arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.10336cs.RO

基于OpenStreetMap车道几何的里程计无关漂移校正

Odometer-Agnostic Drift Correction Using OpenStreetMap Lane Geometry

Joaquin Caballero, Emilio Garcia-Fidalgo, Alberto Ortiz, Jarno Ralli

首次发表
浏览论文内容

中文总结 AI 辅助

提出一种轻量级、开源、里程计无关的漂移校正方法,通过将短轨迹段与OSM车道中心线直接对齐,无需稠密先验,在LiDAR和视觉里程计实验中显著减少长期漂移。

中文摘要 AI 辅助

尽管里程计估计取得了显著进展,长期漂移仍然是增量位姿积分的基本限制,尤其是在大规模或无回环环境中。现有的地图辅助方法可以减少漂移,但往往依赖于稠密地图、特定于传感器的处理或复杂的匹配流程。我们提出了一种轻量级、开源、里程计无关的校正方法,该方法将短轨迹段与OpenStreetMap(OSM)车道中心线对齐。通过将漂移校正表述为近期里程计与稀疏车道几何之间的直接对齐,该方法无需稠密先验或昂贵的预处理即可实现高效的在线操作。使用LiDAR和视觉里程计后端的实验表明,该方法带来了一致的改进,在严重漂移下尤其显著。

英文摘要

Despite significant progress in odometry estimation, long-term drift remains a fundamental limitation of incremental pose integration, especially in large-scale or loop-free environments. Existing map-assisted methods can reduce drift, but often depend on dense maps, sensor-specific processing, or complex matching pipelines. We propose a lightweight open-source, odometry-agnostic correction method that aligns short trajectory segments to OpenStreetMap (OSM) lane centerlines. By formulating drift correction as a direct alignment between recent odometry and sparse lane geometry, the method enables efficient online operation without dense priors or expensive preprocessing. Experiments with LiDAR and visual odometry backends demonstrate consistent improvements, with particularly strong gains under severe drift.

发表机构

  • Distance Technologies Oy(距离科技有限公司)
  • University of the Balearic Islands(巴利阿里群岛大学)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