Instructions to use chair510/microduck-ballkick with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Microduck
How to use chair510/microduck-ballkick 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 chair510/microduck-ballkick
- Notebooks
- Google Colab
- Kaggle
ballkick
Right-foot ball kick. Trained 2026-11-10 on an M1 Pro (Mjlab-BallKick-Flat-MicroDuck, 400 rounds x 256 envs). Mean reward 0.8 to 53.4; falls to zero.
A episodic policy for the microduck (61-D observation, 14 actions, 50 Hz). Runs 5.0 s and returns itself to a standing pose.
Run it on a robot
sudo robotctl policy add ballkick chair510/microduck-ballkick
robotctl robot do ballkick
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:
develop - commit:
0daab160d - exported from a checkout with uncommitted changes
- Downloads last month
- 16