{
  "title": "Short-prefix execution and replanning",
  "caption": "The author recommends execution of only a trusted short rollout prefix, with new observations and replanning as model uncertainty or drift becomes important. The branching fan illustrates prediction ambiguity. It is not a calibrated confidence interval or a certified safe/unsafe classifier. Author-created explanatory diagram. Playback time is illustrative and is not measured runtime.",
  "alt": "Replanning flow: a robot executes a short trusted prefix, gets observations and changes the plan, with branches for uncertainty.",
  "sources": [
    {
      "path": "content/blog/2026-06-09_world-models-for-embodied-ai/post.md",
      "description": "Article mechanism and retained citations"
    },
    "https://web.stanford.edu/class/ee364b/lectures/mpc_slides.pdf",
    "https://arxiv.org/abs/2603.25685"
  ],
  "limitations": [
    "This playback is an example. Playback duration is not measured runtime.",
    "The forecast fan is a conceptual uncertainty diagram. It gives no probability scale or safety certification.",
    "The model imagines the same short-prefix path before the robot executes it. Animation duration does not encode the physical horizon."
  ]
}