外观
论文arXiv 2609.3718129 天前
EgoHumanoid-V2：用于移动操作的协调全身技能从人到人形机器人的迁移
原文链接：EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation（arXiv 2609.37181 · 发布日期：2026-09-29）
EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation
EgoHumanoid-V2通过粗到细动作对齐与视觉适配，将人类全身移动操作技能迁移到人形机器人，并在四个真实任务上验证。
核心要点
- 以往第一视角迁移多关注解耦控制下的场景泛化，协调全身技能直接迁移探索不足。
- 采用运动学参考校正结合动力学感知细化的粗到细动作对齐，兼顾末端精度与全身协调。
- 通过机器人手臂渲染和训练时图像增强，缩小视觉具身差距并提升视角鲁棒性。
- 四个真实任务中，VLA策略无需目标任务机器人示教即可零样本迁移，得分接近遥操作数据训练策略。
验证范围与局限：验证范围为四个真实世界任务，使用对齐人类数据训练VLA策略，未使用目标任务机器人示教。
英文摘要 (Abstract)
Human demonstrations capture diverse scenes and rich whole-body skills without requiring robot teleoperation. Prior work on egocentric transfer has emphasized scene generalization in loco-manipulation under decoupled control, leaving direct transfer of coordinated whole-body skills less explored. We present EgoHumanoid-V2, the first egocentric human-to-humanoid skill transfer framework for coordinated whole-body loco-manipulation. At its core, coarse-to-fine action alignment combines kinematic reference correction with dynamics-aware refinement. It improves end-effector pose accuracy while preserving whole-body coordination. We also use robot-arm rendering and training-time image augmentation to reduce the visual embodiment gap and improve viewpoint robustness. On four real-world tasks, vision-language-action (VLA) policies trained on aligned human data show zero-shot skill transfer without target-task robot demonstrations. Task scores are comparable to those of policies trained on teleoperation data at a lower collection cost. These results support human data as direct skill supervision.
作者：Jin Chen, Yiming Jiang, Chongyang Xu, Modi Shi, Shijia Peng, Li Chen, Tianyu Li, Mu Xu, Yilun Chen, Steven Hoi
来源
本页事实对应的公开页面，以原文为准。