Two-Level Architecture: Planning-Control

A robot needs solutions at two timescales:

Long-term planning (0.1–1 Hz) — “clean the kitchen” → sequence of subgoals: semantics, dependencies, multi-step plan;
VLA control (1–10 Hz) — specific operation: smooth control signals.

The separation simplifies complexity: planning answers “what to do”, control answers “how to do it”.

This is structurally similar to fast/slow thinking in speech, but the cut is different: “plan holistically” vs. “execute in real time”. The real-time requirement doesn’t disappear, it’s shifted to the control level and softened by breaking actions into blocks — trading reactivity for smoothness.