Robot tablecloth demo works via staged repair loop: rule-based checks plus learned policies
arankomatsuzaki · x · 2026-10-14
Komatsu-zaki explains why a robot tablecloth-clearing demo is so reliable: every task is split into stages with explicit success checks.
Pushing and positioning are rule-based functions (e.g. cloth extends >5cm past the table edge), while grasping and folding are learned policies. A failed grasp check sends the robot back to re-position and retry — a simple repair loop that makes the whole pipeline robust.
Related event: Robot tablecloth demo combines rules with world model(2 posts)→
More from Embodied
- Visor: open-source Android app replaces the Meta AI app on Ray-Ban Meta glasses with your own model — jedisct1 · 2026-10-14
- 304 robotics papers hit arXiv in a single day as the field explodes — DJiafei · 2026-10-14
- NTU's COAP: code replaces LLMs in the robot control loop, hitting 75% on 42 bimanual tasks — liuziwei7 · 2026-10-14
- WAVE-0 adds a 257M world model to VLA, lifting real-world success from 38.3% to 73.3% — Haomin Wang · 2026-10-14
- 99%+ data gap: Sophia Capital partner on embodied-AI investing — 创业邦 · 2026-10-14
- AI glasses ship with zero third-party apps; phone projection is the only workaround — alexisgallagher · 2026-10-14