On Data Sharing Strategy for Decentralized Collaborative Visual-Inertial Simultaneous Localization and Mapping

张宁 On Data Sharing Strategy for Decentralized Collaborative Visual-Inertial Simultaneous Localization and Mapping

Rodolphe Dubois, Alexandre Eudes, Vincent Fr´emont
链接:https://pan.baidu.com/s/1DGEZtJ7H7eITfyyns7h06A
提取码:zvcu

Abstract—This article introduces and evaluates two decentralized data sharing algorithms for multi-robot visualinertial simultaneous localization and mapping (VI-SLAM): Factor Sparsi?cation for Visual-Inertial Packets (FS-VIP) and Min-K-Cover Selection for Visual-Inertial Packets (MKCS-VIP). Both methods make robots regularly build and exchange data packets which describe the successive portions of their map, but rely on distinct paradigms. While FS-VIP builds on consistent marginalization and sparsi?cation techniques, MKCSVIP selects raw visual and inertial information which can best help to perform a faithful and consistent re-estimation while reducing the communication cost. Performances in terms of accuracy and communication loads are evaluated on multirobot scenarios built on both available (EUROC) and custom datasets (SOTTEVILLE).

本文介绍并评估了用于多机器人视觉惯性同时定位和建图(VI-SLAM)的两种分散数据共享算法:视觉惯性数据包的因子稀疏(FS-VIP)和视觉惯性数据包的最小K覆盖选择( MKCS-VIP)。两种方法都使机器人可以定期构建和交换描述其地图连续部分的数据包,但要依靠不同的范例。FS-VIP建立在一致的边缘化和分散技术的基础上,而MKCSVIP选择原始的视觉和惯性信息,这些信息可以最有效地执行忠实和一致的重新估计,同时降低通信成本。在基于可用(EUROC)和自定义数据集(SOTTEVILLE)构建的多机器人方案中评估准确性和通信负载方面的性能。

原文地址:https://www.cnblogs.com/feifanrensheng/p/12232465.html

时间: 2024-10-29 05:21:36

On Data Sharing Strategy for Decentralized Collaborative Visual-Inertial Simultaneous Localization and Mapping的相关文章

Visual simultaneous localization and mapping: a survey 论文解析(全)

当激光或声纳等距离传感器被用来构建小的静态环境的二维地图时,SLAM的问题被认为是解决的.然而,对于动态,复杂和大规模的环境,使用视觉作为唯一的外部传感器,SLAM是一个活跃的研究领域. 第一部分是简介 移动机器人的自主导航问题分为三个主要方面:定位,建图和路径规划. 定位包括以确切的方式确定机器人在环境中的当前姿态. 建图将环境的部分观测结果整合到一个统一的模型中. 路径规划确定了地图中通过环境进行导航的最佳路线. 最初,定位和建图是独立研究的,后来认识到它们是依赖的.在外部环境中,在动态环境

Openresty 数据共享API.Data Sharing within an Nginx Worker

摘要自:https://github.com/openresty/lua-nginx-module/#data-sharing-within-an-nginx-worker 每nginx worker的数据共享 定义一个lua模块,在content_by_lua或者content_by_lua_block中require它. 建议只用于共享只读数据.如果一定要共享可变数据,注意确保写操作是非阻塞的. 如果需要所有worker共享的数据,可选择: ngx.shared.DICT 或者memcach

JSONP -- one way of cross-domain data sharing

要说清楚JSONP首先得说Same-origin policy,同源策略.为了安全起见,两个不同得网站之间是不能访问对方的数据的,比如A站的cookies不能被B站访问.但是如果这两个网站是相同domain的,比如是同一个公司的网站,那彼此访问是没有问题的,因为是可信任的.就像同domain的OOS(单点登录)的实现可以用cookie来实现一样. 这样的domain,或者说Same-origin里面的origin指的是 URI scheme, hostname, and port number,

g2o vs GTSAM vs HOG-Man

摘自 Comparison of Optimization Techniques for 3D Graph-based SLAM  Doaa M. A.-Latif et al. (2013) Ain Shams University  PDF This paper presents a comparison of the recent methods for graph optimization in terms of translation, rotation, and trajectory

图像处理与计算机视觉基础,经典以及最近发展

*************************************************************************************************************** 在这里,我特别声明:本文章的源作者是   杨晓冬  (个人邮箱:[email protected]).原文的链接是 http://www.iask.sina.com.cn/u/2252291285/ish.版权归 杨晓冬 朋友所有. 我非常感谢原作者辛勤地编写本文章,并愿意共

Open Source Projects Released By Google

Open Source Projects Released By Google Google has released over 20 million lines of code and over 900 projects. Many engineers work on open source projects full time, and even more use their 20% time to create new projects or contribute to their fav

数据集的使用

Participate in Reproducible Research General Image Processing OpenCV (C/C++ code, BSD lic) Image manipulation, matrix manipulation, transforms Torch3Vision (C/C++ code, BSD lic) Basic image processing, matrix manipulation and feature extraction algor

Computer Vision Algorithm Implementations

Participate in Reproducible Research General Image Processing OpenCV (C/C++ code, BSD lic) Image manipulation, matrix manipulation, transforms Torch3Vision (C/C++ code, BSD lic) Basic image processing, matrix manipulation and feature extraction algor

图像处理与计算机视觉基础,经典以及最近发展--转载

*************************************************************************************************************** 在这里,我特别声明:本文章的源作者是   杨晓冬  (个人邮箱:[email protected]).原文的链接是http://www.iask.sina.com.cn/u/2252291285/ish.版权归 杨晓冬 朋友所有. 我非常感谢原作者辛勤地编写本文章,并愿意共享