Topomap: Topological Mapping and Navigation Based on Visual SLAM Maps

Fabian Bl¨ochliger, Marius Fehr, Marcin Dymczyk, Thomas Schneider and Roland Siegwart

Topomap:基于Visual SLAM地图的拓扑映射和导航

https://arxiv.org/pdf/1709.05533.pdf

Abstract—Visual robot navigation within large-scale, semistructured environments deals with various challenges such as computation intensive path planning algorithms or insufficient knowledge about traversable spaces. Moreover, many state of-the-art navigation approaches only operate locally instead of gaining a more conceptual understanding of the planning objective. This limits the complexity of tasks a robot can accomplish and makes it harder to deal with uncertainties that are present in the context of real-time robotics applications.

大规模半结构化环境中的视觉机器人导航处理各种挑战,例如计算密集型路径规划算法或关于可穿越空间的不充分知识。此外,许多最先进的导航方法仅在本地运行,而不是对规划目标进行更概念性的理解。这限制了机器人可以完成的任务的复杂性,并且使得处理实时机器人应用中存在的不确定性变得更加困难。

In this work, we present Topomap, a framework which simplifies the navigation task by providing a map to the robot which is tailored for path planning use. This novel approach transforms a sparse feature-based map from a visual Simultaneous Localization And Mapping (SLAM) system into a three-dimensional topological map. This is done in two steps. First, we extract occupancy information directly from the noisy sparse point cloud. Then, we create a set of convex free-space clusters, which are the vertices of the topological map. We show that this representation improves the efficiency of global planning, and we provide a complete derivation of our algorithm. Planning experiments on real world datasets demonstrate that we achieve similar performance as RRT* with significantly lower computation times and storage requirements. Finally, we test our algorithm on a mobile robotic platform to prove its advantages.

在这项工作中,我们介绍了Topomap,这是一个简化导航任务的框架,它为机器人提供了一个专为路径规划使用而定制的地图。这种新颖的方法将稀疏的基于特征的地图从视觉同时定位和建图(SLAM)系统转换为三维拓扑地图。这分两步完成。 首先,我们直接从嘈杂的稀疏点云中提取占用信息。然后,我们创建一组凸自由空间簇,它们是拓扑图的顶点。我们证明了这种表示提高了全局规划的效率,并且我们提供了算法的完整推导。在现实世界数据集上进行规划实验表明,我们实现了与RRT *类似的性能,同时显着降低了计算时间和存储要求。最后,我们在移动机器人平台上测试我们的算法,以证明其优势。

泡泡一分钟:Topomap: Topological Mapping and Navigation Based on Visual SLAM Maps的更多相关文章

  1. 泡泡一分钟:Collaborative Mapping with Pose Uncertainties using different Radio Frequencies and Communication Modules

    张宁 Collaborative Mapping with Pose Uncertainties using different Radio Frequencies and Communication ...

  2. 泡泡一分钟:Tightly-Coupled Aided Inertial Navigation with Point and Plane Features

    Tightly-Coupled Aided Inertial Navigation with Point and Plane Features 具有点和平面特征的紧密耦合辅助惯性导航 Yulin Ya ...

  3. 泡泡一分钟:Semantic Labeling of Indoor Environments from 3D RGB Maps

    张宁 Semantic Labeling of Indoor Environments from 3D RGB Maps Manuel Brucker,  Maximilian Durner,  Ra ...

  4. 泡泡一分钟:GEN-SLAM - Generative Modeling for Monocular Simultaneous Localization and Mapping

    张宁  GEN-SLAM - Generative Modeling for Monocular Simultaneous Localization and Mapping GEN-SLAM  - 单 ...

  5. 泡泡一分钟:Semi-Dense Visual-Inertial Odometry and Mapping for Quadrotors with SWAP Constraints

    张宁 Semi-Dense Visual-Inertial Odometry and Mapping for Quadrotors with SWAP Constraints 具有SWAP约束的四旋翼 ...

