[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83869-en":3,"doc-seo-83869-105":30,"detail-sidebar-cat-0-en-105":92},{"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},83869,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation","Dexterous multi-finger hands enable human-like manipulation but are hard to train for real robots because contact-rich physics and imperfect actuation complicate policy learning and transfer. The work presents a sim-to-real reinforcement learning approach that uses dense tactile feedback and joint torque sensing to explicitly regulate physical interactions. A fast tactile simulator, a data-driven current-to-torque calibration, and randomized actuator dynamics modeling support effective transfer. Policies trained entirely in simulation are deployed zero-shot on a five-finger hand.","Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation  \nZhe Zhao 1 , Zhibin Li2 , Yilin Ou 1 , and Mengshi Qi 1  \n1 State Key Laboratory of Networking and Switching Technology  \nBeijing University of Posts and Telecommunications, China  \n2University College London, United Kingdom  \narXiv :2607 .04940v 1 [ cs .RO] 6 Jul 2026  \nAbstract—Human-like dexterous hands with multiple fingers offer human-level manipulation capabilities but remain difficult to train the control policies that can deploy on real hardware due to contact-rich physics and imperfect actuation. We present a sim-to-real reinforcement learning that leverages dense tactile feedback combined with joint torque sensing to explicitly regulate physical interactions. To enable effective simto-real transfer, we introduce (i) a computationally fast tactile simulation that computes distances between dense virtual tactile units and the object via parallel forward kinematics, providing high-rate, high-resolution touch signals needed by RL; (ii) a current-to-torque calibration that eliminates the need for torque sensors on dexterous hands by mapping motor current to joint torque; and (iii) actuator dynamics modeling with randomization to account for non-ideal torque–speed effects and bridge the actuation gaps. Using an asymmetric actor–critic PPO pipeline, we train policies entirely in simulation and deploy them directly to a five-finger hand. The resulting policies demonstrated two essential human-hand skills: (1) commandbased controllable grasp force tracking and (2) reorientation of objects in the hand, both of which were robustly executed without fine-tuning on the robot. By combining tactile and torque in the observation space with scalable sensing/actuation modeling, our system provides a practical solution to achieve reliable dexterous manipulation. To our knowledge, this is the first demonstration of controllable grasping on a multi-finger dexterous hand trained entirely in simulation and transferred zero-shot on real hardware.  \nI. INTRODUCTION  \nMulti-finger dexterous hands offer human-like manipulation capabilities, but their high degrees of freedom and complex contact dynamics make control challenging. Most realworld applications still rely on simple parallel-jaw grippers, and robust in-hand manipulation remains an open problem.  \nThis work explores the use of full-state feedback—tactile sensing and motor currents—to learn policies that explicitly sense and regulate contact forces. Unlike vision- or kinematics-only methods, we provide the policy with highresolution tactile data and motor currents, capturing detailed interaction forces. Using these inputs, we train for two key skills: (i) force-adaptive grasping that tracks commanded grip forces, and (ii) in-hand object rotation.  \nDeep reinforcement learning has advanced dexterous manipulation, with methods such as large-scale domain randomization for sim-to-real transfer of object rotation [1] .  \nSubsequent work in automatic domain randomization on a Corresponding author: Mengshi Qi ([qms@bupt.edu.cn](qms@bupt.edu.cn)).  \nFig. 1: Learning full-state policy with tactile sensing and joint torques for dexterous grasping and in-hand manipulation.  \nRubik’s Cube task [2] showed that sim-to-real is the key [3] . Recent simulation improved fidelity and robustness for cube reorientation on an Allegro Hand [4] . Tactile sensing further enhances dexterity, e.g., via visuotactile fusion [5] or binary touch signals [6] . Related advances include dexterous grasping [7], humanoid manipulation [8], and in-hand manipulation of thin objects with binary tactile sensing [9], showing that sim-to-real RL can produce transferable policies.  \nHowever, two practical hurdles limit the use of tactile sensing and joint torques: (i) Simulation of dense tactile contacts: Simulating high-resolution tactile/contact is computationally too slow for massive RL exploration, resulting in a br","cbCait2dI8yrGXbW","https://ap.wps.com/l/cbCait2dI8yrGXbW","pdf",4199663,6,1,9,"English","en",105,"# Introduction\n## Challenges in dexterous sim-to-real transfer\n## Proposed sim-to-real recipe and contributions","[{\"question\":\"What problem does the paper address in dexterous hand learning?\",\"answer\":\"Training control policies for real dexterous hands is difficult due to contact-rich physics and imperfect actuation, which causes a reality gap between simulation and hardware.\"},{\"question\":\"How does the method enable sim-to-real transfer without fine-tuning?\",\"answer\":\"It combines dense tactile feedback with torque/current information, using a fast tactile simulation, current-to-torque calibration to avoid torque sensors, and randomized actuator dynamics modeling to bridge actuation discrepancies.\"},{\"question\":\"What are the main skills the trained policies perform on the real five-finger hand?\",\"answer\":\"The policies demonstrate controllable grasp force tracking and in-hand object reorientation, executed robustly without robot fine-tuning.\"}]",1784191103,23,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"closing-the-reality-gap-zero-shot-sim-to-real-deployment-for-dexterous-force-based-grasping-and-manipulation","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/closing-the-reality-gap-zero-shot-sim-to-real-deployment-for-dexterous-force-based-grasping-and-manipulation/83869/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-27","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the paper address in dexterous hand learning?","Question",{"text":76,"@type":77},"Training control policies for real dexterous hands is difficult due to contact-rich physics and imperfect actuation, which causes a reality gap between simulation and hardware.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the method enable sim-to-real transfer without fine-tuning?",{"text":81,"@type":77},"It combines dense tactile feedback with torque/current information, using a fast tactile simulation, current-to-torque calibration to avoid torque sensors, and randomized actuator dynamics modeling to bridge actuation discrepancies.",{"name":83,"@type":74,"acceptedAnswer":84},"What are the main skills the trained policies perform on the real five-finger hand?",{"text":85,"@type":77},"The policies demonstrate controllable grasp force tracking and in-hand object reorientation, executed robustly without robot fine-tuning.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,120,123,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},"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":22,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"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":107,"slug":137},19,"General","general"]