search

google-research / ravens

Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet. Transporter Nets, CoRL 2020.
https://transporternets.github.io
Apache License 2.0
538 stars 93 forks source link

Adding new robots #22

Open siddk opened 2 years ago

siddk commented 2 years ago

Love the Ravens work & ability to script demonstrations with the provided robot. I'm looking to work on cross-embodiment transfer with language, specifically trying to use the existing Ravens workspace (and as much of the demo scripting code as possible), but with a variety of different robots (e.g., Franka Emika Panda, Sawyer, etc.).

How straightforward would it be to drop in a new URDF and start generating new demos for a new robot?

ZhouYFeng commented 1 year ago

Hi, @siddk

I am trying the Ravens. But I run it on the remote GPU server by SSH, the --disp must be set as False.

I want to know how to visualize the process of simulation like the picture below. (https://user-images.githubusercontent.com/111882855/223467716-ca7944fe-4ad7-4eac-b298-4a93182d53ac.png)

Thanks.