# HomeLoop仿真框架发布：评测VLM家庭IoT协同，最优得分仅61.9%

> 原文链接：https://robotics.hellobike.com/papers/2026-11-09-2611-08914-31dea6e9
> 频道：papers | 更新日期：2026-11-09 | 标签：auto, arxiv
> 核心摘要：基于Isaac Sim构建的HomeLoop框架开源2100种家庭布局与5类机器人本体，基准测试显示最优VLM在IoT协同任务中得分仅61.9%，且过度干预失败率是漏报率的2倍以上，揭示了具身智能在复杂家庭场景下的安全决策短板。

# HomeLoop仿真框架发布：评测VLM家庭IoT协同，最优得分仅61.9%

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[HomeLoop: A Simulation Framework and Benchmark for Robot-IoT Coordination in Everyday Domestic Assistance and Safety](https://arxiv.org/abs/2611.08914)（arXiv 2611.08914）

## 核心内容

针对家庭服务机器人与现有IoT设备协同难题，研究团队推出基于Isaac Sim的HomeLoop仿真框架与基准测试。该系统集成机器人、网络设备、穿戴设备及动态演化的家庭隐患，包含5大类20项任务。评测6款主流VLM发现，最优模型家庭平衡得分仅为61.9%，暴露出当前大模型在处理模糊家庭警报时普遍存在推理不足与决策缺陷。

技术架构上，HomeLoop内置时序逻辑运行时监视器，对动作序列与最终结果进行双重评分并预设成本函数。数据集涵盖2100种可自动配置的家庭布局、5种机器人本体及20类联网设备，支持故障传感器模拟。实验数据显示，模型因未查明原因即切断电源等“过度反应”导致的失败案例，数量超过“漏报必要干预”案例的两倍，为隐私安全权衡与长期记忆研究提供量化底座。

## 关键看点

- **仿真资产规模**：开源2100种自动布局家庭场景、5种机器人本体及20类IoT设备，支持动态隐患演化与故障传感器模拟
- **VLM性能瓶颈**：6款开闭源VLM评测中最高分仅61.9%，过度干预失败数是漏报数的2倍以上，常误关灶具而未查警报源
- **评估机制创新**：采用时序逻辑运行时监视器，结合预定义动作成本函数，对任务执行过程与最终结果进行双重量化打分
- **研究定位明确**：专为机器人-IoT协同、长期记忆、主动辅助及隐私安全权衡设计，解决多义性家庭警报响应难题

## 工程与产业观察

该基准揭示了VLM在真实家庭IoT环境中的“过敏”倾向，表明单纯提升语义理解不足以保障具身安全。工程侧需强化时序因果推理与多模态状态确认机制，避免端到端模型在模糊场景下产生高风险误操作。其提供的2100种布局与标准化评测协议，为验证具身智能长尾安全性确立了新坐标。

## 英文摘要 (Abstract)

Recent progress in embodied robotics is bringing robots closer to deployment in homes, as vision-language models (VLMs) are demonstrating significant advances in reasoning, making VLM-driven robots promising home assistant agents. These agents will often be introduced into homes that already have cameras, Internet of Things (IoT) devices, and residents with wearables. To fulfill their potential, they need to integrate with existing smart infrastructure and reason through ambiguous scenarios: a smoke alarm may come from a pan about to ignite, a pan already on fire, a resident cooking or a faulty sensor, and each calls for a different response. To that end, we introduce HomeLoop, a simulation framework and benchmark built on Isaac Sim that combines robot bodies, networked devices and wearables, simulated residents and visitors, faulty sensors, and hazards that evolve over time. Our benchmark is composed of 20 tasks across five families grounded in real-world household hazards and needs, and designed so that the same alert can have different causes. A runtime monitor scores each episode with temporal-logic checks on the final outcome and the actions along the way, and every action carries a predefined cost. We evaluate six open-weight and proprietary VLMs. The best achieves a family-balanced score of 61.9%, and across models we see a pattern of over-reaction: failed episodes involving prohibited interventions outnumber those involving missed required interventions by more than two to one, with models often shutting off the stove before investigating the alarm's cause. HomeLoop is an extensible foundation intended for use in research on robot-IoT coordination, long-term memory, proactive assistance, and privacy-safety trade-offs. HomeLoop will be released with 2,100 home layouts that can be automatically furnished in diverse configurations, five robot bodies and 20 networked device types.

作者：Ramy ElMallah, Marc Bishara, Hyegang Kim, Yuxi Zhang, Chongyu Zhu, Chi-Guhn Lee
:::

## 原始参考来源 (Sources)

- [arXiv 2611.08914：HomeLoop: A Simulation Framework and Benchmark for Robot-IoT Coordination in Everyday Domestic Assistance and Safety](https://arxiv.org/abs/2611.08914)