GraphTinker：位姿图SLAM中回环的添加与剔除

每天一分钟，带你读遍机器人顶级会议文章

标题：GraphTinker: Outlier rejection and inlier injection for pose graph SLAM

作者：Linhai Xie，Sen Wang，Andrew Markham

来源：IROS 2017(IEEEIntelligent Robots and Systems)

播音员：申影

编译：刘彤宇

欢迎个人转发朋友圈；其他机构或自媒体如需转载，后台留言申请授权

摘要

今天介绍的文章是“GraphTinker: Outlier rejection and inlier injection for pose graph SLAM”——GraphTinker:位姿图SLAM中回环的添加与剔除，该文章发表在IROS2017。

在位姿图SLAM系统中，错误的闭环会严重影响优化器产生正确的结果，同时显著降低定位精度和地图的一致性。因此，当存在大量假阳性回环时，增强它们的鲁棒性是至关重要的。现有算法在使用不可靠的前端系统时往往会失败，判断出大量错误的回环。在本文中，我们提出一个无缝嵌入前端和后端的新型中间层，以提高整个SLAM系统的鲁棒性。本文主要做了两点工作：1）所提出的中间层提供了一种新的机制，用于可靠的检测和移除假阳性回环，即使回环的数量庞大。2）自动重建人工回环并把它添加到扩展RTS平滑器框架中的位姿图中，从而增强回环的可靠性。这个算法可以修改前端生成的图，然后通过任一后端系统优化。通过大量的实验证明，作者提出的算法和现有方法与各种后端相比，显著的提高了系统的精确度和鲁棒性，从而验证了这个算法的有效性。

作者构建了一种新颖的系统叫做GraphTinker（GTK）——一种通用的中间层，可结合任何前端和后端系统使用，以提高整个SLAM系统的鲁棒性。

系统架构如图所示

。

在GTK中，首先检测位姿图中不一致的回环并被剔除模型剔除。 然后重建一组人工回环，并通过添加模块插入，从而给后端提供一个增强图。 架构图底部给出三个姿态图示例。红色和浅绿色线分别表示假阳性回环和添加的回环。

Abstract:

In pose graph Simultaneous Localization and Mapping (SLAM) systems, incorrect loop closures can seriously hinder optimizers from converging to correct solutions, significantly degrading both localization accuracy and map consistency. Therefore, it is crucial to enhance their robustness in the presence of numerous false-positive loop closures. Existing approaches tend to fail when working with very unreliable front-end systems, where the majority of inferred loop closures are incorrect. In this paper, we propose a novel middle layer, seamlessly embedded between front and back ends, to boost the robustness of the whole SLAM system. The main contributions of this paper are two-fold: 1) the proposed middle layer offers a new mechanism to reliably detect and remove false-positive loop closures, even if they form the overwhelming majority; 2) artificial loop closures are automatically reconstructed and injected into pose graphs in the framework of an Extended Rauch-Tung-Striebel smoother, reinforcing reliable loop closures. The proposed algorithm alters the graph generated by the front-end and can then be optimized by any back-end system. Extensive experiments are conducted to demonstrate significantly improved accuracy and robustness compared with state-of-the-art methods and various back-ends, verifying the effectiveness of the proposed algorithm.

如果你对本文感兴趣，想要下载完整文章进行阅读，可以关注【泡泡机器人SLAM】公众号。