外观
论文arXiv 2610.2145313 天前
CarryOn：用于个性化且可靠机器人辅助的双循环框架
原文链接：CarryOn: A Dual-Loop Harness for Personalized and Reliable Robot Assistance（arXiv 2610.21453 · 发布日期：2026-10-15）
CarryOn: A Dual-Loop Harness for Personalized and Reliable Robot Assistance
CarryOn通过双循环增强冻结VLA策略，面向个性化可靠机器人辅助，并在真机与仿真中验证。
核心要点
- 通用VLA模型缺少对持久用户偏好的落地与可靠执行能力，难以直接用于真实辅助。
- 规划循环维护用户级和场景级上下文，并随新观察和交互持续校正。
- 执行循环监督策略执行过程，屏蔽预测危险接触，失败后调用可复用恢复技能。
- 实验中违规率由52.6%降至6.1%，复用精炼技能使恢复成功率由13%升至80%。
验证范围与局限：验证范围为一台真实机器人和仿真，涉及跨用户与场景的偏好一致子任务调度及执行监督。
英文摘要 (Abstract)
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.
作者：Zixuan Wang, Yuqi Liu, Yuxin Chen, Sengqiao Yang, Jinhui Ye, Pengguang Chen, Changsheng Lu, Shu Liu, Bei Yu, Jiaya Jia
来源
本页事实对应的公开页面，以原文为准。