Instructions to use SusanSS/microduck-walking-full-hill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Microduck
How to use SusanSS/microduck-walking-full-hill with Microduck:
sudo robotctl policy load walk SusanSS/microduck-walking-full-hill
- Notebooks
- Google Colab
- Kaggle
walking-full-hill
MicroDuck walking_full flat-ground baseline on 8-degree hill, 5/5 finishes at 0.45 m/s
A perpetual policy for the microduck (61-D observation, 14 actions, 50 Hz). Runs until told otherwise โ a gait for the walk slot.
Run it on a robot
sudo robotctl policy load walk SusanSS/microduck-walking-full-hill
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:
9aaec6db4
- Downloads last month
- 9