microduck-running

Running policy robustified from a 1.687 m/s speed frontier with velocity pushes, centre-of-mass variation and initial tilt, holding 1.651 m/s nominal and 1.612 m/s under a combined backlash and disturbance battery. The author calls it a hardware candidate and says heading and lateral drift remain substantial. Sim-only.

Project Overview

--- thumbnail: https://huggingface.co/HannesVonEssen/microduck-running/resolve/main/media/social-preview.png pipeline tag: reinforcement-learning tags: [microduck, microduck-policy, mjlab, robotics, locomotion, running] license: apache-2.0 ---

A robustified forward-running policy for the stock MicroDuck on flat ground. The default artifact is iteration 12,195 , continued from the 1.687 m/s speed frontier with progressively stronger velocity pushes, centre-of-mass variation, and initial tilt.

The mat video uses the preserved iteration-8,749 controller, not the new root policy. Its obstacle, collision augmentation, camera treatment, post-impact motor cutoff, and sparks are scripted demonstration elements. The policy has no obstacle perception and did not learn to react to a mat. Both videos are silent.

Task

Field	Value
Source	HUGGING FACE MODEL SOURCE
Runtime contract	61 observations / 14 actions / 50 Hz
Verification	Pending independent Duckio review
Artifact	Not indexed

Source Coverage

The upstream README includes: Normal simulation rollout — iteration 12,195, Run-into-mat edit — legacy iteration 8,749, Versions, Command, Try it in simulation, Continue training, Contract, Simulation evaluation.

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.