外观
论文arXiv 2310.175962023-10-26
MimicGen：200条人类演示生成5万机器人训练数据
本文由 AI 根据公开内容整理，可能有误，请以原文为准：MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations（arXiv 2310.17596）
核心内容
针对机器人模仿学习中人类演示数据采集成本高、周期长的瓶颈，研究团队推出MimicGen数据生成系统。该系统核心能力是将少量人类示范自动适配至新场景，仅凭约200条原始演示即合成了超过5万条高质量训练数据，覆盖18种不同任务配置、物体实例及机械臂类型，为规模化机器人学习提供了低成本数据引擎。
技术验证表明，基于MimicGen合成数据训练的Agent在多部件组装、咖啡制作等长时序高精度任务中表现优异，且对初始状态分布具有强鲁棒性。对比实验显示，合成数据的训练效能与额外采集真实人类演示相当甚至更优，证明其可作为真实数据的有效替代。相关数据集、仿真环境及演示视频已在mimicgen.github.io开源。
关键看点
- 数据扩增比：仅用约200条人类演示自动生成超5万条训练数据，覆盖18类任务与多种机械臂构型
- 任务验证：在多部件组装与咖啡制备等长时序高精度任务中，合成数据训练Agent性能达实用水平
- 效能对标：合成数据训练效果优于或持平于额外采集真实人类演示，验证了数据生成的经济性
- 开源资产：完整数据集、仿真环境及可视化视频已通过mimicgen.github.io向社区开放
工程与产业观察
MimicGen验证了“小样本演示+自动化生成”范式在具身智能数据工程中的可行性，将数据采集成本降低两个数量级。对于缺乏大规模真机数据的团队，该方案提供了从仿真到策略训练的低成本闭环路径，是解决长尾操作任务数据稀缺的关键基础设施。
英文摘要 (Abstract)
Imitation learning from a large set of human demonstrations has proved to be an effective paradigm for building capable robot agents. However, the demonstrations can be extremely costly and time-consuming to collect. We introduce MimicGen, a system for automatically synthesizing large-scale, rich datasets from only a small number of human demonstrations by adapting them to new contexts. We use MimicGen to generate over 50K demonstrations across 18 tasks with diverse scene configurations, object instances, and robot arms from just ~200 human demonstrations. We show that robot agents can be effectively trained on this generated dataset by imitation learning to achieve strong performance in long-horizon and high-precision tasks, such as multi-part assembly and coffee preparation, across broad initial state distributions. We further demonstrate that the effectiveness and utility of MimicGen data compare favorably to collecting additional human demonstrations, making it a powerful and economical approach towards scaling up robot learning. Datasets, simulation environments, videos, and more at https://mimicgen.github.io .
作者：Ajay Mandlekar, Soroush Nasiriany, Bowen Wen, Iretiayo Akinola, Yashraj Narang, Linxi Fan, Yuke Zhu, Dieter Fox
来源
本页事实对应的公开页面，以原文为准。