[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83563-en":3,"doc-seo-83563-105":29,"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":21,"is_downloadable":21,"audit_status":21,"page_count":11,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},83563,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Robots Ask the Way: Communication-Enabled Social Navigation","Assistive autonomous robots operating in multiagent environments need efficient strategies to find specific individuals among multiple residents. Existing social navigation emphasizes reactive collision avoidance and trajectory adaptation, lacking proactive mechanisms to gather task-relevant information via human-robot communication. Communication-enabled Social Navigation (CommNav) has robots request spatio-temporal cues from residents about recent sightings, locations, and movements. Evaluation via Habitat 3.0c shows a 10 percentage-point Episode Success gain and strong robustness to colloquial natural-language instructions.","Robots Ask the Way: Communication-Enabled Social Navigation  \nValentino Sacco* and Luca Scofano* and Indro Spinelli and Fabio Galasso  \narXiv :2607 .0 1044v 1 [ cs .RO] 1 Jul 2026  \nAbstract—Assistive autonomous robots operating in multiagent environments require efficient strategies to locate specific individuals among multiple residents. Current social navigation methods focus on reactive collision avoidance and trajectory adaptation, but lack mechanisms to proactively gather information through human-robot communication.  \nWe introduce Communication-enabled Social Navigation (CommNav). In this novel task, robotic agents actively seek assistance from residents to locate target individuals by requesting information about recent sightings, locations, and movements.  \nTo evaluate CommNav, we extend Habitat 3.0 to create Habitat 3.0c, a communication-enabled variant supporting multi-human environments with information exchange protocols. Adding our communication module (COMM) to a stateof-the-art social navigation model yields a 10 percentagepoint improvement in Episode Success. We further investigate the transition from structured data to natural language by evaluating models trained on LLM-generated instructions and on colloquial instructions collected from a human study.  \nOur experiments reveal that: (i) explicit human-robot communication substantially enhances multi-person navigation performance; (ii) pre-training COMM on a communication pretext task effectively addresses the challenge of occasional interaction signals; and (iii) the navigation policy is highly robust to natural, colloquial human language, achieving an episode success statistically similar to the model using perfect structured data.  \nI. INTRODUCTION  \nSocial navigation requires robots to avoid obstacles, interpret human behavior, and adapt to dynamic, partially unknown environments. Existing approaches have primarily emphasized collision avoidance and motion planning [1], yet they lack proactive mechanisms for acquiring task-relevant information from other agents. This limitation becomes critical when robots must identify and interact with specific individuals in shared spaces such as households, offices, or care facilities. For instance, a robotic assistant tasked with delivering medication would, under traditional methods, rely on exhaustive room-by-room searches. In contrast, humans naturally employ communication to obtain spatial cues [2],[3], [4], and prior work confirms that dialogue improves cooperative navigation [5], [6] and that intermittent language instructions can boost long-horizon task performance [7] . State-of-the-art social navigation methods [8], [9], [10] cannot leverage human knowledge of recent spatial events or exploit the collaborative potential of human-robot cohabitation, and incorporating communication introduces challenges related to sparse interaction signals, heterogeneous cue types, and scalability as the number of agents grows.  \n*Authors contributed equally.  \nSapienza University of Rome, Italy, email: lastname@di.uniroma1.it  \nWe introduce Communication-enabled Social Navigation (CommNav), a novel task where robotic agents actively seek assistance from residents to locate target individuals, as illustrated in Fig. 1. We formalize CommNav as a multiagent navigation problem where robots query human agents for spatio-temporal information about a target’s location. Instead of exhaustive search, the robot can approach a resident and ask,“Have you seen them?” A helpful response, such as “I saw them entering the kitchen a few minutes ago,”allows the robot to navigate far more efficiently.1  \nTo enable this skill, we introduce a novel COMM module integrated into a leading DDPPO navigation model. Learning from the sparse and unpredictable signals of human interaction is a significant challenge. We address this by pretraining COMM on a communication pretext task, which achieves significant performance improvements over noncommunicat","cbCaitGa2DMJgZTP","https://ap.wps.com/l/cbCaitGa2DMJgZTP","pdf",3793802,3,1,"English","en",105,"# Introduction\n# Related Work\n## Embodied Navigation","[{\"question\":\"What problem does CommNav address in social navigation?\",\"answer\":\"CommNav targets the need to locate specific individuals in shared multiagent spaces. It addresses limitations of methods that focus mainly on collision avoidance without proactively acquiring information from people.\"},{\"question\":\"How do robots in CommNav obtain information from residents?\",\"answer\":\"Robots approach a resident and ask for spatio-temporal cues such as recent sightings, the resident’s observed location and movement, and related directional information. This conversational input guides navigation more efficiently than exhaustive search.\"},{\"question\":\"What evidence shows that communication improves navigation performance and language robustness?\",\"answer\":\"Adding the COMM module to a state-of-the-art social navigation model improves Episode Success by 10 percentage points. Experiments also evaluate transitions from structured data to LLM-generated and human colloquial instructions, showing navigation policy robustness with statistically similar performance to using perfect structured data.\"}]",1784188854,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"robots-ask-the-way-communication-enabled-social-navigation","",{"@graph":35,"@context":84},[36,52,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":20},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/robots-ask-the-way-communication-enabled-social-navigation/83563/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-26","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},"What problem does CommNav address in social navigation?","Question",{"text":74,"@type":75},"CommNav targets the need to locate specific individuals in shared multiagent spaces. It addresses limitations of methods that focus mainly on collision avoidance without proactively acquiring information from people.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How do robots in CommNav obtain information from residents?",{"text":79,"@type":75},"Robots approach a resident and ask for spatio-temporal cues such as recent sightings, the resident’s observed location and movement, and related directional information. This conversational input guides navigation more efficiently than exhaustive search.",{"name":81,"@type":72,"acceptedAnswer":82},"What evidence shows that communication improves navigation performance and language robustness?",{"text":83,"@type":75},"Adding the COMM module to a state-of-the-art social navigation model improves Episode Success by 10 percentage points. Experiments also evaluate transitions from structured data to LLM-generated and human colloquial instructions, showing navigation policy robustness with statistically similar performance to using perfect structured data.","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":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":21,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]