search

real-stanford / diffusion_policy

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion
https://diffusion-policy.cs.columbia.edu/
MIT License
1.39k stars 260 forks source link

Is it possible to release the code for the mid-level controller used in Franka? #90

Open Kimagure7 opened 3 months ago

Kimagure7 commented 3 months ago

In Appendix D.1, you mentioned that Experiments for Sauce Pouring and Spreading, Bimanual Egg Beater, Bimanual Mat Unrolling, and Bimanual Shirt Folding tasks are performed on the Franka robot station. For the non-haptic control, a custom mid-level controller is implemented to generate desired joint positions from desired end effector poses from the learned policies.

I already know that the Franka experiments used TRI's proprietary software infrastructure, therefore it cannot be open-sourced. Howerer, I am interested in Inverse Kinematics for robotic arm. Is it possible to release the code for the mid-level controller ?

Kimagure7 commented 3 months ago

Additionally, I've noticed that in the Franka kitchen task, it seems that motor state control is being used rather than end-effector pose control. Is my understanding correct?