Ask Your Question
0

Best VSLAM Algorithm for Outdoor Navigation

asked 2021-11-28 17:52:11 -0600

Nabil Miri gravatar image

Hello, I am building an outdoor robot and would like to know what is the most suitable algorithm of visual SLAM for outdoor robot navigation using ROS.

edit retag flag offensive close merge delete

2 Answers

Sort by ยป oldest newest most voted
0

answered 2021-11-29 14:41:44 -0600

updated 2021-11-29 14:42:11 -0600

I'm not usually about advertising my papers in this venue, but I think some work here could give you some good context https://arxiv.org/abs/2107.07589 "A Comparison of Modern General-Purpose Visual SLAM Approaches". The aim of the paper was comparing existing openly available VSLAM systems for practical service robot application.

While we do not specifically focus on "Outdoor" you can see extensive discussions about the weaknesses and strengths of different methods given access to different hardware in various service environments (including outdoors as an important subsection).

edit flag offensive delete link more

Comments

This paper is really informative, thanks

Nabil Miri gravatar image Nabil Miri  ( 2021-12-03 15:26:27 -0600 )edit
0

answered 2021-11-29 09:00:26 -0600

This is not all inclusive answer because the subject it's a very broad and well researched. Excluding hardware demands as this another broad subject, I will just give you some guidance to start your research.

For example ORB_SLAM2 is well established and popular ROS community.

ORB_SLAM2: 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.

Reference: https://github.com/appliedAI-Initiati...

To compare the performance against others, you can read ORB-SLAM: a Versatile and Accurate Monocular SLAM System goes in depth about the particulars of benefits, benchmarks and results http://webdiis.unizar.es/~raulmur/Mur...

If you visit KITTI Vision Benchmark Suite: You will find hundreds of implementations, with papers and many algorithms that optimize for particular requirements. http://www.cvlibs.net/datasets/kitti/...

From this you can use KITTI dataset to test your algorithm and compare performance to others as well. All these implementations can be integrated with ROS.

Other implementation to consider is Open VSLAM: https://arxiv.org/pdf/1910.01122.pdf

And more recent and extremely promising ORB_SLAM3: https://github.com/UZ-SLAMLab/ORB_SLAM3

edit flag offensive delete link more

Comments

Thanks for this info

Nabil Miri gravatar image Nabil Miri  ( 2021-12-03 15:26:40 -0600 )edit

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account.

Add Answer

Question Tools

3 followers

Stats

Asked: 2021-11-28 17:52:11 -0600

Seen: 38 times

Last updated: Nov 29 '21