RealAppliance：让高保真家电资产可控可用，并与真实手册对齐
RealAppiance: Let High-fidelity Appliance Assets Controllable and Workable as Aligned Real Manauls
提供了100个高保真家电资产及配套基准，可用于评测多模态大语言模型在手册检索、部件定位和开/闭环操作规划上的能力，为具身操作研究提供标准化测试平台。
原文依据 we introduce the RealAppliance dataset, comprising 100 high-fidelity appliances with complete physical, electronic mechanisms, and program logic aligned with their manuals.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有家电资产存在渲染质量差、机制不完整以及与手册不对齐的问题，导致仿真与现实之间的差距，阻碍了家电操作的发展。在本工作中，我们引入了RealAppliance数据集，包含100个高保真家电，具有完整的物理、电子机制以及与手册对齐的程序逻辑。基于这些资产，我们提出了RealAppliance-Bench基准，评估多模态大语言模型和具身操作规划模型在家电操作规划关键任务上的表现：手册页面检索、家电部件定位、开环操作规划和闭环规划调整。我们对模型在RealAppliance-Bench上表现的分析为推进家电操作研究提供了见解。
英文原文摘要 831 字符
Existing appliance assets suffer from poor rendering, incomplete mechanisms, and misalignment with manuals, leading to simulation-reality gaps that hinder appliance manipulation development. In this work, we introduce the RealAppliance dataset, comprising 100 high-fidelity appliances with complete physical, electronic mechanisms, and program logic aligned with their manuals. Based on these assets, we propose the RealAppliance-Bench benchmark, which evaluates multimodal large language models and embodied manipulation planning models across key tasks in appliance manipulation planning: manual page retrieval, appliance part grounding, open-loop manipulation planning, and closed-loop planning adjustment. Our analysis of model performances on RealAppliance-Bench provides insights for advancing appliance manipulation research