Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Launch files #19

Merged
merged 11 commits into from
Dec 20, 2013
Merged

Launch files #19

merged 11 commits into from
Dec 20, 2013

Conversation

lindzey
Copy link
Contributor

@lindzey lindzey commented Dec 19, 2013

These are the changes to the clear_table state machine and the launch files that allow us to use the same launch file for the fully-autonomous demo and the grabcut demo, just changing one command line argument.

* pr2_hydro.launch is from /etc/ros/hydro/robot.launch, modified to point to robot_hydro.launch
* robot_hydro.launch is from /opt/ros/hydro/share/pr2_bringup/pr2.launch, modified to:
  * remove arm & head cameras
  * start up the head-mount kinect
  * remove the EKF, replace with static_transform_publisher from odom_combined -> base_footprint (to avoid the tiny angular offsets in pose)
…le any combination of our pick & place pipeline's options
* clear_table_unified.launch can now switch between ORK/Grabcut object segmentation,
based on command-line argument
* this required combining clear_table_moveit.py and clear_table_moveit_ork.py
* assumes that robot.launch, rviz, move_group, and ork_core are launched separately
…added yesterday when I made pose/dims optional)
…pdate at once. I'm not sure it's an improvement...
@ghost ghost assigned dejanpan Dec 19, 2013
@@ -29,8 +30,7 @@ def __init__(self):
#self.sensors = SensorHandler()
self.scene = SceneHandler()
self.orkClient = actionlib.SimpleActionClient('ork_tabletop', TabletopAction)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

So I am wondering if I should not rather implement ORK stuff inside the SensorHandler class to have one consistent interface to all segmentation algorithms? The same as below for grabcut.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Created an issue, see #22

dejanpan added a commit that referenced this pull request Dec 20, 2013
@dejanpan dejanpan merged commit 45fd0d5 into master Dec 20, 2013
@dejanpan dejanpan deleted the launch-files branch December 20, 2013 19:16
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants