MS-Mapping: Multi-session LiDAR Mapping with Wasserstein-based Keyframe Selection and Balanced Pose Graph

Table of Contents

• Introduction
• News
• Dataset
• Results
• Citations
• License

Introduction

MS-Mapping presents a novel multi-session LiDAR mapping system that employs an incremental mapping scheme and flexibly supports various LiDAR-based odometry front-ends, enabling high-precision and consistent map assembly in large-scale environments.

News

• 2024/06/03: submit to a workshop.
• 2024/05/20: submit to a journal.

Dataset

Fusion Portable V2 Dataset

Our algorithms were rigorously tested on the Fusion Portable V2 Dataset.

Self-collected Dataset

Map Evaluation

Time Analysis

To plot the results, you can follow this scripts.

Citations

Please cite:

@misc{hu2024msmapping,
      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}
}

License

This project's code is available under the MIT LICENSE.