RoboCasa：針對通用機器人的日常任務大規模模擬

摘要

人工智慧（AI）領域近期的進展主要是由規模化推動的。在機器人領域，規模化受限於無法取得龐大的機器人數據集。我們主張使用逼真的物理模擬作為擴展環境、任務和機器人學習方法的手段。我們提出了RoboCasa，這是一個用於在日常環境中訓練通用型機器人的大規模模擬框架。RoboCasa具有逼真且多樣化的場景，重點放在廚房環境上。我們提供了超過150個物件類別的數千個3D資產，以及數十個可互動的家具和家電。我們利用生成式AI工具豐富了模擬的逼真度和多樣性，例如從文本生成3D模型的物件資產，以及從文本生成圖像的環境紋理。我們設計了一套包括由大型語言模型引導生成的複合任務在內的100個任務，以進行系統性評估。為了促進學習，我們提供高質量的人類示範，並整合自動生成軌跡的方法，以極大地擴展我們的數據集，減輕人力負擔。我們的實驗表明，使用合成生成的機器人數據進行大規模模仿學習呈現明顯的規模化趨勢，並展示了在實際任務中利用模擬數據的巨大潛力。視頻和開源代碼可在https://robocasa.ai/ 上找到。

English

Recent advancements in Artificial Intelligence (AI) have largely been propelled by scaling. In Robotics, scaling is hindered by the lack of access to massive robot datasets. We advocate using realistic physical simulation as a means to scale environments, tasks, and datasets for robot learning methods. We present RoboCasa, a large-scale simulation framework for training generalist robots in everyday environments. RoboCasa features realistic and diverse scenes focusing on kitchen environments. We provide thousands of 3D assets across over 150 object categories and dozens of interactable furniture and appliances. We enrich the realism and diversity of our simulation with generative AI tools, such as object assets from text-to-3D models and environment textures from text-to-image models. We design a set of 100 tasks for systematic evaluation, including composite tasks generated by the guidance of large language models. To facilitate learning, we provide high-quality human demonstrations and integrate automated trajectory generation methods to substantially enlarge our datasets with minimal human burden. Our experiments show a clear scaling trend in using synthetically generated robot data for large-scale imitation learning and show great promise in harnessing simulation data in real-world tasks. Videos and open-source code are available at https://robocasa.ai/

RoboCasa：針對通用機器人的日常任務大規模模擬

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

摘要

Support