[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83275-en":3,"doc-seo-83275-105":28,"detail-sidebar-cat-0-en-105":90},{"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":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":13,"seo_description":14,"update_tm":26,"read_time":27},83275,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Context-Aware Force Estimation for Deformable Tool Manipulation in Robotic Environmental Swabbing","Robotic surface swabbing depends on accurate tip-level contact force estimation during sustained interaction between a compliant deformable tool and heterogeneous environments. Deformable dynamics create nonlinear viscoelastic hysteresis that decouples wrist-mounted force measurements from true interface forces, while tool-tip sensing is impractical under sterility and disposability constraints. The proposed data-driven framework estimates contact force for deformable tool manipulation using proprioceptive sensing only, identifying a compact LSTM for low-latency inference. To generalize across unseen surfaces and compliance conditions, it applies parameter-isolated few-shot adaptation with FiLM-based context embeddings over a frozen recurrent backbone, improving robustness under domain shift by up to 63% without catastrophic forgetting.","Context-Aware Force Estimation for Deformable Tool Manipulation in Robotic Environmental Swabbing via Few-Shot Continual Adaptation  \nSiavash Mahmoudi 1 , Chaitainya Kuppar Reddy2 , Yang Tian 1 , and Dongyi Wang 1 ,2  \narXiv :2607 .07574v 1 [ cs .RO] 8 Jul 2026  \nAbstract—Robotic surface swabbing requires sustained interaction between a compliant tool and heterogeneous environments, where accurate estimation of tip-level contact force is critical for consistent sampling performance. However, deformable tool dynamics introduce nonlinear viscoelastic hysteresis that decouples wrist-mounted force measurements from true contact forces, while tool-integrated sensors are impractical for deployment due to sterility and disposability constraints. This paper presents a data-driven framework for contact force estimation in Deformable Tool Manipulation (DTM) that leverages proprioceptive sensing without requiring explicit physical models or permanent embedded sensing hardware atthe tool tip. A recurrent architecture is first identified through a comparative evaluation of temporal models, where a compact LSTM achieves the lowest estimation error and sub-millisecond inference latency. To address generalization across unseen surfaces and tool compliance conditions, we introduce a parameterisolated few-shot adaptation strategy that augments a frozen recurrent backbone with low-dimensional context embeddings using feature-wise linear modulation (FiLM). Experiments on a UR5e platform across nine tool–surface interaction regimes demonstrate that the proposed approach significantly improves robustness under domain shift, reducing zero-shot estimation error by up to 63% while preserving baseline performance without catastrophic forgetting. These results show that separating shared deformation-history dynamics from domain-specific conditioning enables reliable force estimation for DTM in nonstationary environments.  \nI. INTRODUCTION  \nDeformable interaction is a long-standing challenge in robotics and has been extensively studied under the umbrella of deformable object manipulation (DOM), with applications such as cloth folding, rope handling, and food manipulation [1] . In these problems, a rigid robot end-effector interacts with a deformable object, and the primary challenge lies in modeling and controlling the object deformation [2] .  \nManipulation tasks in which a robot operates through a deformable tool constitute a distinct and often more challenging class of problems, as the robot must interact with the environment indirectly through a compliant, deformable medium rather than directly manipulating a deformable object [3] . As illustrated in Fig. 1, in such settings, the tool itself undergoes continuous internal deformation during contact, causing the interaction forces at the tool–environment interface to be  \n*This work is supported by the project award no. 2023-70442-39232, from the U.S. Department of Agriculture’s National Institute of Food and Agriculture.  \n1Authors are with the Department of Biological and Agricultural Engineering, University of Arkansas, Fayetteville, AR 72701, USA. Email: [siavashm@uark.edu](siavashm@uark.edu)  \n2Author is with the Department of Food Science, University of Arkansas, Fayetteville, AR 72701, USA. Email: [dongyiw@uark.edu](dongyiw@uark.edu)  \nFig. 1. Force transmission dynamics. (a) Rigid tools show direct correspondence between wrist and contact forces. (b) Tool deformation decouples wrist sensing from tip forces.  \nfiltered, delayed, and decoupled from the forces measured at the robot wrist. This sensing and control mismatch makes accurate force estimation particularly difficult [4] . DTM is central to a wide range of practical applications, including wiping, brushing, polishing, surface inspection, surgical swabbing, and environmental sampling, where sustained contact and precise force regulation are essential for task effectiveness and safety. Unlike rigid tool manipulation, where interaction forc","cbCaigVGDHIgYfpn","https://ap.wps.com/l/cbCaigVGDHIgYfpn","pdf",33826887,1,"English","en",105,"# Abstract\n# Introduction\n## Deformable object manipulation background\n## Deformable tool manipulation (DTM) challenges\n## Why wrist sensing fails for deformable tools\n## Modeling difficulties: nonlinearity, hysteresis, and rate dependence","[{\"question\":\"Why is contact force estimation difficult for deformable tool manipulation?\",\"answer\":\"Deformable tool dynamics introduce viscoelastic hysteresis that decouples wrist-mounted forces from the true tool–surface contact forces, making conventional force sensing unreliable.\"},{\"question\":\"What model is used to estimate contact force without explicit physical models?\",\"answer\":\"A data-driven recurrent architecture is selected through temporal model evaluation, where a compact LSTM provides the lowest estimation error and sub-millisecond inference latency.\"},{\"question\":\"How does the method adapt to new surfaces and tool compliance conditions?\",\"answer\":\"It uses a parameter-isolated few-shot adaptation strategy that freezes a recurrent backbone and adds low-dimensional context embeddings with feature-wise linear modulation (FiLM) to improve generalization under domain shift.\"}]",1784186439,20,{"code":4,"msg":29,"data":30},"ok",{"site_id":23,"language":22,"slug":31,"title":13,"keywords":32,"description":14,"schema_data":33,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":26},"context-aware-force-estimation-for-deformable-tool-manipulation-in-robotic-environmental-swabbing","",{"@graph":34,"@context":84},[35,52,67],{"@type":36,"itemListElement":37},"BreadcrumbList",[38,42,46,49],{"item":39,"name":40,"@type":41,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":43,"name":44,"@type":41,"position":45},"https://docshare.wps.com/document/","Document",2,{"item":47,"name":12,"@type":41,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":41,"position":51},"https://docshare.wps.com/document/context-aware-force-estimation-for-deformable-tool-manipulation-in-robotic-environmental-swabbing/83275/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":39,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why is contact force estimation difficult for deformable tool manipulation?","Question",{"text":74,"@type":75},"Deformable tool dynamics introduce viscoelastic hysteresis that decouples wrist-mounted forces from the true tool–surface contact forces, making conventional force sensing unreliable.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What model is used to estimate contact force without explicit physical models?",{"text":79,"@type":75},"A data-driven recurrent architecture is selected through temporal model evaluation, where a compact LSTM provides the lowest estimation error and sub-millisecond inference latency.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the method adapt to new surfaces and tool compliance conditions?",{"text":83,"@type":75},"It uses a parameter-isolated few-shot adaptation strategy that freezes a recurrent backbone and adds low-dimensional context embeddings with feature-wise linear modulation (FiLM) to improve generalization under domain shift.","https://schema.org",{"og:url":50,"og:type":86,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":88,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":44,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":45,"doc_module":4,"doc_module_name":44,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":44,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":44,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":44,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":44,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":44,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":44,"category_name":124,"show_sort_weight":27,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":27,"doc_module":4,"doc_module_name":44,"category_name":127,"show_sort_weight":27,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":44,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":44,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]