Instructions to use CWKAM/microduck-sad-duck with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Microduck
How to use CWKAM/microduck-sad-duck with Microduck:
# Replace SLOT with the slot specified in the model card (walk, stand, sitstand, ground_pick, kick_left, kick_right, roulade). sudo robotctl policy load SLOT CWKAM/microduck-sad-duck
- Notebooks
- Google Colab
- Kaggle
sad-duck
ๅทๆ้ดจ Sad Duck: walks 5 steps, sits, slowly hangs its head, shakes it, two quacks (combo of Pollen velstand walk + Pollen Got a Talent sitstand reference, switched by body[0])
A perpetual policy for the microduck (61-D observation, 14 actions, 50 Hz). Runs until told otherwise โ a gait, loaded into a policy slot.
Run it on a robot
sudo robotctl policy load <slot> CWKAM/microduck-sad-duck
The observation normalizer is baked into policy.onnx; feed raw observations.
manifest.json follows schema 2 of the microduck policy manifest (docs/policy-manifest.md in the daemon repo).
Training
- repo:
pollen-robotics/microduck_rl - branch:
main - commit:
6ff40704a - exported from a checkout with uncommitted changes
- Downloads last month
- 3