中文

MTD-Map: Single-Stage Long-Term LiDAR Map Maintenance Framework via Mixture Transition Distribution

机器人学 2026-06-28 v1

摘要

While robust map maintenance has advanced significantly, existing studies have focused on specific tasks, especially dynamic object removal or change detection. In this paper, we take a holistic view of the map maintenance problem and propose MTD-Map, a single-stage framework that handles both dynamic object removal and change detection without separate task-specific modules. MTD-Map employs an explicit representation that compactly encodes the direction and duration of occupancy transitions through Mixture Transition Distribution (MTD) modeling. We develop a recursive MTD formulation that encodes historical occupancy patterns into an augmented state to capture high-order temporal dependencies. Furthermore, a stability-driven adaptive strategy balances noise suppression with the preservation of quasi-static structures. Extensive experiments verify that MTD-Map robustly removes dynamic objects and achieves competitive change detection performance, subsequently reducing computational costs. Our project page is available at: https://taeyoung96.github.io/mtd_map/.

引用

@article{arxiv.2606.29469,
  title  = {MTD-Map: Single-Stage Long-Term LiDAR Map Maintenance Framework via Mixture Transition Distribution},
  author = {TaeYoung Kim and Gilhwan Kang and Tae Ihn Kim and Seungwon Song and Hun Keon Ko},
  journal= {arXiv preprint arXiv:2606.29469},
  year   = {2026}
}

备注

8 pages, Accepted to IROS 2026