MS-Mapping: An Uncertainty-Aware Large-Scale Multi-Session LiDAR Mapping System

Xiangcheng Hu¹ · Jin Wu¹ · Jianhao Jiao^2*
Binqian Jiang ¹· Wei Zhang¹ · Wenshuo Wang³ · Ping Tan^1*†

¹HKUST   ²UCL   ³BIT

†project lead *corresponding author

MS-Mapping is a novel multi-session LiDAR mapping system designed for large-scale environments. It addresses challenges in data redundancy, robustness, and accuracy with three key innovations:

• Distribution-aware keyframe selection: Captures the contributions of each point cloud frame by analyzing map distribution similarities. This reduces data redundancy and optimizes graph size and speed.

• Uncertainty model: Automatically adjusts using the covariance matrix during graph optimization, enhancing precision and robustness without scene-specific tuning. It monitors pose uncertainty to avoid ill-posed optimizations.

• Enhanced evaluation: Redesigned baseline comparisons and benchmarks demonstrate MS-Mapping's superior accuracy over state-of-the-art methods.

Applications include surveying, autonomous driving, crowd-sourced mapping, and multi-agent navigation.

News

• 2025/02/26: Baseline method F2F and M2F released! Tutorial is here!
• 2024/08/08: We released the first version of MS-Mapping on ArXiv, together with the example merged data and related YouTube and bilibili videos.
• 2024/07/19: accepted by ICRA@40 as a extended abstract.
• 2024/06/03: submit to a workshop.

CP5-NG	CP5-NG-PK1

Dataset

Fusion Portable V2 Dataset	Newer College	Urban-Nav	MS-Dataset

Trajectory Evaluation

Map Evaluation

Time Analysis

To plot the results, you can follow this scripts.

Quick Run

The implementation of baseline method F2F and M2F, only radius keyframe selection + fix-cov PGO.

• Step 1: single session mapping using old session to prepare data

• Step2: incrimental mapping using new session

• Step3: global map merging

• Step4: Lifelong Mapping with BeautyMap

With BeautyMap	Ground Truth Map

TO DO

• Clean codes
• Add more dataset support
• Add place recognition algothem for initialization

Citations

Please cite:

@misc{hu2024mskeyframe,
      title={MS-Mapping: Multi-session LiDAR Mapping with Wasserstein-based Keyframe Selection}, 
      author={Xiangcheng Hu, Jin Wu, Jianhao Jiao, Wei Zhang and Ping Tan},
      year={2024},
      eprint={2406.02096},
      archivePrefix={arXiv},
      primaryClass={cs.RO}
}

@misc{hu2024msmapping,
      title={MS-Mapping: An Uncertainty-Aware Large-Scale Multi-Session LiDAR Mapping System}, 
      author={Xiangcheng Hu, Jin Wu, Jianhao Jiao, Binqian Jiang, Wei Zhang, Wenshuo Wang and Ping Tan},
      year={2024},
      eprint={2408.03723},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2408.03723}, 
}

Acknowledgment

The code in this project is adapted from the following projects:

• The odometry method is adapted from FAST-LIO2.
• The basic framework for pose graph optimization (PGO) is adapted from SC-A-LOAM.

Contributors