用扩散模型实现高灵巧机械手的高效真实世界操作。
mimic-one: a Scalable Model Recipe for General Purpose Robot Dexterity
- 基于扩散模型，从原始感官输入端到端训练控制策略。
- 在复杂操作中实现93.3%的跨域成功率，自修正能力提升33.3%。
- 适合研究灵巧操作与真实机器人部署的团队参考。
我们提出一种基于扩散模型的通用机器人灵巧操作方案，用于高度灵巧的人形机械手在真实环境中的控制，旨在实现样本高效的在线学习与平滑的精细动作推理。系统采用全新设计的16自由度肌腱驱动手部结构，配备广角腕部摄像头，并安装于Franka Emika Panda机械臂上。我们开发了融合手套与虚拟现实接口的多功能遥操作流程与数据采集协议，覆盖抓取、分类与装配插入等多种任务，实现高质量数据收集。通过高频生成式控制，模型从原始感官输入端到端训练，可在复杂操作中实现平滑且具备自我修正能力的动作。真实世界评估显示，系统在分布外任务中达到最高93.3%的成功率，得益于涌现的自修正行为，性能提升达+33.3%，同时揭示了策略性能的可扩展规律。该成果通过软硬件一体化、实用化的集成方法，推动了灵巧机器人操作的最新进展。
原文摘要 · Abstract (English)
We present a diffusion-based model recipe for real-world control of a highly dexterous humanoid robotic hand, designed for sample-efficient learning and smooth fine-motor action inference. Our system features a newly designed 16-DoF tendon-driven hand, equipped with wide angle wrist cameras and mounted on a Franka Emika Panda arm. We develop a versatile teleoperation pipeline and data collection protocol using both glove-based and VR interfaces, enabling high-quality data collection across diverse tasks such as pick and place, item sorting and assembly insertion. Leveraging high-frequency generative control, we train end-to-end policies from raw sensory inputs, enabling smooth, self-correcting motions in complex manipulation scenarios. Real-world evaluations demonstrate up to 93.3% out of distribution success rates, with up to a +33.3% performance boost due to emergent self-correcting behaviors, while also revealing scaling trends in policy performance. Our results advance the state-of-the-art in dexterous robotic manipulation through a fully integrated, practical approach to hardware, learning, and real-world deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。