GOTT：基于可复用跨形态原语的对象中心灵巧操作
GOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive
浏览论文内容
中文总结 AI 辅助
GOTT提出跨形态接触获取原语，结合到达-获取-移动框架，将对象轨迹转化为灵巧手操作，在多样对象和手形态上实现稳健接触并提升任务成功率。
中文摘要 AI 辅助
基础模型和大规模人类数据提供了丰富的操作意图来源，但将这些意图转化为多指机器人行为仍然困难。灵巧手仍然缺乏一种可复用的低级原语，能够在不同任务和形态间可靠地建立接触。我们提出GOTT，一个围绕单一跨形态接触获取原语构建的“到达-获取-移动”框架。给定一个与机器人无关的对象轨迹和到达规范，GOTT首先将手移动到与任务相关的接触区域附近。然后，共享的闭环原语从该近似初始化建立稳定接触，姿态条件控制器跟踪期望的对象运动。到达规范可来自未来感知规划、外部模型或人类演示，而原语和跟踪后端保持不变。仿真和真实世界实验表明，GOTT能够在多样对象、臂手平台以及已见和未见手形态上建立稳健接触。它还能持续提升端到端任务成功率，优于开环抓取执行。
英文摘要
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.
发表机构
- Amazon FAR（亚马逊FAR）
- UC San Diego（加州大学圣迭戈分校）
- University of Chicago（芝加哥大学）
- UC Berkeley（加州大学伯克利分校）
机构由 AI 辅助整理，请以论文原文为准。
