Robotics researcher: domain randomization trades away precision, classical control has better guarantees
KyleMorgenstein · x · 2026-10-02
Kyle Morgenstein pushes back in a robotics debate: practitioners destroy precision with domain randomization to be robust to poor models, and you fundamentally can't have both without an explicit estimator — at which point you're doing adaptive + robust control, which offers better guarantees.
Related event: Robotics Researchers Debate Whether RL Beats Classical Control(4 posts)→
More from Embodied
- Peking University's DexPolicy lifts dexterous manipulation success to 85% via annealed exploration — PekingUniversity · 2026-10-02
- AMD to buy Fei-Fei Li's World Labs for ~$8.2B in stock; Li becomes chief scientist — ChrisUniverse · 2026-10-02
- Qualcomm's IVD benchmark shows VLMs lag far behind humans at real-time real-world Q&A — rishit_dagli · 2026-10-02
- 'A robot without people to design and fix it is inventory, not revenue' — MatthewChang · 2026-10-02
- Galaxy General's ET1 humanoid starts at 79,000 yuan, learns dance moves by watching — 量子位 · 2026-10-02
- Robotics papers on arXiv hit 210 per day, up from 20-30 four years ago — DJiafei · 2026-10-02