logos

ORB-SLAM

Authors: Raúl Mur-Artal, Juan D. Tardós, J. M. M. Montiel and Dorian Gálvez-López (DBoW2)
ORB-SLAM is a versatile and accurate SLAM solution for Monocular, Stereo and RGB-D cameras. It is able to compute in real-time the camera trajectory and a sparse 3D reconstruction of the scene in a wide variety of environments, ranging from small hand-held sequences of a desk to a car driven around several city blocks. It is able to close large loops and perform global relocalisation in real-time and from wide baselines. It includes an automatic and robust initialization from planar and non-planar scenes. See the related publication [1] for more details. Demostrating videos, code and related publications are shown below.

Source Code

ORB-SLAM: https://github.com/raulmur/ORB_SLAM . (Monocular. ROS integrated)
ORB-SLAM2: https://github.com/raulmur/ORB_SLAM2 . (Monocular, Stereo, RGB-D. ROS optional)

ORB-SLAM and ORB-SLAM2 are released under a GPLv3 license.
For a closed-source version for commercial purposes, please contact the authors: orbslam (at) unizar (dot) es.
January 2016

New ORB-SLAM2 for Monocular, Stereo and RGB-D Cameras

Find the code on GitHub: https://github.com/raulmur/ORB_SLAM2 .




July 2015

New Semi-Dense Reconstruction Results

We are currently able to perform semi-dense reconstructions using the accurately localised stream of keyframes from ORB-SLAM. Check our RSS 2015 paper [2]. See the video below running in real-time in an intel core i7-4700MQ. No GPU acceleration was used. This module has not been released yet.

Demostrating Videos in Public Datasets

(select the HD option in youtube)


Dataset: KITTI (Odometry benchmark). Sequence 00.
- Scene: large scale outdoors with multiple loops.
- Motion: car


Dataset: KITTI (Odometry benchmark). Sequence 05.
- Scene: large scale outdoors with multiple loops.
- Motion: car


Dataset: TUM RGB-D Benchmark . fr3_long_office_household.
- Scene: desk with a loop and relative scale changes
- Motion: hand-held


Dataset: TUM RGB-D Benchmark . fr3_walking_halfsphere.
- Scene: desk with people moving around
- Motion: hand-held

Related Publications

[1] 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, October 2015.
2015 IEEE Transactions on Robotics Best Paper Award .
DOI: 10.1109/TRO.2015.2463671
[pdf]

[2] Raúl Mur-Artal and Juan D. Tardós.
Probabilistic Semi-Dense Mapping from Highly Accurate Feature-Based Monocular SLAM.
Robotics: Science and Systems. Rome, Italy, July 2015.
[pdf] [poster]

[3] Raúl Mur-Artal and Juan D. Tardós.
ORB-SLAM: Tracking and Mapping Recognizable Features.
Robotics: Science and Systems (RSS) Workshop on Multi VIew Geometry in RObotics (MVIGRO), Berkeley, USA, July 2014. Oral presentation
[pdf]

[4] Raúl Mur-Artal and Juan D. Tardós.
Fast Relocalisation and Loop Closing in Keyframe-Based SLAM.
IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, June 2014.
[pdf]

[5] 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, October 2012.
DOI: 10.1109/TRO.2012.2197158
[pdf]


Last updated: May 2016