外观
论文arXiv 2610.0386126 天前
GOTT：基于可复用跨具身原语的以物体为中心的灵巧操作
原文链接：GOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive（arXiv 2610.03861 · 发布日期：2026-10-02）
GOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive
针对多指机器人难以复用地建立接触的问题，GOTT以跨具身接触获取原语构建reach-acquire-move框架，并在仿真和真实实验中验证。
核心要点
- 问题在于基础模型和大规模人类数据的操作意图，仍难转化为多指机器人行为。
- GOTT围绕单一跨具身接触获取原语，依次接近接触区域、建立稳定接触并跟踪物体运动。
- 到达规格可来自前瞻规划、外部模型或人类示范，而原语和跟踪后端保持不变。
- 仿真和真实实验显示其可跨多样物体、臂手平台及已见和未见手形态建立鲁棒接触，并优于开环抓取执行。
验证范围与局限：验证范围为仿真和真实实验，覆盖多样物体、臂手平台以及已见和未见手部形态。
英文摘要 (Abstract)
Foundation models and large-scale human data provide rich sources of manipulation intent, but translating this intent into multi-fingered robot behavior remains difficult. Dexterous hands still lack a reusable low-level primitive that reliably establishes contact across tasks and embodiments. We propose GOTT, a reach-acquire-move framework built around a single cross-embodiment contact-acquisition primitive. Given a robot-agnostic object trajectory and a reach specification, GOTT first brings the hand near a task-relevant contact region. The shared closed-loop primitive then establishes stable contact from this approximate initialization, and a pose-conditioned controller tracks the desired object motion. Reach specifications may come from future-aware planning, external models, or human demonstrations, while the primitive and tracking backend remain unchanged. Simulation and real-world experiments show that GOTT is able to establish robust contact across diverse objects, arm-hand platforms, and seen and unseen hand morphologies. It also consistently improves end-to-end task success over open-loop grasp execution.
作者：Yulin Liu, Lai Wei, Yen‐Jen Wang, Akash Sharma, Pieter Abbeel, Henrik I. Christensen, Haozhi Qi
来源
本页事实对应的公开页面，以原文为准。