HiFi-UMI：仅从高保真UMI数据中学习可部署的操作策略

摘要

学习可部署的操作策略面临瓶颈，即缺乏同时具备高保真度和可扩展性的数据。真实机器人遥操作精确但扩展成本高昂；无机器人UMI数据采集易于扩展，当前实践中主要将产生的数据用于预训练，并在后训练阶段添加少量真实机器人数据作为“锚点”。我们探究：是否可以通过提升无机器人UMI数据的保真度（而非减少真实机器人数据的比例）来消除这一锚点。我们提出了HiFi-UMI，这是一个便携式UMI数据生产系统，其在轨迹精度、夹爪间相对位姿、同步性和视场方面进行了协同设计：头戴式离线双目惯性SLAM、原生而非重建的相对位姿、共享微秒级GPIO触发器，以及每只手配备两个覆盖约200度的广角摄像头。该系统无需外部追踪基础设施，即可实现3毫米级别的工作空间局部末端执行器精度。利用这一数据语料库，我们展示了零机器人后训练：仅基于HiFi-UMI演示数据进行后训练的策略可直接部署到真实机器人上，并在涵盖视觉-语言-动作和世界-动作模型家族的三个主干网络上，与领域内遥操作的性能相当；在StarVLA-QwenPI、OpenPI-pi_0.5和LingBot-VA上，成功率差异分别为-2.5、+3.1和-0.6个百分点。最强的策略在精密插入任务上达到85%的成功率，尽管遥操作基线在评估场景中采集，而HiFi-UMI轨迹从未在该场景中出现。在同一语料库上进行4000小时的预训练，将在十个未见任务上的动作误差降低41%，并在StarVLA-QwenPI上进一步提升真实机器人成功率18.1个百分点。我们开源了HiFi-UMI-2K，包含2000小时微秒级同步、超宽视场的演示数据，每条数据均通过仿真回放自动重建和验证，为机器人学习社区提供了一个大规模、高保真度的资源。

English

Learning deployable manipulation policies is bottlenecked by the scarcity of data that is both high-fidelity and scalable. Real-robot teleoperation is accurate but costly to scale; robot-free UMI capture scales readily, and current practice uses the resulting data mainly for pre-training, adding a small real-robot "anchor" at post-training. We ask whether raising the fidelity of robot-free UMI data, rather than shrinking the real-robot fraction, can remove that anchor. We present HiFi-UMI, a portable UMI data-production system co-designed for trajectory accuracy, inter-gripper relative pose, synchronization, and field of view: head-mounted offline stereo-inertial SLAM, native rather than reconstructed relative pose, a shared microsecond GPIO trigger, and two wide-angle cameras per hand covering ~200 degrees. It reaches 3 mm workspace-local end-effector accuracy without external tracking infrastructure. Using this corpus, we demonstrate zero-robot post-training: a policy post-trained solely on HiFi-UMI demonstrations deploys directly on a real robot and matches in-domain teleoperation across three backbones spanning the vision-language-action and world-action-model families, with success-rate differences of -2.5, +3.1, and -0.6 percentage points on StarVLA-QwenPI, OpenPI-pi_0.5, and LingBot-VA; the strongest policy reaches 85% on a precision insertion task, even though the teleoperation baseline is collected in the evaluation scene and no HiFi-UMI trajectory is. Pre-training on 4,000 hours from the same corpus lowers action error on ten unseen tasks by 41% and, on StarVLA-QwenPI, raises real-robot success by a further 18.1 percentage points. We open-source HiFi-UMI-2K, 2,000 hours of microsecond-synchronized, ultra-wide-FoV demonstrations, each automatically reconstructed and validated through simulation replay, as a large-scale, high-fidelity resource for the robot-learning community.