| ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange |
Hey guys,
Is there any ROS 3D pointcloud SLAM package available, which does not use any odometry sources? http://wiki.ros.org/ethzasl_icp_mapper seems to require the sensor_frame → /odom transform.
Thanks.
For depth only,
http://wiki.ros.org/loam_velodyne （code not available now）
http://sourceforge.net/p/slam6d/code/... （SLAM 6D）
https://github.com/search?q=velodyne+...
As for RGBD sensor, some state-of-the-art algorithms are listed below.
actually I am not talking about visual odometry. I am looking for package that only makes use of pointcloud data, for example from a Velodyne sensor, and perform 3D SLAM. Thanks!
You're welcome. loam_velodyne seems to be the best, but now the source code cannot be accessed. Maybe you can try implementing their algorithm described in their paper.
(probably old) loam_velodyne code can be found here: http://docs.ros.org/indigo/api/loam_v...
Hi @Kailegh, the original loam_velodyne repository is no longer available (I think the author founded Real Earth). However there is a fork here that seems to be active. If you try it, let us know how it works for you.
Asked: 2015-07-01 02:46:13 -0600
Seen: 11,245 times
Last updated: Jul 02 '15
ROS Answers is licensed under Creative Commons Attribution 3.0 Content on this site is licensed under a Creative Commons Attribution Share Alike 3.0 license.
