外观
论文arXiv 2406.025232024-06-04
RoboCasa仿真框架发布：千级资产百项任务验证合成数据Scaling Law
本文由 AI 根据公开内容整理，可能有误，请以原文为准：RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots（arXiv 2406.02523）
核心内容
针对机器人学习缺乏大规模数据集的痛点，研究团队推出RoboCasa大规模仿真框架，旨在通过逼真物理模拟扩展环境、任务与数据规模。该框架聚焦厨房场景，提供涵盖150+对象类别的数千个3D资产及数十种可交互家具家电，并设计了100项系统化评估任务（含LLM生成的复合任务）。项目代码与视频已开源，为具身智能算法验证提供了标准化基准。
技术层面，RoboCasa利用Text-to-3D与Text-to-Image生成式AI工具增强资产与纹理的真实感及多样性。为解决数据获取难题，框架内置高质量人类演示数据，并集成自动化轨迹生成方法以低成本扩充数据集。实验表明，使用合成数据进行大规模模仿学习存在清晰的Scaling趋势，且仿真数据在真实世界任务中展现出良好的迁移潜力，验证了“仿真即数据”的技术路线可行性。
关键看点
- 资产规模：内置数千个3D资产覆盖150+对象类别，包含数十种可交互厨房家具与电器，支持高保真物理仿真。
- 任务体系：设计100项系统化评估任务，利用大语言模型指导生成复合任务，覆盖日常操作全链路。
- 数据生成：集成自动化轨迹生成方法与高质量人类演示，结合Text-to-3D/2D生成式AI大幅降低数据构建成本。
- Scaling验证：实验证实合成数据在模仿学习中呈现明确Scaling趋势，并成功验证Sim-to-Real迁移效果。
工程与产业观察
RoboCasa为具身智能提供了标准化的Kitchen Domain仿真基准，其核心价值在于验证了合成数据在模仿学习中的Scaling Law。对于算法工程师，该框架降低了高质量操作数据的获取门槛；对于产业界，它证明了利用生成式AI构建仿真资产与自动化标注管线的工程可行性，是推进通用机器人Sim-to-Real落地的关键基础设施。
英文摘要 (Abstract)
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/
作者：Soroush Nasiriany, Abhiram Maddukuri, Lance Zhang, Adeet Parikh, Aaron Lo, Abhishek Joshi, Ajay Mandlekar, Yuke Zhu
来源
本页事实对应的公开页面，以原文为准。