  6. 泡泡一分钟:Perception-aware Receding Horizon Navigation for MAVs

    作为在空中抛掷四旋翼飞行器后恢复的第一步,它需要检测它使用其加速度计的发射.理想的情况下,在飞行中,加速度计理想地仅测量由于施加的转子推力引起的加速度,即.因此,当四旋翼飞行器发射时,我们可以检测到测 ...

  7. 泡泡一分钟:Aided Inertial Navigation: Unified Feature Representations and Observability Analysis

    http://udel.edu/~yuyang/downloads/tr_observabilityII.pdf Aided Inertial Navigation: Unified Feature R ...

  8. 泡泡一分钟:Towards real-time unsupervised monocular depth estimation on CPU

    Towards real-time unsupervised monocular depth estimation on CPU Matteo Poggi , Filippo Aleotti , Fa ...

  9. 泡泡一分钟:Stabilize an Unsupervised Feature Learning for LiDAR-based Place Recognition

    Stabilize an Unsupervised Feature Learning for LiDAR-based Place Recognition Peng Yin, Lingyun Xu, Z ...

随机推荐

  1. Dubbo基础入门

    Dubbo概述 Dubbo的背景 随着互联网的发展,网站应用的规模不断扩大,常规的垂直应用架构已无法应对,分布式服务架构以及流动计算架构势在必行,亟需一个治理系统确保架构有条不紊的演进. 单一应用架构 ...

  2. mysql 杂记 —— 时区问题

    查看时区: SHOW VARIABLES LIKE "%time_zone%"; 输出 Variable_name Value system_time_zone CST time_ ...

  3. 黄杉杉 --java第八次作业

    题目:编写一个应用程序,创建一个矩形类,类中具有长.宽两个成员变量和求周长的方法.再创建一个矩形类的子类——正方形类,类中定义求面积方法.重写求周长的方法.在主类中,输入一个正方形边长,创建正方形对象 ...

  4. Linux命令基础3-cd命令

    cd 到带空格的文件夹 [root@cctg-sjc16-grafana ccatgbld]# cd 'my test' [root@cctg-sjc16-grafana my test]# cd . ...

  5. 大小端示例-arm c51

    大小端系列文章https://blog.csdn.net/liming0931/article/details/100016425 MDK(Keil5,STM32F407)C语言: #include  ...

  6. zjoj1706: [usaco2007 Nov]relays 奶牛接力跑

    矩阵乘法(快速幂) 为说明方便,这里让\(k\)为点数,\(n\)为路径长度. 先将点都离散化,这样最后的点只有\(2k\)个. 先考虑一种暴力,每次用\(O(k^3)\)的复杂度来暴力更新,设当前长 ...

  7. MySql数据库导出完整版(导出数据库,导出表,导出数据库结构)

    MySql数据库导出完整版(导出数据库,导出表,导出数据库结构) 用MySqlCE导出数据库脚本时,如数据库中包含中文内容,则导出异常. 现在可以通过mysqldump.exe直接导出数据库脚本步骤如 ...

  8. python爬取动态网页数据,详解

    原理:动态网页,即用js代码实现动态加载数据,就是可以根据用户的行为,自动访问服务器请求数据,重点就是:请求数据,那么怎么用python获取这个数据了? 浏览器请求数据方式:浏览器向服务器的api(例 ...

  9. 五.划分LVM逻辑卷

    作用:    1.整合分散的空间    2.空间可以进行扩大   零散空闲存储 ---- 整合的虚拟磁盘 ---- 虚拟的分区   由众多的物理卷(PV)组合成卷组(VG),从卷组中划分多个逻辑卷(L ...

  10. 利用fgetc合并2个源文件的内容,到一个新的文件中

    #include <stdio.h> #include <stdlib.h> //功能: 合并2个源文件的内容,到一个新的文件中 int main(int a,char *ar ...