[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84995-en":3,"doc-seo-84995-105":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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"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},84995,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Social-spatial Dependencies for Learning Visual Navigation","Navigation for social organisms is not independent: group structure, dynamics, and embodied interactions shape useful behavior. Neural-network controlled agents are trained to navigate hidden targets under different social contexts, where learned strategies depend on relative task performance and spatial effects. Increasing high-quality social information induces phase transitions from individual navigation to following, and to collision avoidance under crowded foraging. Nonstationary but predictable environmental dynamics promote behavioral hybridization between individual and social navigation, challenging purely individual-focused analysis.","arXiv :2607 .07460v 1 [ cs .NE] 8 Jul 2026  \nSOCIAL-SPATIAL DEPENDENCIES FOR LEARNING VISUAL  \nNAVIGATION  \nA PREPRINT  \nPatrick Govoni* 1 and Pawel Romanczuk 1,2,3  \n1Institute for Theoretical Biology, Department of Biology, Humboldt Universität zu Berlin, Berlin, Germany  \n2 Science of Intelligence, Research Cluster of Excellence, Berlin, Germany  \n3Bernstein Center for Computational Neuroscience, Berlin, Germany  \nJuly 9, 2026  \nABSTRACT  \nNavigation for social organisms rarely is a fully independent activity. Group structure and dynamics, as well as embodied interactions, critically influence useful behavior. Individual neural network controlled agents are trained to navigate in different social contexts, where social dependence and behavioral strategy learned is determined by relative task performance and spatial effect. Increasing high quality social information drives phase transitions from individual to following navigational strategy, and to collision avoidance in response to a crowded foraging patch. Predictable, nonstationary environmental dynamics drive behavioral hybridization between individual and social navigation, far and near the patch. Our findings challenge the approach of only inspecting individual behavior for social organisms and highlight the importance of taking a bottom-up approach in understanding how organisms behave.  \nKeywords spatial navigation · visual perception · collective behavior · social learning · sensorimotor control  \n1 Results  \nModel design  \nThe task is to navigate to a hidden patch located at a fixed position in a minimal, square environment (Fig. 1, left) . Four walls can be distinctly identified, where the four corners comprise the salient landmarks. The agents, both trained and untrained, are initialized randomly in the environment for each simulation. Additionally, two types of untrained agents  \n∗ Corresponding Author E-mail: [pgovoni21@gmail.com](pgovoni21@gmail.com)  \nprovide the option of social navigation with differing skill levels: experienced agents that walk directly to the patch and inexperienced agents that walk randomly about the environment. Population-level skill level and density were varied asthe relative proportion and total number of direct and random agents in the training environment.  \nFigure 1: Agent flow & train-test methodology. Left: (clockwise from bottom left) visual encoding, information processing, action conversion, environment update. Visual encoding identifies walls and other agents corresponding to retinal angles of a raycast (between-θ & θ field of view limits) . Visual information for the trained agent (blue) passes through convolutional neural network, perceptron, linear output layer, and hyperbolic tangent tranformations to directly represent both turning angle and speed via a linear function, which updates agent position and orientation for the next timestep. Untrained agents can be identified by their action-location status: on the patch and exploiting (purple), or off the patch and exploring (cyan) . Right: training with varying group structure and testing with a point perturbation; (top) two example environments with low/high social skill, where dotted lines showing potential paths of the others; (bottom) measuring learned social dependency by comparing behavior in perturbed test environments.  \nThe trained agent visually perceives the environment and other agents by raycast, inspired by [1] and extending thenon-social navigation in [2] . Eight rays extend from a center retina to the first collided object: boundary wall or another agent. Collisions one-hot encode which objects are at which egocentric angles. Other agents can be distinguished according to action-location status: whether the agent is on the patch and exploiting, or off the patch and exploring.  \nBody collisions, both agent-agent and agent-wall, are simulated with absorbing boundary conditions, where only movement directions in non-colliding directions are permitted. To brea","cbCaimdCghSqWXIu","https://ap.wps.com/l/cbCaimdCghSqWXIu","pdf",6022458,1,17,"English","en",105,"# Results\n## Model design\n## Task dependence","[{\"question\":\"How do group structure and dynamics influence navigation behavior in this study?\",\"answer\":\"Group structure and dynamics, along with embodied interactions, critically determine the behaviors that agents learn to perform effectively in social settings.\"},{\"question\":\"What happens when agents receive increasing amounts of high-quality social information?\",\"answer\":\"More high-quality social information drives phase transitions from individual navigation to following strategies, and under crowding it triggers collision avoidance.\"},{\"question\":\"Why does the study emphasize a bottom-up approach rather than only inspecting individual behavior?\",\"answer\":\"Because environmental dynamics and social cues jointly shape hybrid behavior that depends on both individual and social navigation, individual-only inspection cannot capture the full mechanism.\"}]",1784200111,43,{"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},"social-spatial-dependencies-for-learning-visual-navigation","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"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":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/social-spatial-dependencies-for-learning-visual-navigation/84995/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"How do group structure and dynamics influence navigation behavior in this study?","Question",{"text":74,"@type":75},"Group structure and dynamics, along with embodied interactions, critically determine the behaviors that agents learn to perform effectively in social settings.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What happens when agents receive increasing amounts of high-quality social information?",{"text":79,"@type":75},"More high-quality social information drives phase transitions from individual navigation to following strategies, and under crowding it triggers collision avoidance.",{"name":81,"@type":72,"acceptedAnswer":82},"Why does the study emphasize a bottom-up approach rather than only inspecting individual behavior?",{"text":83,"@type":75},"Because environmental dynamics and social cues jointly shape hybrid behavior that depends on both individual and social navigation, individual-only inspection cannot capture the full mechanism.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"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":52,"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":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]