Ropedia A0: code-only robot policy hits 70.24% on RoboDojo, 75% first-try sim2real
liuziwei7 · x · 2026-10-24
Ropedia's new Ropedia-A0 introduces Code-Only-as-Policy: robot task policies written as code, with no model called at runtime.
- Scores 70.24% success on RoboDojo vs 46.85% for the best model-in-the-loop baseline.
- The policy is a shared code library with a thin program per task; programs reuse across episodes to generate unlimited trajectories, and skills transfer across tasks — doubling as an efficient data engine.
- The shared library generalizes to new embodiments (LIBERO) and simulators (MuJoCo) with only thin adapters, and achieves 75% first-try success on real-world pick-and-place with no retries.
Related event: Ropedia A0 Introduces Code-Only-as-Policy, Hitting 70.24% on RoboDojo(2 posts)→
More from Embodied
- microagi promises a billion robots by 2029; skeptics say scene understanding won't be solved by 2027 — AlexTensor · 2026-10-24
- Tesla registers 69 more Cybercabs, bringing its Robotaxi fleet to 420 vehicles — mitchdeg · 2026-10-24
- CMU RI PhD open-sources full robotics faculty job market application materials — sh_reya · 2026-10-24
- Holi-World turns egocentric video into 3D/4D data: 4B model beats zero-shot 27B — liuziwei7 · 2026-10-24
- Unitree's Wang Xingxing: GPT-6 Astra handles robot painting and Go with no specialized training — Afinetheorem · 2026-10-24
- Rodney Brooks on Amazon's 1M robots: real-world deployment is the hard part — rodneyabrooks · 2026-10-24