发表机构
North Carolina State University; Google; Purdue University（北卡罗来纳州立大学; 谷歌; 普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MRPilot通过混合现实系统，在四个阶段（形成、审查、跟随、修复）监督和干预LLM驱动的多机器人团队，显著降低用户工作负载并提升情境意识、信任和控制感。
AI 中文摘要
大型语言模型（LLM）使用户能够通过自然语言指挥异构多机器人系统（MRS），但使得任务解释、机器人分配和协调难以检查和更改。基于对12名非专家用户的形成性研究，我们开发了MRPilot，这是一个围绕监督和干预四个阶段组织的混合现实系统。MRPilot将机器人团队计划和执行状态表示为结构化承诺，这些承诺在同步的情境视图和概览视图中共享。在四个阶段中，它帮助用户解决模糊引用（形成阶段）、在执行前审查计划（审查阶段）、监控分布式执行（跟随阶段），并在出现问题时进行机器人级或团队级更改（修复阶段）。在一项包含20名参与者在虚拟现实模拟家庭中的受试者内研究中，与使用相同LLM规划器和机器人能力的传统基于LLM的对话界面相比，MRPilot减少了工作负载，增加了情境意识、透明度、信任和感知控制。我们为基于LLM的MRS中的多尺度干预、自适应监督和校准依赖提供了设计启示。
英文摘要
Large language models (LLMs) let users direct heterogeneous multi-robot systems (MRS) through natural language, but make task interpretation, robot assignment, and coordination difficult to inspect and change. Based on a formative study with 12 non-expert users, we developed MRPilot, a mixed reality system organized around four stages of supervision and intervention. MRPilot represents robot-team plans and execution states as structured commitments shared across synchronized situated and overview views. Across four stages, it helps users resolve ambiguous references (Forming), review plans before execution (Reviewing), monitor distributed execution (Following), and make robot-level or team-level changes when problems arise (Repairing). In a within-subjects study with 20 participants in a virtual reality-simulated home, MRPilot reduced workload, increased situational awareness, transparency, trust, and perceived control compared with a conventional LLM-based conversational interface using the same LLM planner and robot capabilities. We provide design implications for multi-scale intervention, adaptive supervision, and calibrated reliance in LLM-based MRS.
Comments15 pages, 8 figures
