Object Recognation Kitchen(ORK) User Guide
User Manual:
Open the PDF directly: View PDF 
.
Page Count: 2
Work with Object Recognation Kitchen(ORK)
Caution: This document is not fully complete yet
ORK Official site
https://wg-perception.github.io/object_recognition_core/
Install relavent package for ros
sudo apt-get install ros-kinetic-object-recognition-core
do search on what else with object recognition by following command
apt-cache search ros-kinetic-object-recognition
install all the pacake
apt-get install ros-kinetic-object-recognition-capture
apt-get install ros-kinetic-object-recognition-core
apt-get install ros-kinetic-object-recognition-msgs
apt-get install ros-kinetic-object-recognition-reconstruction
apt-get install ros-kinetic-object-recognition-ros
apt-get install ros-kinetic-object-recognition-ros-visualization
apt-get install ros-kinetic-object-recognition-tod
apt-get install ros-kinetic-object-recognition-transparent-objects
install any of the following to the catkin_ws/src
git clone http://github.com/wg-perception/object_recognition_core
git clone http://github.com/wg-perception/capture
git clone http://github.com/wg-perception/reconstruction
git clone http://github.com/wg-perception/linemod
git clone http://github.com/wg-perception/ork_renderer
git clone http://github.com/wg-perception/tabletop
git clone http://github.com/wg-perception/tod
git clone http://github.com/wg-perception/transparent_objects
Edit ORK config file
You can edit the ork config file under the tabletop/conf folder, or you can copy the config files into
a package you perfer to have, or you can copy the original file to other folder as backup.
Find the pepper camera topics
While have the pepper_full launch runing, open a new terminal, run rostopic list to see what
topics does the Pepper have.
Modify the config file with relavent camera path for pepper as follow
detection.object.ros.ork
cd tabletop/conf
vim detection.object.ros.ork
Make sure is as following
parameters:
rgb_frame_id: CameraTop_optical_frame
rgb_image_topic: /pepper_robot/camera/front/image_rect_color
rgb_camera_info: /pepper_robot/camera/front/camera_info
depth_image_topic: /pepper_robot/camera/ir/image_raw
depth_camera_info: /pepper_robot/camera/ir/camera_info
detection.table.ros.ork
vim detection.table.ros.ork
Make sure is as following
parameters:
rgb_frame_id: 'CameraTop_optical_frame'
rgb_image_topic: '/pepper_robot/camera/front/image_rect_color'
rgb_camera_info: '/pepper_robot/camera/front/camera_info'
depth_image_topic: '/pepper_robot/camera/ir/image_raw'
depth_camera_info: '/pepper_robot/camera/ir/camera_info'
Build the workspace
catkin build –continue-on-failure
or if the workspace is build by catkin_make, then use
catkin_make
To add the workspace to your ROS environment you need to source the generated setup file:
. ~/catkin_ws/devel/setup.bash
check if the package can be found with roskpack find command
rospack find pepper_ork
If the package can be found, then continue follow the ork tutorial.
rosrun object_recognition_core detection -c `rospack nd
pepper_ork`/cong/detection.table.ros.ork
refrence site on how to get ORK work with robot (Japanese)
http://olfash.hateblo.jp/entry/fetch_experiment
