机器人听懂“给我做个三明治”之后，还得记住你上次的口味
现在的机器人助手能听懂“给我做个三明治”，但它不记得你上次要的是全麦还是白面包。这篇给机器人套了个“双循环”外壳：一个循环专门记你的长期偏好和当前场景，每次执行前都拿新观察去核对、修正；另一个循环盯着动作，预测到危险接触就拦下，真失败了就调用之前总结好的恢复技能。结果：一个已经做过安全微调的模型，违规率从52.6%降到6.1%，恢复成功率从13%提到80%。它不是你明天能买到的产品，但“机器人得记住你这个人，而不只是听懂这句话”这个方向，是家用机器人真正能落地的前提。
📄 原文摘要(英文)
While generalist vision-language-action (VLA) models have enabled diverse open-world manipulation, real-world robotic assistance requires two critical capabilities they currently lack: personalization and reliable execution. First, executing an instruction like "make me a sandwich" requires grounding subtask decomposition in persistent user preferences rather than relying on a single generic solution. Second, reliable deployment demands explainable safety assurance that proactively prevents hazards and gracefully recovers from occasional physical failures. To address these gaps, we present CarryOn, a dual-loop harness designed to augment a frozen VLA policy. The planning loop maintains persistent user-level and scene-level context that is continually grounded against new observations and revised through interaction, enabling personalized task selection and execution grounding across conversations and changing scenes. The execution loop actively supervises policy rollouts, shielding actions from predicted hazardous contact. When execution fails, the system invokes reusable control-based recovery skills that restore task progress and are refined through reflection on earlier failures. On a real robot and in simulation, CarryOn dispatches preference-consistent subtasks across users and scenes, reduces the violation rate of an already safety-finetuned VLA from 52.6% to 6.1%, and increases recovery success from 13% to 80% when refined skills are reused.