[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81684-en":3,"doc-seo-81684-105":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},81684,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Tactile Genesis Exploring Tactile Sensors at Scale for Learning Dexterous Tasks","Tactile sensing is essential for contact-rich dexterous manipulation, yet the field lacks clarity on which tactile abstractions a policy needs and when richer tactile fields justify their hardware cost. Tactile Genesis introduces a GPU-parallel tactile sensor simulation platform that unifies many sensor modalities under configurable placement, resolution, and realistic noise. It reaches over 20,000 parallel environments and 1,000 taxels per GPU, enabling scalable teacher-student training and sensor ablations.","arXiv :2606 .22332v2 [ cs .RO] 9 Jul 2026  \nTactile Genesis: Exploring Tactile Sensors at Scale for Learning Dexterous Tasks  \nTrinity Chung†, 1 Kashu Yamazaki 1 Dhruv Patel 1 Alexis Duburcq2 Yiling Qiao2 Katerina Fragkiadaki 1 Aran Nayebi 1  \n1 Carnegie Mellon University 2 Genesis AI  \n†Corresponding Author: [trinityc@cmu.edu](trinityc@cmu.edu)  \nAbstract: Tactile sensing is critical for contact-rich dexterous manipulation, yet it remains unclear which tactile abstractions a policy needs and when richer tactile fields justify their hardware cost. This is hard to study empirically: each sensor effectively defines a new robot, and no lab can replicate the same learning experiment across all of them. We present Tactile Genesis, a GPU-parallel tactile sensor simulation platform that exposes binary contact, contact depth, per-taxel kinematic force/torque, elastomer marker displacement, geometry-aware proximity, contact audio, and a voxelized temperature field (the first of its kind in robot learning physics simulation platforms) under a common interface, with configurable placement, resolution, and a realistic noise model (drift, hysteresis, dead taxels, crosstalk) . It scales past 20,000 parallel environments and 1,000 taxels on a single GPU, improving throughput by 3 to 20 times over previous tactile simulators. We train teacher-student policies on three dexterous tasks, ablating sensor type, placement, resolution, and noise, and verify transfer to the real XHand1 . Proprioception alone is insufficient on every task. Sensor placement dominates sensor type: fingertip-only coverage trails whole-hand coverage by a wide margin, while adding the palm and proximal phalanges closes most of the gap to the privileged teacher. Resolution matters far less than coverage: placing 200 taxels across the whole hand suffices across tasks. We find that force/torque per taxel is consistently the most useful sensor type. These results give concrete guidance for both future tactile hardware design for improving robot hands and policy-side observation choice in dexterous manipulation.  \n[https://neuroagents-lab.github.io/tactile-genesis/](https://neuroagents-lab.github.io/tactile-genesis/)  \nKeywords: tactile simulation, dexterous manipulation  \n1 Introduction  \nDexterous manipulation is fundamentally contact-rich. Vision can localize objects before contact, and proprioception can track the robot’s own motion, but many manipulation failures happen through local phenomena that neither modality observes directly: slip, incipient loss of force closure, decoupled object-hand motion, small contact timing errors, and hidden contacts inside clutter. Biological manipulation makes the same point from the other direction: humans and animals can manipulate objects with little or no visual feedback once contact is established. The question for robot learning is therefore not whether touch can help, but what kind of tactile information a policy needs.  \nCurrent tactile hardware spans capacitive arrays [1], magnetic skins [2], vision-based elastomer sensors [3], strain gauge [4], contact microphones [4, 5], multisensory fingertips [6, 7, 8] . These sensors differ in spatial resolution, bandwidth, cost, durability, wiring complexity, calibration burden, and suitability to cover the entire hand versus only the fingertip. A lab that buys or builds one sensorized hand usually cannot repeat the same dexterous learning experiment across all of these alternatives.  \nConfi Sensor Contact Physics (b) Sim vs Real Demonstration  \n| \u003Cbr>\u003Cbr>\u003Cbr>Fingertips only\u003Cbr>\u003Cbr> |\n| --- |\n| Simulated XHand1 with KinematicTaxel sensors Real XHand1 |\n\nFigure 1: Overview of Tactile Genesis features. (a) The sensor physics can be configured to match their real sensor analogues, including 6-axis force/torque measurements, elastomer displacement, and proximity signal.(b) A visual comparison of the simulated tactile force reading per taxel on an XHand1 compared to the real XHand1’s sensor fidel","cbCaiiRsGWdGK1Ty","https://ap.wps.com/l/cbCaiiRsGWdGK1Ty","pdf",12920196,3,1,24,"English","en",105,"# Abstract\n# Introduction\n## Contact-rich manipulation and the role of touch\n## Limitations of existing tactile hardware\n## Controlled simulation as the missing comparison\n## Tactile Genesis overview and contributions","[{\"question\":\"Why is tactile sensing important for dexterous manipulation?\",\"answer\":\"Dexterous manipulation is contact-rich, and many failures stem from local phenomena that vision and proprioception may not directly observe, such as slip or incipient loss of force closure. Touch becomes critical once contact is established.\"},{\"question\":\"What does Tactile Genesis provide that prior tactile simulators could not?\",\"answer\":\"Tactile Genesis offers a scalable, hardware-agnostic tactile simulation platform with a unified interface for multiple contact abstractions. It supports configurable placement, resolution, and realistic noise, enabling controlled comparisons at large scale.\"},{\"question\":\"What sensor design factors most influence policy performance in the presented experiments?\",\"answer\":\"Sensor placement dominates sensor type: whole-hand coverage substantially outperforms fingertip-only coverage, and adding palm and proximal phalanges closes much of the gap. Resolution matters less than coverage, and force/torque per taxel is consistently the most useful sensor type.\"}]",1784175397,60,{"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},"tactile-genesis-exploring-tactile-sensors-at-scale-for-learning-dexterous-tasks","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"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":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/tactile-genesis-exploring-tactile-sensors-at-scale-for-learning-dexterous-tasks/81684/",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","2026-07-24","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 important for dexterous manipulation?","Question",{"text":75,"@type":76},"Dexterous manipulation is contact-rich, and many failures stem from local phenomena that vision and proprioception may not directly observe, such as slip or incipient loss of force closure. Touch becomes critical once contact is established.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does Tactile Genesis provide that prior tactile simulators could not?",{"text":80,"@type":76},"Tactile Genesis offers a scalable, hardware-agnostic tactile simulation platform with a unified interface for multiple contact abstractions. It supports configurable placement, resolution, and realistic noise, enabling controlled comparisons at large scale.",{"name":82,"@type":73,"acceptedAnswer":83},"What sensor design factors most influence policy performance in the presented experiments?",{"text":84,"@type":76},"Sensor placement dominates sensor type: whole-hand coverage substantially outperforms fingertip-only coverage, and adding palm and proximal phalanges closes much of the gap. Resolution matters less than coverage, and force/torque per taxel is consistently the most useful sensor type.","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},[93,97,101,105,109,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"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":29,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"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"]