SLIM: Scalable and Lightweight LiDAR Mapping in Urban Environments

2024-09-13

IEEE Transactions on robotics

AI Summary

To address the high memory overhead and poor maintainability of long-term LiDAR mapping in urban environments, this paper proposes SLIM: a Structured, Lightweight, and Incrementally Updatable semantic-enhanced mapping system. Its core innovations include: (i) the first introduction of parametric line/surface-based map representation to replace dense point clouds; (ii) a map-centric nonlinear factor recovery method that significantly sparsifies the pose graph while preserving global consistency and mapping accuracy; and (iii) support for cross-session map reuse and long-term evolution. Evaluated on KITTI, NCLT, and HeLiPR datasets, SLIM achieves only 130 KB/km memory footprint, localization accuracy comparable to dense point-cloud maps, and real-time optimization with multi-session fusion capability. The source code is publicly released to advance research on lightweight long-term mapping.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

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
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

LiDAR point cloud maps are extensively utilized on roads for robot navigation due to their high consistency. However, dense point clouds face challenges of high memory consumption and reduced maintainability for long-term operations. In this study, we introduce SLIM, a scalable and lightweight mapping system for long-term LiDAR mapping in urban environments. The system begins by parameterizing structural point clouds into lines and planes. These lightweight and structural representations meet the requirements of map merging, pose graph optimization, and bundle adjustment, ensuring incremental management and local consistency. For long-term operations, a map-centric nonlinear factor recovery method is designed to sparsify poses while preserving mapping accuracy. We validate the SLIM system with multi-session real-world LiDAR data from classical LiDAR mapping datasets, including KITTI, NCLT, and HeLiPR. The experiments demonstrate its capabilities in mapping accuracy, lightweightness, and scalability. Map re-use is also verified through map-based robot localization. Ultimately, with multi-session LiDAR data, the SLIM system provides a globally consistent map with low memory consumption (130 KB/km). We have made our code open-source to benefit the community.

Problem

• Reducing memory consumption in dense LiDAR point cloud maps
• Enhancing long-term maintainability of urban LiDAR mapping
• Ensuring global consistency with lightweight structural representations

Innovation

• Parameterizes LiDAR point clouds into lines and planes
• Uses map-centric nonlinear factor recovery method
• Ensures low memory consumption and global consistency