NVlabs / RVT

Official Code for RVT-2 and RVT

Home Page:https://robotic-view-transformer-2.github.io/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

proprioception dimension

Harimus opened this issue · comments

Hi first of all thank you for the amazing work of RVT.

I have a question. I'm trying to reproduce some of the results on the real-robot setting with a Franka robot, and I'm trying to understand the proprioception data. According to the MTV config the proprioception_dim is 4. What does those 4dim represent? If it's the joint position I assume it should bigger, and if it was cartesian position of the end-effector I assume it is either 3 or 6 (or 7 if quaternion).

Thank you in advance

Hi @Harimus,

I think #19 should address your question. Let me know if any questions still remain.

Best,
Ankit

ah wow I missed that one somehow, thank you!