Matrix/Franka Research 3/Diffusion Policy

Does Diffusion Policy run on Franka Research 3?

partial

T3 · community reportedlast verified 2026-10-25 · todayLeRobot

Scope: Training evidenced by public checkpoint(s); on-robot inference not documented by a primary source.

Capabilities

Capability	State	Evidence
Train / fine-tune	works	ev-hub-sashopepi-diffusion-box, ev-hub-sashopepi-diffusion-tomato
Real-robot inference	no verified evidence	—
Simulation inference	no verified evidence	—
Teleop + record	no verified evidence	—

Evidence 2 sources; the cell shows the highest tier

T3 · community reportedhub-checkpointsource 2026-03-19verified 2026-10-25 (today)
config.json type=diffusion; train_config.json dataset SashoPepi/franka-gello-close-box-filtered (100000 steps), whose meta/info.json robot_type=fr3 (75 episodes, 8-D state, two cameras; GELLO-teleoperated per the repo names). Auto-generated card, no results.
https://huggingface.co/SashoPepi/lerobot_diffusion_policy_filtered
T3 · community reportedhub-checkpointsource 2026-03-26verified 2026-10-25 (today)
config.json type=diffusion; train_config.json dataset SashoPepi/tomato_close_box (6000 steps), whose meta/info.json robot_type=fr3 (257 episodes).
https://huggingface.co/SashoPepi/tomato_close_box_diffusion_3Ksteps

Embed this cell

Badge for READMEs and model cards. It always shows the current state.

[![Diffusion Policy on Franka Research 3: partial](https://caniembody.pages.dev/badge/franka-fr3/diffusion.svg)](https://caniembody.pages.dev/compat/franka-fr3/diffusion)

<iframe src="https://caniembody.pages.dev/embed/franka-fr3/diffusion" width="380" height="132" style="border:0" title="Diffusion Policy on Franka Research 3 | CanIEmbody"></iframe>

History

No committed history yet. Source file: data/compat/franka-fr3__diffusion.yaml