# SEAM：轨迹变形下用于终身 LiDAR 建图的子地图锚定证据

> 原文链接：https://robotics.hellobike.com/papers/2026-09-16-2609-18819
> 频道：papers | 更新日期：2026-09-16 | 标签：arxiv, cs.RO
> 核心摘要：SEAM用子地图级锚点优化轨迹生成证据，进行动态物体移除和变化检测，并在真实施工现场与长期多会话数据集验证。

# SEAM：轨迹变形下用于终身 LiDAR 建图的子地图锚定证据

::: v-pre
> 原文链接：[SEAM: Submap-Anchored Evidence for Lifelong LiDAR Mapping under Trajectory Deformation](https://arxiv.org/abs/2609.18819)（arXiv 2609.18819 · 发布日期：2026-09-16）

**SEAM: Submap-Anchored Evidence for Lifelong LiDAR Mapping under Trajectory Deformation**

SEAM用子地图级锚点优化轨迹生成证据，进行动态物体移除和变化检测，并在真实施工现场与长期多会话数据集验证。

## 核心要点

- 单一会话全局锚点下，轨迹被新会话修改会使证据面临重算问题。
- SEAM基于子地图级锚点优化轨迹，并通过子地图级重投影复用证据。
- 它用DOP置信度抑制不可靠跨会话回环边，并采用方向体素证据模型。
- 实验显示，在两个真实数据集上，SEAM精度和处理速度高于现有方法。

**验证范围与局限**：验证范围为真实施工现场数据集和长期多会话数据集。

## 英文摘要 (Abstract)

We propose SEAM, a LiDAR-based lifelong mapping framework. Instead of relying on a single anchor spanning the entire session, SEAM generates evidence based on a trajectory optimized with submap-level anchors, and performs dynamic object removal and change detection. Through submap-level reprojection, the generated evidence remains usable even if the trajectory is subsequently modified by a new session, eliminating the need to recompute the entire process from scratch. SEAM suppresses geometrically unreliable inter-session loop edges using a DOP-based confidence measure. Suppressing unreliable loop edges prevents alignment errors. SEAM also uses a directional voxel-wise evidence model. The model accounts for occupancy patterns that vary with ray direction. Direction-aware evidence separates dynamic objects from environmental changes more precisely. Experiments on a real construction-site dataset and a long-term multi-session dataset show that SEAM achieves higher accuracy and faster processing than existing methods.

作者：Kyuwon Kim
:::

## 原始参考来源 (Sources)

- [arXiv 2609.18819：SEAM: Submap-Anchored Evidence for Lifelong LiDAR Mapping under Trajectory Deformation](https://arxiv.org/abs/2609.18819)