search

pantor / learning-pick-and-place

Self-supervised Learning for Precise Pick-and-place without Object Model
https://pantor.github.io/learning-pick-and-place/
GNU General Public License v3.0
29 stars 10 forks source link

Using Self-supervised Learning for Precise Pick-and-place without Object Model with a KUKA iiwa #5

Closed Marcelbgit closed 2 years ago

Marcelbgit commented 2 years ago

Hello Pantor,

thanks for sharing your very exciting work and code! Is it possible to adapt your code to a KUKA iiwa? What steps would be necessary here? Replacing the launch and include files would be my guess. Are there also other interfaces that I need to adapt for this. I would be glad about the help and answer. I would like to test and develop your code for other applications.

Best regards, Marcel

pantor commented 2 years ago

Hi Marcel,

it is definitely possible to adapt this project for the Kuka iiwa! Please keep in mind that this repository is not meant to be plug-and-play, so it will be a bit of work to integrate all your hardware (robot, camera, gripper) and setting up the software. You can also have a look at Griffig, which currently only does grasp calculation, but might be a useful to understand the abstraction between manipulation planning and robot control.

Anyway, you are right that you would primarily need to adapt the Robot class, the launch files, and a few things in config.py. If there are any more specific questions, feel free to ask.