ORB-SLAM2

ORB-SLAM2 Authors: Raul Mur-Artal, Juan D. Tardos, J. M. M. Montiel and Dorian Galvez-Lopez (DBoW2). The original implementation can be found here.

ORB-SLAM2 ROS node

This is the ROS implementation of the ORB-SLAM2 real-time SLAM library for Monocular, Stereo and RGB-D cameras that computes the camera trajectory and a sparse 3D reconstruction (in the stereo and RGB-D case with true scale). It is able to detect loops and relocalize the camera in real time. This implementation removes the Pangolin dependency, and the original viewer. All data I/O is handled via ROS topics. For visualization you can use RViz. This repository is maintained by Lennart Haller on behalf of appliedAI.

Features

• Full ROS compatibility
• Supports a lot of cameras out of the box, such as the Intel RealSense family. See the run section for a list
• Data I/O via ROS topics
• Parameters can be set with the rqt_reconfigure gui during runtime
• Very quick startup through considerably sped up vocab file loading
• Full Map save and load functionality based on this PR.
• Loading of all parameters via launch file
• Supports loading cam parameters from cam_info topic

Related Publications:

[Monocular] Raúl Mur-Artal, J. M. M. Montiel and Juan D. Tardós. ORB-SLAM: A Versatile and Accurate Monocular SLAM System. IEEE Transactions on Robotics, vol. 31, no. 5, pp. 1147-1163, 2015. (2015 IEEE Transactions on Robotics Best Paper Award). PDF.

[Stereo and RGB-D] Raúl Mur-Artal and Juan D. Tardós. ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras. IEEE Transactions on Robotics, vol. 33, no. 5, pp. 1255-1262, 2017. PDF.

[DBoW2 Place Recognizer] Dorian Gálvez-López and Juan D. Tardós. Bags of Binary Words for Fast Place Recognition in Image Sequences. IEEE Transactions on Robotics, vol. 28, no. 5, pp. 1188-1197, 2012. PDF

1. License

ORB-SLAM2 is released under a GPLv3 license. For a list of all code/library dependencies (and associated licenses), please see Dependencies.md.

For a closed-source version of ORB-SLAM2 for commercial purposes, please contact the authors: orbslam (at) unizar (dot) es.

If you use ORB-SLAM2 (Monocular) in an academic work, please cite:

@article{murTRO2015,
  title={{ORB-SLAM}: a Versatile and Accurate Monocular {SLAM} System},
  author={Mur-Artal, Ra\'ul, Montiel, J. M. M. and Tard\'os, Juan D.},
  journal={IEEE Transactions on Robotics},
  volume={31},
  number={5},
  pages={1147--1163},
  doi = {10.1109/TRO.2015.2463671},
  year={2015}
 }

if you use ORB-SLAM2 (Stereo or RGB-D) in an academic work, please cite:

@article{murORB2,
  title={{ORB-SLAM2}: an Open-Source {SLAM} System for Monocular, Stereo and {RGB-D} Cameras},
  author={Mur-Artal, Ra\'ul and Tard\'os, Juan D.},
  journal={IEEE Transactions on Robotics},
  volume={33},
  number={5},
  pages={1255--1262},
  doi = {10.1109/TRO.2017.2705103},
  year={2017}
 }

2. Building orb_slam2_ros

We have tested the library in Ubuntu 16.04 with ROS Kinetic and Ubuntu 18.04 with ROS Melodic. A powerful computer (e.g. i7) will ensure real-time performance and provide more stable and accurate results. A C++11 compiler is needed.

Getting the code

Clone the repository into your catkin workspace:

git clone https://github.com/appliedAI-Initiative/orb_slam_2_ros.git

ROS

This ROS node requires catkin_make_isolated or catkin build to build. This package depends on a number of other ROS packages which ship with the default installation of ROS. If they are not installed use rosdep to install them. In your catkin folder run

sudo rosdep init
rosdep update
rosdep install --from-paths src --ignore-src -r -y

to install all dependencies for all packages. If you already initialized rosdep you get a warning which you can ignore.

Eigen3

Required by g2o. Download and install instructions can be found here. Otherwise Eigen can be installed as a binary with:

sudo apt install libeigen3-dev

Required at least Eigen 3.1.0.

Building

To build the node run

catkin build

in your catkin folder.

3. Configuration

Vocab file

To run the algorithm expects both a vocabulary file (see the paper) which ships with this repository.

Config

The config files for camera calibration and tracking hyper paramters from the original implementation are replaced with ros paramters which get set from a launch file.

ROS parameters, topics and services

Parameters

There are three types of parameters right now: static- and dynamic ros parameters and camera settings. The static parameters are send to the ROS parameter server at startup and are not supposed to change. They are set in the launch files which are located at ros/launch. The parameters are:

File truncated at 100 lines see the full file