Instructions to use apirrone/velstand_improve_standup with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Microduck
How to use apirrone/velstand_improve_standup with Microduck:
sudo robotctl policy load walk apirrone/velstand_improve_standup
- Notebooks
- Google Colab
- Kaggle
|
Download README.md from apirrone/velstand_improve_standup: direct link, hf CLI and curl.
- Browser
- Download file 977 Bytes
-
https://huggingface.co/apirrone/velstand_improve_standup/resolve/main/README.md
- Command line
-
hf download hf://apirrone/velstand_improve_standup/README.md
-
curl -L -o README.md https://huggingface.co/apirrone/velstand_improve_standup/resolve/main/README.md
977 Bytes
metadata
tags:
- microduck
- robotics
- reinforcement-learning
- onnx
- microduck-slot:walk
library_name: microduck
pipeline_tag: robotics
velstand_improve_standup
velstand get-up fix: swing-foot clearance + no side freeze (dk50vhok@5000)
A perpetual policy for the microduck (61-D observation, 14 actions, 50 Hz). Runs until told otherwise — a gait for the walk slot.
Run it on a robot
sudo robotctl policy load walk apirrone/velstand_improve_standup
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
- task_id:
Mjlab-VelStand-Rough-Backlash-MicroDuck - repo:
pollen-robotics/microduck_rl - branch:
standup_foot_catch - commit:
12cfed24d - run:
pollen-robotics/mjlab_microduck/dk50vhok - checkpoint:
5000