从离线人体演示直接生成精准机器人动作，无需人工遥控数据
WARP: Whole-Body Retargeting for Learning from Offline Human Demonstrations
- 用几何解法精确追踪末端执行器位置，保持全身结构意图
- 生成一致可靠的机器人轨迹，支持开环真实世界重播
- 首个零样本实现全身移动操作的离线演示转译框架
将人体示范直接转化为可学习的机器人动作，是实现可扩展全身移动操作的关键。尽管人体数据比远程操控更易获取，但仍需克服显著的本体差异。现有重定向方法导致动作不精确或不一致，引发动作多模态，阻碍监督策略收敛。我们提出全身感知的离线重定向框架WARP，显式建模本体差异，提取精确且唯一的全身动作。WARP采用闭式肩-肘-腕（SEW）几何求解器，实现末端执行器的精确跟踪，同时保留全身结构意图。结合懒惰式移动基座控制，生成准确一致的机器人轨迹。评估表明，WARP能提供高度可靠的数据用于开环真实世界重播。据我们所知，WARP是首个直接从离线人体示范实现零样本全身移动操作的框架，无需人工在环的遥操作动作数据。
原文摘要 · Abstract (English)
Direct transfer from human demonstration to learnable robot action is a crucial step towards scalable whole-body mobile manipulation. While human data scales better than mobile teleoperation, it requires overcoming significant embodiment gaps. Existing retargeting methods yield imprecise or inconsistent solutions, causing action multi-modality that prevents supervised policies from reliably converging. We present Whole-body-Aware Retargeting from human Pose (WARP), an offline pipeline that explicitly models embodiment differences to extract precise, unique whole-body actions. WARP leverages a closed-form Shoulder-Elbow-Wrist (SEW) geometric solver for exact end-effector tracking while preserving whole-body structural intent. Paired with lazy mobile-base control, it extracts accurate, consistent robot trajectories. Evaluations show WARP provides highly reliable data for open-loop real-world replay. To our knowledge, WARP is the first framework to achieve zero-shot whole-body mobile manipulation directly from offline human demonstrations, eliminating the need for human-in-the-loop teleoperation action data. More details on https://warp-retargeting.github.io/
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。