Ask Your Question


asked 2017-10-12 03:00:43 -0500 gravatar image

hi all, i am new in ros and rtabmap. my goal is create map and navigate around the map with simulator robot. my work is not on line. i captured stereo images from two web cam and save these images at left and right image files. then used tutorial of rtabmap and draw map for stereo images from this link ( ). then i want re-use this map for navigation. i studied tutorials of rtabmap_ros from this link ( ) but i don't understand. please help me and write how can i reuse map for navigation?

edit retag flag offensive close merge delete


Hello, we will need more info to help you. Step by step, where are you in the tutoriel ? what's the issue ? How did you tried to go over it and why did it still failed ?

TTDM gravatar image TTDM  ( 2017-10-12 07:16:15 -0500 )edit

thanks TTDM, i am new in rtabmap. i have to web cam and take left and right images. stereo images saved in file and for simulation location and mapping from these camera i used rtabmap_ros (link above) i have not a robot but i want path planning. but i don't know how? gravatar image  ( 2017-10-12 08:23:14 -0500 )edit

at tutorial of rtabmap exit a example ( but this example is for kinetic. how can i use this example for stereo images? gravatar image  ( 2017-10-12 08:27:15 -0500 )edit

kinetic is the name of the ros distrbution, the first part of its version ID if you prefer. I suggest you to follow the ROS tutorials to really understand the tool you are trying to use, ROS, then it will be easier to work on the path planning.

TTDM gravatar image TTDM  ( 2017-10-12 08:35:16 -0500 )edit

oh excuse me! I mean is kinect (RGB_D camera) gravatar image  ( 2017-10-12 09:02:19 -0500 )edit

1 Answer

Sort by ยป oldest newest most voted

answered 2017-10-12 09:22:36 -0500

TTDM gravatar image

Answering your comments, a RGB-D images is simply an rgb image associated with a depth image.

According to the rtabmap documentation, all the infos coming from the kinect are given as entry in the rtabmap node as 3 msgs :

  1. A sensor_msgs/Image which gives the rgb image
  2. A sensor_msgs/Image which gives the depth image
  3. A sensors_msgs/Camerainfo which gives the info of the rgb camera.

So what you can do ss give the left rgb image and left camera info directly as if it was the kinect. Then for the depth image, you add a node which contains a stereo algorithm for exemple this one then you define its output image as the depth image in entry of the rtabmap. If you don't know about it, you should look into what's called "remapping" to do those steps.

edit flag offensive delete link more

Your Answer

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

Add Answer

Question Tools

1 follower


Asked: 2017-10-12 03:00:43 -0500

Seen: 112 times

Last updated: Oct 12 '17