Microduck skill tree (sim only)
Collection
Policies trained in simulation for a Pollen Robotics Microduck still on order, one level per skill, plus the training log. Sim only so far. • 6 items • Updated
standup
Get-up policy (Mjlab-StandUp-Flat-MicroDuck), simulation only: 25,000 iterations (the maker's 15,000 plus a 10,000 extension), 4096 envs, 407 min on one RTX 5090. Stands from sitting and from face down and holds standing; from flat on its back it freezes half-rolled (0 of 2 takes). Not yet tested on a real Microduck.
A episodic policy for the microduck (61-D observation, 14 actions, 50 Hz). Runs 6.0 s and returns itself to a standing pose.
Run it on a robot
sudo robotctl policy add standup witcheer/microduck-standup
robotctl robot do 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
- repo:
pollen-robotics/microduck_rl - branch:
develop - commit:
53b8971b6