机器人学AI，数据金字塔比模型更重要
大模型靠全网文本和图像学会说话和看东西，但机器人不行——它需要“看到+动手”的配对数据，这种数据稀缺且昂贵。研究者把机器人数据来源整理成一座“金字塔”，从最易获取但离机器人最远的通用图文数据，到最精准但最贵的真实机器人数据，共五层。他们发现，当前最强的机器人模型在训练时，往往混合了多种数据源，但每种数据都有取舍：仿真数据量大但物理真实感差，人类演示数据丰富但动作格式不统一。文章最后列出六个待解难题，比如缺少触觉数据、缺少失败案例数据等。这不是你明天能用上的技术，但它揭示了机器人AI发展的核心瓶颈——不是算法，而是数据。
📄 原文摘要(英文)
Multimodal foundation models learned to see and to speak by consuming the whole internet. Embodied agents admit no such shortcut, since they require data that couple observations with physical states and actions. These signals can be provided, to varying degrees, by multiple data sources. In this work, we organize the embodied data ecosystem as a "pyramid" spanning five complementary sources: real-robot data, UMI-style data, egocentric and exocentric data, simulation data, and general vision-language data. We organize the pyramid around the tension between scalability and robot alignment, and further characterize each source in terms of data quality, diversity, reusability, and physical fidelity. We then analyze recent embodied foundation models through the lens of their data recipes, examining how different sources are selected, aligned, and mixed during pretraining. For embodied brain models, vision-language-action models, and world-action models alike, we relate data composition to capabilities in perception, reasoning, planning, action generation, and world prediction. We close by discussing six open challenges: building large-scale tactile datasets, collecting failure and recovery data, developing scalable data-collection pipelines, aligning actions across embodiments, leveraging egocentric data for dexterous manipulation, and designing principled data recipes for robot learning. We hope this work paves the foundation for the design of next-generation embodied systems.