الملخص
Collecting whole-body demonstrations for humanoid manipulation mostly relies on teleoperation, which is costly and hard to scale up. The Universal Manipulation Interface (UMI) provides a scalable data collection paradigm, but end-effector trajectories alone underdetermine humanoid whole-body coordination, which is insufficient for whole-body demonstration collection. Therefore, we introduce Whole-Body UMI (WB-UMI), a task-agnostic, real-time and end-effector conditioned motion generator that decouples whole-body coordination learning from task semantics learning through a shared end-effector interface. A diffusion policy learns from native UMI demonstrations, while WB-UMI learns independently from retargeted motion capture, requiring no body trackers or paired image--whole-body demonstrations during task-specific data collection. In real deployment, an asynchronous hierarchy integrates the diffusion policy, motion generator, and a whole-body controller with latency compensation and measured-state feedback. Real-robot experiments on G1 support real-time closed-loop transfer across four tasks, achieving 90% success in drawer closing, 80% in shelf pick-and-place, 30% in ball toss, and 40% in Loco-PnP, which shows the effectiveness of this hierarchy in transferring native UMI skills to humanoid whole-body manipulation.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Nai, Y., Chang, L., Yang, L., Yang, S., & Li, Z. (2026). Whole-Body UMI: Transferring UMI Manipulation Skills to Humanoid Whole-Body Manipulation via Real-Time Motion Generation. https://omanscience.com/ar/articles/whole-body-umi-transferring-umi-manipulation-skills-to-humanoid-whole-body-manipulation-via-real-time-motion-generation
MLA 9
Nai, Yuxuan, et al. "Whole-Body UMI: Transferring UMI Manipulation Skills to Humanoid Whole-Body Manipulation via Real-Time Motion Generation." https://omanscience.com/ar/articles/whole-body-umi-transferring-umi-manipulation-skills-to-humanoid-whole-body-manipulation-via-real-time-motion-generation.
شيكاغو (المؤلف–التاريخ)
Nai, Yuxuan, Leixin Chang, Liangjing Yang, Shuo Yang, and Zhongyu Li. 2026. "Whole-Body UMI: Transferring UMI Manipulation Skills to Humanoid Whole-Body Manipulation via Real-Time Motion Generation." https://omanscience.com/ar/articles/whole-body-umi-transferring-umi-manipulation-skills-to-humanoid-whole-body-manipulation-via-real-time-motion-generation.
هارفارد
Nai, Y., Chang, L., Yang, L., Yang, S. and Li, Z. (2026) 'Whole-Body UMI: Transferring UMI Manipulation Skills to Humanoid Whole-Body Manipulation via Real-Time Motion Generation', Available at: https://omanscience.com/ar/articles/whole-body-umi-transferring-umi-manipulation-skills-to-humanoid-whole-body-manipulation-via-real-time-motion-generation.
فانكوفر
Nai Y, Chang L, Yang L, Yang S, Li Z. Whole-Body UMI: Transferring UMI Manipulation Skills to Humanoid Whole-Body Manipulation via Real-Time Motion Generation. https://omanscience.com/ar/articles/whole-body-umi-transferring-umi-manipulation-skills-to-humanoid-whole-body-manipulation-via-real-time-motion-generation
IEEE
Y. Nai, L. Chang, L. Yang, S. Yang, and Z. Li, "Whole-Body UMI: Transferring UMI Manipulation Skills to Humanoid Whole-Body Manipulation via Real-Time Motion Generation," https://omanscience.com/ar/articles/whole-body-umi-transferring-umi-manipulation-skills-to-humanoid-whole-body-manipulation-via-real-time-motion-generation.