arXiv 综述：基础模型时代的灵巧机器手硬件、数据、跨本体迁移、学习与评估全栈梳理
Dexterous Robotic Hands in the Foundation-Model Era: A Full-Stack Survey of Hardware, Data, Cross-Embodiment Transfer, Learning, and Evaluation
AI 导读
作者 Ji Pei 在 arXiv 发布灵巧机器手综述（arXiv:2611.06724，45 页、8 图、21 表），覆盖 2024 年 1 月至 2026 年 11 月初的文献，将研究组织为硬件、数据采集与整理、跨本体迁移、学习与基础模型、评估与应用五个相互依赖的层次。
正文 · 原文
Abstract:Dexterous robotic hands are increasingly coupled to large-scale human data and foundation models, yet progress in hardware, representation learning and evaluation is often assessed separately. This survey reviews work from January 2024 to early November 2026, with earlier studies included to establish technical lineages. We organize the literature into five interdependent layers: hardware; data collection and curation; cross-embodiment transfer; learning and foundation models; and evaluation and applications. Human hand-object understanding and tactile sensing provide two cross-cutting perspectives. A system-level architecture, comparative tables and five case analyses connect design choices across these layers. We distinguish within-study experimental comparisons from heterogeneous corpus statistics, vendor specifications and company-reported results. Three conclusions emerge. First, the value of human data depends on kinematic, visual and contact alignment, not recording volume alone. Second, shared action representations and foundation policies do not remove embodiment-specific constraints on force, latency and contact. Third, task completion is insufficient to establish physical correctness or deployment readiness. Evidence remains limited for zero-shot transfer of contact-rich skills between morphologically different hands, long-duration reliability, and cross-sensor tactile generalization. We identify eleven open problems and propose reporting interfaces and controlled comparisons that can make full-stack progress more measurable. The review is a structured narrative synthesis rather than a pooled performance ranking or an exhaustive systematic review.
| Comments: | 45 pages, 8 figures, 21 tables. Structured narrative review of hardware, data, cross-embodiment transfer, foundation models, tactile sensing, and evaluation for dexterous robotic hands |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.06724 [cs.RO] |
| (or arXiv:2611.06724v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06724 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ji Pei [view email]
[v1]
Wed, 4 Nov 2026 16:13:29 UTC (272 KB)
来源：arXiv cs.AI · arxiv.org