arXiv：cs.AI· Yulin Liu, Lai Wei, Yen-Jen Wang, Akash Sharma, Pieter Abbeel, Henrik I. Christensen, Haozhi Qi·· 13 小时前
GOTT：用可复用的跨形态接触获取原语实现以物体为中心的多指灵巧操作
GOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive
AI 导读
GOTT 是一个围绕单一跨形态接触获取原语构建的 reach-acquire-move 框架，可将与机器人无关的物体轨迹和 reach 规格转化为多指手操作行为。该闭环原语能从近似初始化建立稳定接触，再由姿态条件控制器跟踪目标物体运动，且原语与跟踪后端保持不变。仿真和真机实验显示，GOTT 能在多样物体、臂手平台及已见与未见手部形态上建立稳健接触，并持续提升端到端任务成功率。
正文
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.
| Comments: | Project page: this https URL |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.03861 [cs.RO] |
| (or arXiv:2610.03861v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03861 arXiv-issued DOI via DataCite |
Submission history
From: Yulin Liu [view email]
[v1]
Fri, 2 Oct 2026 17:58:42 UTC (8,136 KB)
[v2]
Thu, 8 Oct 2026 23:54:24 UTC (8,136 KB)
来源：arXiv：cs.AI · arxiv.org