Beyond motion tracking: why robots still need closed-loop S0 controllers
animesh_garg · x · 2026-11-22
Animesh Garg shares Haoyang Weng's research note arguing that LLMs/VLMs like Astra can serve as upper-level policies (S1) generating interaction intent, but cannot directly control robots. Spatial grounding isn't dynamics grounding: producing commands at 50 Hz doesn't teach a policy to adjust as contact, loads, and disturbances change. True dynamics grounding requires closed-loop interaction experience — acting, sensing effects, adapting — which supervised learning struggles to provide. Robots still need dynamics-grounded S0 low-level controllers with expressive interfaces that let S1 steer physical interaction precisely.
More from Embodied
- One chef, multiple auto stir-fry machines: automated wok kitchen goes viral — churchkey · 2026-11-22
- Simple robot demo test: move the table mid-task and ask it to pick up the apple again — VraserX · 2026-11-22
- Japanese studio sells a quadruped robot-style phone stand for ¥20,900 — Promptmethus · 2026-11-22
- Wall-painting robot targets high-rises up to 100 meters, taking on the deadliest exterior work — TansuYegen · 2026-11-22
- Robot Foot Designed With Fable Weighs Just 117g: Carbon Plate Plus 7075 Aluminum — dee_hw · 2026-11-22
- Musk says compute is going to Optimus; cars will remain at AI4 — CyberRobooo · 2026-11-22