Does Diffusion Policy run on LeKiwi?
partial
Scope: Training evidenced by public checkpoint(s); on-robot inference not documented by a primary source.
Capabilities
| Capability | State | Notes | Evidence |
|---|---|---|---|
| Train / fine-tune | works | ev-hub-liosgr-diffusion, ev-hub-wiscohumanoids-diffusion | |
| 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 2026-09-18verified 2026-10-25 (today)
config.json type=diffusion; train_config.json dataset lioSgr/pick_toy_elephant (100000 steps), whose meta/info.json robot_type=lekiwi_client (50 episodes; arm joints plus x/y/theta base velocities; front + wrist cameras).
https://huggingface.co/lioSgr/dp_pick_toy_elephant - T3 · community reportedhub-checkpointsource 2026-04-15verified 2026-10-25 (today)
config.json type=diffusion; train_config.json dataset wiscohumanoids/pick_up_single_colored_cube_into_tape_v7 (80000 steps), whose meta/info.json robot_type=lekiwi_client (226 episodes).
https://huggingface.co/wiscohumanoids/pick_up_single_colored_cube_into_tape_v7_diffusion_h128
Embed this cell
Badge for READMEs and model cards. It always shows the current state.
[](https://caniembody.pages.dev/compat/lekiwi/diffusion)<iframe src="https://caniembody.pages.dev/embed/lekiwi/diffusion" width="380" height="132" style="border:0" title="Diffusion Policy on LeKiwi | CanIEmbody"></iframe>History
No committed history yet. Source file: data/compat/lekiwi__diffusion.yaml