[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84612-en":3,"doc-seo-84612-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},84612,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation","Tactile sensing is essential for dexterous, contact-rich robotic manipulation because it provides precise force feedback that vision cannot reliably infer. Existing tactile datasets are limited in scale and contact coverage, and tactile-enabled vision-language-action models often lack dynamics-aware post-training, capping downstream performance. The work introduces H-Tac, a large-scale tactile-action dataset built from 160 hours of egocentric human video with 300+ tasks and 135k episodes. It further proposes Transferable Tactile Pre-Training (TTP) with unified tactile/action spaces and dual tactile expert dynamics modeling, achieving stronger generalization in simulation and on real robots for fine-grained manipulation.","arXiv :2607 .0 1067v 1 [ cs .RO] 1 Jul 2026  \n∝ BeingBeyond  \nHuman-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation  \nChi Zhang 1 ,2 ,∗ Penglin Cai 1 ,2 ,∗ Ziheng Xi2 ,3 Haoqi Yuan 1 ,2  \nHao Luo 1 ,2 Wanpeng Zhang 1 ,2 Sipeng Zheng2 Chaoyi Xu 1 ,2 Zongqing Lu 1 ,2 ,†  \n1 Peking University 2 BeingBeyond 3 Tsinghua University  \n[https://beingbeyond. github. io/TTP/](https://beingbeyond. github. io/TTP/)  \nAbstract  \nAs an essential modality for dexterous and contact-rich tasks, tactile sensing provides precise force feedback that cannot be reliably inferred from vision. However, limited by hardware and data collection systems, existing datasets with tactility remain small in scale and narrow in contact coverage. Meanwhile, Vision-Language-Action (VLA) models with tactile modality are constrained on dynamics-agnostic post-training, which limits the performance ceiling on downstream tasks. In this paper, we present H-Tac, a large-scale tactile-action dataset with 160-hour egocentric human videos containing more than 300 tasks and 135k episodes. Building upon this, we propose Transferable Tactile Pre-Training (TTP), a system of tactile-based pre-training on human data for fine-grained robotic tasks. To bridge the gap between humans and robots, we use unified tactile and action spaces throughout the pre-training and post-training phases, preserving prior knowledge during human-to-robot transfer. By leveraging a tactile expert for future tactile prediction, our framework explicitly models the contact dynamics and precise physical interactions. Extensive experiments in simulation and on real robots demonstrate that our model achieves superior performance, exhibiting robust generalization and finegrained manipulation capabilities. TTP paves the way for scalable tactile pre-training via human-to-robot transfer.  \nDate: July 2, 2026  \n1 Introduction  \nWhile visual perception dominates in many robotic task, tactile sensing is essential for achieving complex, fine-grained, and dexterous manipulation, especially when struggling with problems including occlusion and ambiguity in complex interactions. Tasks such as assembly, threading, or manipulating fragile items cannot be robustly executed without tactile sensing, indicating tactile sensing is a fundamental modality in advanced robotic systems.  \nHowever, collecting tactile data on real robots remains difficult and expensive. Tactile sensors on different embodiments (especially dexterous hands) are non-unified in hardware integration, and teleoperating robots for contact-rich tasks are labor-intensive and hard to scale [63] . In contrast, acquiring human demonstration data is considerably easier and more scalable. This disparity has motivated a series of interest in learning from human demonstrations and human-to-robot  \n*Equal contribution. Orders are decided by flipping a coin.†Correspondence to Zongqing Lu \u003C[lu@beingbeyond.com](lu@beingbeyond.com)> .  \nH-TAC Dataset TTP System Overview Real World Deployment  \nLarge-Scale Tactile & Action Dataset  \nVTDexManip AgiBot World FreeTacMan OmniViTac  \nH-Tac  \n135,000  \nTraj. w/ Tac.  \n\n|  |  |  |  | 73.12 |\n| --- | --- | --- | --- | --- |\n| 25.87 | 29.18 | ance\u003Cbr>32.72 | 51.5 |  |\n| 􀟨0.5 | 􀟨0.5 w/ tac. | BeingH-0.5 TTP-scratch |  | TTP |\n\nOverall Perform  \nFigure 1: Overview of the Transferable Tactile Pre-Training (TTP) system.  \nskill transfer [43, 44, 62, 67] . Yet, existing human demonstration datasets overwhelmingly focus on vision and action, largely overlooking the tactile modality. To fill in such gaps, collecting large-scale human-centric tactile-based dataset can be a possible solution.  \nOn the other hand, apart from tactile-rich human data, we also need proper architectures to learn skills and policies from these datasets. Recent vision-language-action (VLA) models have exhibited impressive abilities in performing complex and long-horizon tasks, demonstrating strong capabilities of planning and semanti","cbCaikcRRFhhhIVP","https://ap.wps.com/l/cbCaikcRRFhhhIVP","pdf",7932271,2,1,22,"English","en",105,"# Abstract\n# Introduction\n## Motivation: tactile sensing limitations\n## Dataset gap: human demonstrations vs tactile coverage\n## Research question and proposed solution","[{\"question\":\"Why is tactile sensing critical for dexterous robotic manipulation?\",\"answer\":\"Tactile sensing provides precise force feedback for contact-rich interactions, especially when vision faces occlusion and ambiguity. Without tactile signals, tasks like assembly, threading, and handling fragile items cannot be executed robustly.\"},{\"question\":\"What is H-Tac and what does it contribute?\",\"answer\":\"H-Tac is a large-scale tactile-action dataset with 160 hours of egocentric human videos, covering 300+ tasks and 135k episodes. It addresses the limited scale and narrow contact coverage of existing tactile datasets.\"},{\"question\":\"How does TTP enable transfer from humans to robots?\",\"answer\":\"TTP uses unified tactile and action spaces across pre-training and post-training to preserve prior knowledge during human-to-robot transfer. It models contact dynamics explicitly via a dual-expert framework that includes a tactile expert for future tactile prediction.\"}]",1784197115,55,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"human-centric-transferable-tactile-pre-training-for-dexterous-robotic-manipulation","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/human-centric-transferable-tactile-pre-training-for-dexterous-robotic-manipulation/84612/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is tactile sensing critical for dexterous robotic manipulation?","Question",{"text":75,"@type":76},"Tactile sensing provides precise force feedback for contact-rich interactions, especially when vision faces occlusion and ambiguity. Without tactile signals, tasks like assembly, threading, and handling fragile items cannot be executed robustly.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is H-Tac and what does it contribute?",{"text":80,"@type":76},"H-Tac is a large-scale tactile-action dataset with 160 hours of egocentric human videos, covering 300+ tasks and 135k episodes. It addresses the limited scale and narrow contact coverage of existing tactile datasets.",{"name":82,"@type":73,"acceptedAnswer":83},"How does TTP enable transfer from humans to robots?",{"text":84,"@type":76},"TTP uses unified tactile and action spaces across pre-training and post-training to preserve prior knowledge during human-to-robot transfer. It models contact dynamics explicitly via a dual-expert framework that includes a tactile expert for future tactile prediction.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]