Giter Club home page Giter Club logo

gslam's Introduction

GSLAM (General Simultaneous Localization and Mapping Framework)

1. Introduction

1.1. What is GSLAM?

GSLAM is aimed to provide a general open-source SLAM framework with following features :

-> 1. Share the same API while maintain compatibility with different SLAM systems (such as feature based or direct methods).

-> 2. Support Monocular, Stereo, RGB-D or any custom input types (SAR, IMU, GPS and so on).

-> 3. Provide high efficient implementations of SLAM util classes like SO3, SE3, Camera, IMU, GPS, Bundle and so on.

-> 4. Support other features like coorperation SLAM to build a singular map.

1.2. What we can do with GSLAM?

  1. For SLAM developers : Everyone can develop their own SLAM implementation based on GSLAM and publish it as a plugin with open-source or not.
  2. For SLAM users : Applications are able to use different SLAM plugins with the same API without recompilation and implementations are loaded at runtime.

1.3. Folder structure

  • src -- source folder
  • GSLAM -- Common SLAM APIs
  • GUtils -- Utils for GSLAM implementations including Pose optimization, BA frame work
  • ORBSLAM -- Implementation of ORBSLAM (SLAM plugin demo)
  • dso -- Implementation of dso (SLAM plugin demo)
  • gslam -- Test system of GSLAM (Apllication demo)
  • Thirdparty --- thirdparty libraries
  • PIL -- the basic c++ library for configuration, display, plugin loader (enssential, buildin)
  • Eigen -- an opensoure linear algebra library (optional, needed by ORBSLAM plugin)
  • g2o -- a general optimization framework (optional & buildin, needed by ORBSLAM plugin)
  • boost -- a c++ development library (optional, needed by ORBSLAM)
  • pba -- an opensoure bundle implementation on GPU (optional)
  • doc --- documents

1.4. Implemented SLAM plugin

SLAM Plugin Name       Plugin Authers Demostration
DSO Yong Zhao DSO
ORBSLAM Yong Zhao ORBSLAM

2. Compilation

2.1. Compile on linux (Tested in Ubuntu 14.04 and 16.04)

2.1.1 Install dependency

Tips: Use ''bash buildAll.sh -d'' to install dependencies. Or you can install the following dependencies by yourself:

Lapack&Blas : sudo apt-get install libblas3 libblas-dev liblapack-dev liblapack3

Boost : sudo apt-get install libboost-all-dev libboost-thread* libboost-system* libboost-filesystem*

OpenCV : sudo apt-get install libopencv-dev

Qt : sudo apt-get install build-essential g++ libqt4-core libqt4-dev libqt4-gui qt4-doc qt4-designer

OpenGL:sudo apt-get install freeglut3 freeglut3-dev libglew-dev libglew1.10

QGLViewer : sudo apt-get install libqglviewer-dev libqglviewer2

Chomod for dso: sudo apt-get install libsuitesparse-dev libeigen3-dev

** WARNING: It it Qt4 instead of Qt5 that should be installed! For Ubuntu 16.06 libqglviewer-qt4 should be linked. **

2.1.2 Compile and install PIL

git clone https://github.com/zdzhaoyong/PIL2
cd PIL2;mkdir build;cd build;
cmake ..;make;sudo make install;

2.1.3 Compile and insall GSLAM

mkdir build;cd build;
cmake ..;make;sudo make install

###2.2 Compile on windows Not tested yet.

3. Run the demo

3.1. Test modules

gslam Act=Tests [Cases=[case1,case2,...,caseN]]

3.2. Test slam system

cd data
gslam conf=orbslam.cfg

3.3. Configuration with Svar

More parameters can be setted with Svar at file *.cfg. See more details of Svar at PILBASE.

4. Contacts

YongZhao: [email protected]

ShuhuiBu: [email protected]

gslam's People

Contributors

zdzhaoyong avatar b0rja avatar bushuhui avatar

Watchers

James Cloos avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.