# Polygraph：无3D地图在线多会话轨迹优化框架

> 原文链接：https://robotics.hellobike.com/papers/2026-11-17-2611-21163-3efa2e95
> 频道：papers | 更新日期：2026-11-17 | 标签：auto, arxiv
> 核心摘要：提出Polygraph在线多会话轨迹优化管线，无需构建3D地图即可实现全局一致。通过聚类检索与双层共识门控验证跨会话边，在Spot机器人及车载数据集上验证，较现有SOTA运行更快且回环误匹配更少。

# Polygraph：无3D地图在线多会话轨迹优化框架

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[Polygraph: Large-Scale Multi-Session Trajectory Optimization using Pose Graphs](https://arxiv.org/abs/2611.21163)（arXiv 2611.21163）

## 核心内容

针对机器人与车辆重复遍历环境时多源轨迹漂移及坐标系不统一难题，arXiv论文提出Polygraph在线多会话轨迹优化框架。该方法突破传统离线批处理限制，支持逐关键帧与空间聚类流式处理，无需预建3D地图。在立体视觉驾驶、HoloLens/iPad室内采集及Boston Dynamics Spot足式机器人等多平台实测中，其运行速度优于同GPU下的对比方法，同时保持或提升了轨迹精度。

技术架构上，Polygraph将关键帧分组为局部聚类，闭合时利用学习式图像检索匹配其他会话，并经稀疏特征、单目度量深度与鲁棒位姿估计三重验证。系统引入双层共识门控机制，仅当独立证据相互印证时才向共享位姿图添加跨会话边，有效抑制误匹配。配合轻量级增量求解维持实时性，以及周期性鲁棒批量求解剔除异常值，实现了大规模场景下的高效全局一致性优化。

## 关键看点

- **在线流式处理**：摒弃离线全量数据依赖，按关键帧与空间聚类单元实时处理，无需预先构建三维地图即可输出全局一致轨迹
- **双层共识门控**：结合学习式检索、稀疏特征匹配与单目度量深度验证，仅当独立证据 corroborate 时才接纳跨会话边，显著降低误闭环率
- **混合求解策略**：采用低成本增量求解器维持位姿图实时更新，辅以周期性鲁棒批量优化剔除离群点，兼顾计算效率与长期精度
- **多平台实证**：覆盖车载立体视觉、手持设备及Boston Dynamics Spot足式机器人等异构平台，在同算力下运行速度快于现有最接近工作

## 工程与产业观察

Polygraph为具身智能体长期自主运行提供了轻量化SLAM后端范式。其无图在线优化与抗误匹配机制，直接解决了多机协作建图与长周期重定位的工程痛点，对降低机器人部署维护成本及提升复杂环境适应性具有明确参考价值。

## 英文摘要 (Abstract)

Robots, vehicles, and wearable devices often traverse the same environment many times. Each pass produces its own trajectory from onboard visual or visual-inertial odometry. These trajectories are locally accurate but drift over time and live in unrelated coordinate frames. Turning many such independent trajectories into one globally consistent set is the large-scale multi-session trajectory optimization problem. Existing solutions largely work offline. All sessions must be available up front, one session is fixed as the reference frame, and a single fused map is then optimized. This paper presents Polygraph, a multi-session trajectory optimization pipeline that processes sessions online, one keyframe and one spatial cluster at a time, and never builds a 3D map. Keyframes are grouped into local clusters. When a cluster closes, it is matched against every other session through learned image retrieval. Candidate pairs are verified with sparse feature matching, monocular metric depth, and robust pose estimation. A two-tier consensus gate admits a cross-session edge into the shared pose graph only once independent evidence corroborates it. A cheap incremental solve keeps the graph current, and a periodic robust batch solve prunes outliers. We evaluate Polygraph on stereo outdoor driving, HoloLens and iPad indoor traversals, legged indoor locomotion with a Boston Dynamics Spot, and large-scale outdoor vehicle and handheld routes. Against the closest prior work on the same GPU model, using its reported timings, Polygraph runs faster, commits fewer loop-closure edges, and matches or improves on accuracy.

作者：Petar Lukovic, Tian Yi Lim, Marc Pollefeys, Pablo Speciale, Hermann Blum, Zuria Bauer
:::

## 原始参考来源 (Sources)

- [arXiv 2611.21163：Polygraph: Large-Scale Multi-Session Trajectory Optimization using Pose Graphs](https://arxiv.org/abs/2611.21163)