Multi-Mapcher: Loop Closure Detection-Free Heterogeneous LiDAR Multi-Session SLAM Leveraging Outlier-Robust Registration for Autonomous Vehicles

2025-11-01

AI Summary

To address degraded mapping accuracy in cross-session SLAM with heterogeneous LiDARs (varying models, point densities, and FoVs) due to failed loop closure detection, this paper proposes Multi-Mapcher—a framework that eliminates reliance on conventional loop closure. Instead, it introduces large-scale, robust map-to-map registration for initial cross-session alignment—the first such application in this context. The method integrates outlier-robust 3D point cloud registration, radius-search-driven loop matching without explicit detection, and anchor-node-enhanced pose graph optimization to construct a globally consistent map. Evaluated on diverse LiDAR datasets, Multi-Mapcher significantly improves cross-session alignment accuracy and robustness: mapping error is reduced by up to 32%, and runtime is accelerated by 1.8× compared to state-of-the-art methods. The source code is publicly available.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

As various 3D light detection and ranging (LiDAR) sensors have been introduced to the market, research on multi-session simultaneous localization and mapping (MSS) using heterogeneous LiDAR sensors has been actively conducted. Existing MSS methods mostly rely on loop closure detection for inter-session alignment; however, the performance of loop closure detection can be potentially degraded owing to the differences in the density and field of view (FoV) of the sensors used in different sessions. In this study, we challenge the existing paradigm that relies heavily on loop detection modules and propose a novel MSS framework, called Multi-Mapcher, that employs large-scale map-to-map registration to perform inter-session initial alignment, which is commonly assumed to be infeasible, by leveraging outlier-robust 3D point cloud registration. Next, after finding inter-session loops by radius search based on the assumption that the inter-session initial alignment is sufficiently precise, anchor node-based robust pose graph optimization is employed to build a consistent global map. As demonstrated in our experiments, our approach shows substantially better MSS performance for various LiDAR sensors used to capture the sessions and is faster than state-of-the-art approaches. Our code is available at https://github.com/url-kaist/multi-mapcher.

Problem

• Eliminates loop closure detection for heterogeneous LiDAR multi-session SLAM
• Performs robust map-to-map registration across different sensor sessions
• Builds consistent global maps using anchor-based pose graph optimization

Innovation

• Eliminates loop closure detection for multi-session SLAM
• Uses outlier-robust map-to-map registration for alignment
• Applies anchor node-based pose graph optimization globally