MicroDuck Jump
Raises happy-hop's band to an in-place hop of 3 to 6 cm on stock servos, with the checkpoint chosen by in-band rate rather than by recency: over 128 episodes half land inside the band and none fall. Its own acceptance checklist records the failure as well, a 128 N landing peak against a 40 N target, with the fix identified but not yet validated. Sim-only.
https://github.com/chenp9527/microduck-jump61 OBSERVATIONS 14 ACTIONS 50 HZ COMPATIBILITY NOT INDEPENDENTLY VERIFIED
AWESOME MICRODUCK INDEX
MicroDuck Jump
Raises happy-hop's band to an in-place hop of 3 to 6 cm on stock servos, with the checkpoint chosen by in-band rate rather than by recency: over 128 episodes half land inside the band and none fall. Its own acceptance checklist records the failure as well, a 128 N landing peak against a 40 N target, with the fix identified but not yet validated. Sim-only.
Project Overview
Trains the MicroDuck — an ~800 g, ~25 cm bipedal robot — to perform an episodic in-place hop of 3–6 cm , on the stock XL330 servos , using the microduck rl training stack (mjlab / MuJoCo Warp + PPO).
Inspired by joanfox's happy-hop (original band 1–3 cm); this work raises the band to 3–6 cm and documents what the hardware can and cannot do.
Two real rollouts of the delivered policy ( best jump policy.pt ) in MuJoCo.
Task
| Field | Value |
|---|---|
| Source | GITHUB SOURCE |
| Runtime contract | 61 observations / 14 actions / 50 Hz |
| Verification | Pending independent Duckio review |
| Artifact | Not indexed |
Source Coverage
The upstream README includes: Demo, duck_RL1 — hop from standstill, duck_RL2 — repeated hops, landing recovery, Result, Acceptance checklist, What is in this repo, Reproduce, Key findings.
Intended Use
Use this entry to assess the project and locate its canonical implementation. Read the complete README, inspect the manifest and artifacts, and reproduce the source's evaluation before assigning simulation or hardware verification.