Clear table #9
Merged
Clear table #9
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…_16UC1, in addition to depth/image of type CV_32FC1
…that a full data set is received
…uster service to determine extent of segmented object
…veit fails quite often
… actionlib interface rather than moveit_commander
… an actual bounding box, rather than an approximation. seems to work better, so I am committing, but it needs to be cleaned up a ton before pushing to master
…ok that was used to develop it.
…it now lives with the simple_robot_control package
…it now lives with the simple_robot_control package
…o the clear_table state machine
ghost
assigned 
| return 'segmentation_failed' | ||
|
|
||
| userdata.object_points = points | ||
| userdata.object_name = 'obj1' |
There was a problem hiding this comment.
is this just a transient name or what does it happen if we assert many objects?
There was a problem hiding this comment.
We only segment one object at a time, so it's a temporary name.
|
|
||
| locations.append(pl) | ||
| return locations | ||
|
|
There was a problem hiding this comment.
In general it would be great if frame_ids and joint_names would be parametrized and if place locations came from a config file
We can convert this into an issue!
|
To me this looks good, if possible I'd try it out on my account. Mostly parametrization issues which we should convert into the repository issue. |
…; adding loop to try repeatedly to get kinect data rather than reporting failure instantly (takes time for assemble_kinect to get first dataset)
…ther tahn my local copy of it
…s to explain magic number
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
A way-too-big branch, with lots of changes.
This is what I just demoed to D with the fully-automated table clearing (using ORK) and the shared autonomy table clearing using Grabcut.
For the ipython notebooks, it'll be easier to look review them here:
http://nbviewer.ipython.org/github/SharedAutonomyToolkit/shared_autonomy_perception/blob/clear_table/random_snippets/clear_table.ipynb
http://nbviewer.ipython.org/github/SharedAutonomyToolkit/shared_autonomy_perception/blob/clear_table/random_snippets/moveit_pick.ipynb
Dependencies:
git clone [email protected]:bosch-ros-pkg/cluster_grasp_planner.git -b hydro-devel
apt-get install ros-hydro-moveit*