slam

GitHub 上优秀的开源SLAM repo (更新中)

99封情书 提交于 2019-12-09 13:52:08
GitHub 上优秀的开源SLAM repo (更新中) 欢迎 watch/star/fork 我们的 GitHub 仓库: Awesome-SLAM , 或者follow 项目的主页: Awesome-SLAM Page 。 本文主要整理自己在Github上关注的一些优秀的开源SLAM repo。 Hot SLAM Repos on GitHub Awesome-SLAM: Resources and Resource Collections of SLAM awesome-slam: A curated list of awesome SLAM tutorials, projects and communities. SLAM: learning SLAM,curse,paper and others A list of current SLAM (Simultaneous Localization and Mapping) / VO (Visual Odometry) algorithms awesome-visual-slam: The list of vision-based SLAM / Visual Odometry open source, blogs, and papers Lee-SLAM-source: SLAM 开发学习资源与经验分享 awesome

Visual studio 2015. c++ compiler error C2280 attempting to reference a deleted function

烂漫一生 提交于 2019-12-08 08:48:56
问题 What i am trying to do is to compile project which was built by CMake. In my code i have next method: /** "in-place" version of TriangularView::solve() where the result is written in \a other * * \warning The parameter is only marked 'const' to make the C++ compiler accept a temporary expression here. * This function will const_cast it, so constness isn't honored here. * * See TriangularView:solve() for the details. */ template<typename MatrixType, unsigned int Mode> template<int Side,

Visual studio 2015. c++ compiler error C2280 attempting to reference a deleted function

偶尔善良 提交于 2019-12-06 19:13:31
What i am trying to do is to compile project which was built by CMake. In my code i have next method: /** "in-place" version of TriangularView::solve() where the result is written in \a other * * \warning The parameter is only marked 'const' to make the C++ compiler accept a temporary expression here. * This function will const_cast it, so constness isn't honored here. * * See TriangularView:solve() for the details. */ template<typename MatrixType, unsigned int Mode> template<int Side, typename OtherDerived> void TriangularView<MatrixType,Mode>::solveInPlace(const MatrixBase<OtherDerived>&

代码解读 | VINS_Mono中的鱼眼相机模型

二次信任 提交于 2019-12-06 01:41:27
本文作者是计算机视觉life公众号成员蔡量力,由于格式问题部分内容显示可能有问题,更好的阅读体验,请查看原文链接: 代码解读 | VINS_Mono中的鱼眼相机模型 VINS_Mono中的鱼眼相机模型 VINS_Mono代码支持的相机包括针孔模型和鱼眼模型相机,针孔模型大家都比较熟悉了,今天向大家介绍一种鱼眼相机模型——MEI模型及其标定方法。 相机模型 投影模型 相比针孔模型可以将3d点直接投影到归一化平面,鱼眼相机则多了一个中间过程:先将3d点投影到单位球面,再将单位球面上的点投影到归一化平面上。废话不多说,请看鱼眼相机投影模型示意图: 代码解读 VINS Mono中相机模型对应代码在/VINS-Mono/camera model/src/camera_models/CataCamera.cc文件**liftSphere**()函数中,该函数是将$2d$ 投影到$3d$ 点(单位球面上),首先对$2d$去畸变,然后再投影到单位球面上。 去畸变过程代码如下: //去畸变过程 int n = 6; Eigen::Vector2d d_u; distortion(Eigen::Vector2d(mx_d, my_d), d_u);//得到畸变量 // Approximate value mx_u = mx_d - d_u(0); my_u = my_d - d_u(1); for

install.packages(“tm”) -&gt; “dependency &#039;slam&#039; is not available”

匿名 (未验证) 提交于 2019-12-03 02:38:01
可以将文章内容翻译成中文,广告屏蔽插件可能会导致该功能失效(如失效,请关闭广告屏蔽插件后再试): 问题: I'm trying to install the tm package on IBM's Data Science Experience (DSX): install.packages("tm") However, I'm hitting this issue: "dependency 'slam' is not available" This post suggests that R version 3.3.1 will resolve the issue, however the R version on DSX is: R version 3.3.0 (2016-05-03) How can I resolve this issue on IBM DSX? Note that you don't have root access on DSX. I've seen similar questions on stackoverflow, but none are asking how to fix the issue on IBM DSX, e.g. dependency ‘slam’ is not available when installing TM package

slam package install fails with make error

匿名 (未验证) 提交于 2019-12-03 01:48:02
可以将文章内容翻译成中文,广告屏蔽插件可能会导致该功能失效(如失效,请关闭广告屏蔽插件后再试): 由 翻译 强力驱动 问题: I'm trying to install the slam package, but it seems to fail on my system. I'm running ubuntu 12.04. I thought it was a missing library or something so I installed a few that match liblas, but no dice. * installing * source * package ‘ slam ’ ... ** package ‘ slam ’ successfully unpacked and MD5 sums checked ** libs gcc - std = gnu99 - I / usr / share / R / include - DNDEBUG - fpic - O3 - pipe - g - c grouped . c - o grouped . o gcc - std = gnu99 - I / usr / share / R / include - DNDEBUG - fpic - O3 - pipe - g - c sparse . c - o

