[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82380-en":3,"doc-seo-82380-105":28,"detail-sidebar-cat-0-en-105":89},{"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":4,"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},82380,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","One-Shot Multimodal Learning from Demonstration with Force-Constrained Elastic Maps","Robotic manipulation tasks require reasoning over both motion and contact forces, yet most Learning from Demonstration (LfD) approaches focus only on spatial trajectories and ignore force interactions. This gap limits robustness and can cause unsafe or inconsistent reproductions in force-constrained settings. A one-shot multimodal LfD framework is proposed for segmenting, encoding, and reproducing force-inclusive demonstrations. It uses multimodal probabilistic segmentation and an elastic maps extension with force constraints learned via convex optimization. Experiments validate force-aware segmentation and reproduction across five real tasks and two force-sensing platforms.","One-Shot Multimodal Learning from Demonstration with Force-Constrained Elastic Maps  \nBrendan Hertel, Jonathan Spanos, Navya Garg, and Reza Azadeh  \narXiv :2607 .09515v1 [ cs .RO] 10 Jul 2026  \nAbstract—Robotic manipulation tasks often require simultaneous reasoning over motion and contact forces, yet most Learning from Demonstration (LfD) methods model only spatial trajectories and neglect force interactions with the environment. This limitation reduces robustness and can lead to unsafe or inconsistent task reproduction in force-constrained settings. We propose a novel one-shot multimodal LfD framework for the segmentation, encoding, and reproduction of force-inclusive demonstrations. First, we introduce a multimodal probabilistic segmentation method that adaptively weighs spatial and force modalities over time, enabling the automatic extraction of forceaware motion primitives. Second, we extend the elastic maps representation to incorporate external force constraints during skill encoding and formulate a convex optimization procedure for learning force-consistent trajectory models. The resulting skills reproduce both motion and contact characteristics from a single demonstration while promoting safer execution by accounting for demonstrated force profiles. We validate our approach on five real-world manipulation tasks across two distinct force-sensing configurations: wrist force sensing on a UR5e with a Robotiq 2f-85 gripper and finger force sensing on a Kinova Gen3 with an Openhand Model O gripper. Experimental results demonstrate robust multimodal segmentation, accurate force-aware reproduction, and cross-platform generality.  \nI. INTRODUCTION  \nRobots are continually increasing their ability to interact with the world around them. Just as humans rely on touch and feel to navigate and manipulate their environment, robot manipulators must be able to do the same. One of the primary ways robots can achieve this is through force sensing. A simple way of teaching robots new tasks is through Learning from Demonstration (LfD) [1], where a human demonstrator shows a task, and the robot encodes and replicates the movement. Incorporating force data in these demonstrations provides robots with crucial context about the environment, allowing them to generate more informed and accurate movements during task reproduction. However, most LfD representations neglect forces, instead focusing solely on the robot’s spatial movements [2], [3] . For robots to consistently and reliably perform tasks, force sensing must be integrated into LfD frameworks.  \nIn this paper, we propose a novel one-shot multimodal Learning from Demonstration (LfD) framework for the segmentation, encoding, and reproduction of force-constrained demonstrations. In this first phase, our framework employs a novel multimodal probabilistic segmentation technique to  \nAuthors are with the Persistent Autonomy and Robot Learning (PeARL) Lab, University of Massachusetts Lowell, Lowell, MA 01854, USA. Emails: {brendan_hertel, jonathan_spanos, [navya_garg](navya_garg}@student.uml.edu)[}](navya_garg}@student.uml.edu)[@student.uml.edu](navya_garg}@student.uml.edu) , [reza@cs.uml.edu](reza@cs.uml.edu)  \nFig. 1: Human demonstrations can sometimes include excessive forces that should not be replicated. Our force-constrained LfD framework avoids these forces resulting in more accurate and safer reproductions.  \nbreak down the demonstrations into a set of primitive movements. Segmentation is often done using only a single modality of a demonstration (usually position or vision) [4], and rarely with other modalities [5] . Our segmentation process, in contrast, can incorporate contextual information of the demonstrations from force data collected via force sensors. Data collection is straightforward due to the inclusion of force sensors located on either the wrist or fingertips of most modern robots. We validate our learning framework through experiments with both sensor configurations, sh","cbCaikepdnNfuHBz","https://ap.wps.com/l/cbCaikepdnNfuHBz","pdf",22831088,1,"English","en",105,"# Introduction\n# Related Work","[{\"question\":\"Why do existing Learning from Demonstration methods struggle in force-constrained robot tasks?\",\"answer\":\"Most LfD representations model only spatial trajectories and neglect force interactions, reducing robustness. This can lead to unsafe or inconsistent reproduction when contact forces matter.\"},{\"question\":\"What does the proposed framework do to handle force during demonstration learning?\",\"answer\":\"It performs multimodal probabilistic segmentation that adaptively weighs spatial and force modalities over time. It also extends elastic maps with external force constraints learned through a convex optimization procedure.\"},{\"question\":\"How is the method validated and what platforms are used?\",\"answer\":\"The approach is evaluated on five real-world manipulation tasks using two force-sensing configurations. These include wrist force sensing on a UR5e with a Robotiq gripper and finger force sensing on a Kinova Gen3 with an Openhand Model O gripper.\"}]",1784180041,20,{"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":84,"head_meta":86,"extra_data":88,"updated_unix":26},"one-shot-multimodal-learning-from-demonstration-with-force-constrained-elastic-maps","",{"@graph":34,"@context":83},[35,52,66],{"@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/one-shot-multimodal-learning-from-demonstration-with-force-constrained-elastic-maps/82380/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":39,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"Why do existing Learning from Demonstration methods struggle in force-constrained robot tasks?","Question",{"text":73,"@type":74},"Most LfD representations model only spatial trajectories and neglect force interactions, reducing robustness. This can lead to unsafe or inconsistent reproduction when contact forces matter.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"What does the proposed framework do to handle force during demonstration learning?",{"text":78,"@type":74},"It performs multimodal probabilistic segmentation that adaptively weighs spatial and force modalities over time. It also extends elastic maps with external force constraints learned through a convex optimization procedure.",{"name":80,"@type":71,"acceptedAnswer":81},"How is the method validated and what platforms are used?",{"text":82,"@type":74},"The approach is evaluated on five real-world manipulation tasks using two force-sensing configurations. These include wrist force sensing on a UR5e with a Robotiq gripper and finger force sensing on a Kinova Gen3 with an Openhand Model O gripper.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,125,128,132],{"id":20,"doc_module":4,"doc_module_name":44,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":45,"doc_module":4,"doc_module_name":44,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":44,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":44,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":44,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":44,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":44,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":44,"category_name":123,"show_sort_weight":27,"slug":124},9,"Religion & Spirituality","religion-spirituality",{"id":27,"doc_module":4,"doc_module_name":44,"category_name":126,"show_sort_weight":27,"slug":127},"World Cup","world-cup",{"id":129,"doc_module":4,"doc_module_name":44,"category_name":130,"show_sort_weight":129,"slug":131},10,"Lifestyle","lifestyle",{"id":133,"doc_module":4,"doc_module_name":44,"category_name":134,"show_sort_weight":104,"slug":135},19,"General","general"]