Wayve researcher: there is no good sim2real — it's always real2sim2real
m_wulfmeier · x · 2026-10-28
Responding to the wave of newcomers in robotics/physical AI, the author argues there's no good pure sim2real — real workflows are always real2sim2real (or r2s2r2s2r...). Reality must inform simulation: you cannot randomize everything; use classical sysid, learned visuals and learned dynamics, and iterate around deployment with the tightest possible loop. Links a Nomagic blog on multiplying deployment data via simulation as an explicit example of this pattern.
More from Embodied
- Dream-1 robot arms grab limes zero-shot from a single prompt in restaurant kitchen demo — ___Mufasaa · 2026-10-28
- Metatron: a System 1 controller that lets coding agents command humanoid robots — ChongZzZhang · 2026-10-28
- DeFM: ETH team builds a DINO-style foundation model for depth images in robotics — ChongZzZhang · 2026-10-28
- Robot fighting teams already run sim2real2sim training pipelines, confirms practitioner cixliv — cixliv · 2026-10-28
- Nomagic details using synthetic sim data to train rare-failure robot anomaly detection — m_wulfmeier · 2026-10-28
- Foldable iPhone retail box surfaces in photo as developer posts "We're doing it" — Dimillian · 2026-10-28