[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82257-en":3,"doc-seo-82257-105":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},82257,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","TactiDex: A Real-World Tactile-Guided Benchmark for Human-Like Dexterous Manipulation","TactiDex addresses the gap between kinematics-only dexterous transfer and contact-level human-like manipulation by introducing a real-world tactile-guided benchmark. The dataset synchronizes whole-hand tactile signals with multi-granularity hand kinematics and object states, enabling physically grounded learning beyond motion imitation. Building on this data paradigm, a tactile-driven transfer framework translates human demonstrations into plausible robotic execution. A companion TactiSkill framework uses a tri-component tactile reward to unify guidance, human-like alignment, and contact constraints, delivering improved success and physical realism across single and bimanual tasks.","TactiDex: A Real-World Tactile-Guided Benchmark for Human-Like Dexterous Manipulation  \nSuting Ni 1,2 Hanbing Zhang 1,2 Zhenyu Wei 1 Guo Chen 1 Chixuan Zhang 1 Ye Shi 1,2  \nJingya Wang 1, ∗  \n{nist2024, zhanghb2025, weizhy2024, chenguo2024, zhangchx12024, shiye, [wangjingya}@shanghaitech.edu.cn](wangjingya}@shanghaitech.edu.cn)  \n1 Shanghaitech University 2 InstAdapt  \narXiv :2607 .09190v1 [ cs .RO] 10 Jul 2026  \nAbstract  \nTactile feedback is fundamental to Hand-Object Interaction (HOI), governing contact formation, force regulation, and stable manipulation, making it essential for achieving true human-like dexterous manipulation. Yet, current human-to-robot dexterous transfer pipelines primarily rely on kinematic trajectories, resulting in motion imitation without physically grounded interaction. To address this, we introduce TactiDex, a real-world tactile-guided benchmark specifically designed to move dexterous manipulation beyond kinematic mimicry toward contact-level human-likeness. TactiDex provides a comprehensive dataset that elegantly aligns whole-hand tactile signals with multi-granularity kinematic and object states, coupled with standardized evaluation metrics. Building upon this data paradigm, we propose a tactile-driven transfer framework that effectively translates human demonstrations into physically plausible robotic execution. We introduce TactiSkill, a framework built upon a novel tri-component tactile reward that innovatively uses tactile signals as structured supervision. This reward unifies guidance, human-like alignment, and contact constraints into a single objective. Through comprehensive experiments on both single and bimanual tasks, we demonstrate that TactiSkill achieves superior performance in manipulation success and physical realism. This work lays a crucial foundation for advancing tactile-aware dexterous manipulation. Our project page at [https://tactidex.github.io/](https://tactidex.github.io/) .  \nKeywords  \nTactile-Guided Transfer, HOI Dataset, Dexterous Manipulation  \n1 Introduction  \nHand-object interaction (HOI) lies at the core of embodied intelligence, enabling humans to manipulate tools, operate daily objects, and perform complex dexterous skills. A defining characteristic of human dexterity is the continuous regulation of contact through tactile feedback, which governs contact formation, force modulation, and manipulation stability. While vision provides spatial and geometric awareness [13, 50, 51], tactile perception determineshow physical interaction is established and maintained at the handobject interface. Neuroscience and robotics research consistently show that successful manipulation relies heavily on force modulation rather than mere spatial positioning [30, 38, 52, 56] . Consequently, human dexterity is not solely a function of kinematic  \n∗ [Corresponding author: wangjingya@shanghaitech.edu.cn](Corresponding author: wangjingya@shanghaitech.edu.cn)  \ntrajectories, but fundamentally grounded in contact-level physical interaction.  \nTransferring such human dexterity to robotic systems remains alongstanding challenge. Recent advances in dexterous manipulation have explored human-to-robot skill transfer through imitation learning [2, 8, 26, 39, 47], motion retargeting [24, 40, 49, 53], and reinforcement learning frameworks [48, 54]. These approaches typically align human hand kinematics with robotic embodiments, leveraging visual observations and joint-level motion supervision to reproduce task behaviors. Despite impressive progress, this trajectory-centric paradigm inherently overlooks the tactile dynamics essential for regulating contact formation and force distribution. Consequently, robotic policies often successfully replicate superficial movement patterns, but deviate significantly in contact behavior, interaction stability, and force modulation.  \nA key factor underlying this gap is the absence of tactile-rich benchmarks and standardized evaluation protocols. Without stric","cbCailZVVuugFAPZ","https://ap.wps.com/l/cbCailZVVuugFAPZ","pdf",12870120,2,1,16,"English","en",105,"# Introduction\n## Hand-object interaction and tactile feedback\n## Limitations of existing transfer pipelines\n## TactiDex dataset and evaluation protocols\n## TactiSkill tactile-driven transfer framework","[{\"question\":\"Why do kinematics-only human-to-robot dexterous transfer pipelines fall short?\",\"answer\":\"They emphasize matching motion trajectories while ignoring tactile dynamics that regulate contact formation, force modulation, and interaction stability. As a result, policies may reproduce superficial movement but fail to achieve contact-level realism.\"},{\"question\":\"What is TactiDex, and what data does it provide?\",\"answer\":\"TactiDex is a real-world tactile-rich HOI dataset designed for contact-aware dexterous transfer. It synchronizes whole-hand tactile sensing with fine-grained hand kinematics, wrist 6D poses, and object 6D trajectories.\"},{\"question\":\"How does TactiSkill use tactile signals to improve robot manipulation?\",\"answer\":\"TactiSkill proposes a tri-component tactile reward that treats tactile signals as structured supervision. The objective combines guidance, human-like alignment, and contact constraints to improve manipulation success and physical realism.\"}]",1784179205,40,{"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},"tactidex-a-real-world-tactile-guided-benchmark-for-human-like-dexterous-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/tactidex-a-real-world-tactile-guided-benchmark-for-human-like-dexterous-manipulation/82257/",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","2026-07-22","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 do kinematics-only human-to-robot dexterous transfer pipelines fall short?","Question",{"text":75,"@type":76},"They emphasize matching motion trajectories while ignoring tactile dynamics that regulate contact formation, force modulation, and interaction stability. As a result, policies may reproduce superficial movement but fail to achieve contact-level realism.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is TactiDex, and what data does it provide?",{"text":80,"@type":76},"TactiDex is a real-world tactile-rich HOI dataset designed for contact-aware dexterous transfer. It synchronizes whole-hand tactile sensing with fine-grained hand kinematics, wrist 6D poses, and object 6D trajectories.",{"name":82,"@type":73,"acceptedAnswer":83},"How does TactiSkill use tactile signals to improve robot manipulation?",{"text":84,"@type":76},"TactiSkill proposes a tri-component tactile reward that treats tactile signals as structured supervision. The objective combines guidance, human-like alignment, and contact constraints to improve manipulation success and physical realism.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]