R: compilation failed for package &#039;slam&#039;

匿名 (未验证) 提交于 2019-12-03 01:08:02
可以将文章内容翻译成中文,广告屏蔽插件可能会导致该功能失效(如失效,请关闭广告屏蔽插件后再试): 问题: I am using R 2.15.2 and I want to install the tm package to do some text analysis. I have downloaded the compatible tm package from the CRAN archives . I downloaded tm_0.5-9 I tried to install it using install.packages("/Downloads/tm_0.5-9.tar.gz", repos = NULL, type="source", dependencies = TRUE) and got the following error Installing package(s) into ‘/Documents/R/win-library/2.15’ (as ‘lib’ is unspecified) ERROR: dependency 'slam' is not available for package 'tm' * removing '/Documents/R/win-library/2.15/tm' Warning in install.packages :

SLAM:gmapping

匿名 (未验证) 提交于 2019-12-03 00:34:01
Package Summary Released Documented This package contains a ROS wrapper for OpenSlam's Gmapping. The gmapping package provides laser-based SLAM (Simultaneous Localization and Mapping), as a ROS node called slam_gmapping. Using slam_gmapping, you can create a 2-D occupancy grid map (like a building floorplan) from laser and pose data collected by a mobile robot. Maintainer status: maintained Maintainer: Vincent Rabaud <vincent.rabaud AT gmail DOT com> Author: Brian Gerkey License: CreativeCommons-by-nc-sa-2.0 Source: git https://github.com/ros-perception/slam_gmapping.git (branch: hydro-devel)

SLAM:loam算法架构分析

匿名 (未验证) 提交于 2019-12-03 00:30:01
在研读了论文及开源代码后,对LOAM的一些理解做一个整理。 文章:Low-drift and real-time lidar odometry and mapping 开源代码:https://github.com/daobilige-su/loam_velodyne 系统概述 LOAM的整体思想就是将复杂的SLAM问题分为:1. 高频的运动估计; 2. 低频的环境建图。 Lidar接收数据,首先进行Point Cloud Registration,Lidar Odometry以10Hz的频率进行运动估计和坐标转换,Lidar Mapping以1Hz的频率构建三维地图,Transform Integration完成位姿的优化。这样并行的结构保证了系统的实时性。 接下来是代码的框架图: 整个算法分为四个模块, 相对于其它直接匹配两个点云的算法,LOAM是通过提取特征点进行匹配之后计算坐标变换。具体流程为:ScanRegistration 提取特征点并排除瑕点; LaserOdometry从特征点中估计运动,然后整合数据发送给LaserMapping;LaserMapping输出的laser_cloud_surround为地图;TransformMaintenance订阅LaserOdometry与LaserMapping发布的Odometry消息,对位姿进行融合优化

SLAM:经典2D_SLAM算法比较:Hector slam、gmapping、cartographer

匿名 (未验证) 提交于 2019-12-03 00:30:01
Hector slam: Hector slam利用高斯牛顿方法解决scan-matching问题,对传感器要求较高。 缺点:需要雷达(LRS)的更新频率较高,测量噪声小。所以在制图过程中,需要robot速度控制在比较低的情况下,建图效果才会比较理想,这也是它没有回环(loop close)的一个后遗症;且在里程计数据比较精确的时候,无法有效利用里程计信息。 优点:不需要使用里程计,所以使得空中无人机及地面小车在不平坦区域建图存在运用的可行性; 利用已经获得的地图对激光束点阵进行优化, 估计激光点在地图的表示,和占据网格的概率 ; 利用高斯牛顿方法解决scan-matching 问题,获得激光点集映射到已有地图的刚体变换(x,y,theta);为避免局部最小而非全局最优,使用多分辨率地图;导航中的状态估计加入惯性测量系统(IMU),利用EKF滤波; 补充 gmapping: scanmatch方法: 链接 gmapping是目前应用最广的2D slam 方法,利用RBPF方法,故需要了解粒子滤波算法。scan-match方法在于估计机器人位置(pose),利用梯度下降的方法,在当前构建的地图,与当前的激光点,和机器人位置(pose)为初始估计值。 粒子滤波的方法一般需要大量的粒子来获取好的结果,但这必会引入计算的复杂度;粒子是一个依据过程的观测逐渐更新权重与收敛的过程