fffiloni/microduck-polite-bow-b1d864

Polite Bow — Microduck policy

Generated with Microduck Motion Lab from Pollen Robotics' microduck_rl sim-to-real stack.

Prompt

Recovered from cloud artifacts: Small, gentle bow with head and body lowering, returning to standing

Reproducibility

• Task: Mjlab-PoliteBow-Flat-MicroDuck
• Base recipe: standup
• microduck_rl revision: d424a0c899f6b33cbd3daeb279913134349c0b63
• Parallel environments: 4096
• PPO iterations: 1000
• Compiler: guided-standup-v0.4
• Final repo: fffiloni/microduck-polite-bow-b1d864

Deployment checks

• Official scripts/export.py: passed
• Shared actor observation contract: 61D
• Policy action output: 14D
• CPU MuJoCo/ONNX rehearsal: passed
• Automatic motion-quality gate: passed
• Preview recipe: standup
• Preview driver: unknown
• Semantic match unverified: False
• Maximum joint motion: unknown°
• XY displacement: unknown m
• Ball displacement: unknown m

Files

• policy.onnx — deployment policy exported by upstream scripts/export.py
• preview.mp4 — headless CPU MuJoCo deployment rehearsal
• thumbnail.webp
• preview_metrics.json
• motion_spec.json
• resolved_plan.json
• compiled_motion.json
• training_result.json
• checkpoints/model_final.pt

A simulation preview is not a guarantee of safe real-robot behavior. Validate conservatively before deploying to hardware.