. To this end, we propose the first unsupervised place recognition framework tailored for heterogeneous LiDARs. Methodologically, we introduce an overlap-driven data mining strategy and a guided triplet loss, incorporate a local spherical Transformer to model geometric invariance, and employ optimal transport-based clustering for device-agnostic global descriptor learning. Our contributions are threefold: (1) the first framework enabling zero-shot generalization to unseen LiDAR types; (2) consistent and significant improvements over state-of-the-art methods on multiple public benchmarks; and (3) open-sourced code to foster community advancement. This work enhances the robustness and scalability of long-term localization for autonomous driving and robotics operating with multi-source LiDAR sensors.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Learning to Search
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

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 at https://github.com/minwoo0611/HeLiOS.

Problem

• LiDAR Compatibility
• Robot Localization
• Place Recognition

Innovation

• HeLiOS
• Learning Methods
• Local Spherical Technique