[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83519-en":3,"doc-seo-83519-105":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},83519,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Path Planning in Physically Viable World Models","Robots operating in unstructured outdoor settings rely on pre-collected scene reconstructions to plan, even when terrain changes before or during execution can make earlier routes unsafe or unreachable. The work introduces a physically viable world model that augments reconstructed 3D Gaussian splat scenes with physics-based simulation, enabling what-if evaluation under future interventions without recollecting sensors. A terrain-aware planner uses these simulated events, obstacles, and deformations to test mission feasibility before committing to a route, verified on real-field experiments with simulated flooding.","arXiv :2607 .00673v 1 [ cs .RO] 1 Jul 2026  \nPath Planning in Physically Viable World Models  \nSu Ann Low Cheng-Hsi Hsiao Xingjian Li  \nAdam J. Thorpe Ufuk Topcu Krishna Kumar  \nThe University of Texas at Austin  \n[suann@utexas.edu](suann@utexas.edu) [chhsiao@utexas.edu](chhsiao@utexas.edu) [xingjian.li@austin.utexas.edu](xingjian.li@austin.utexas.edu)[ ](xingjian.li@austin.utexas.edu)[adam.thorpe@austin.utexas.edu](adam.thorpe@austin.utexas.edu) [utopcu@utexas.edu](utopcu@utexas.edu) [krishnak@utexas.edu](krishnak@utexas.edu)  \nAbstract: Robots deployed in unstructured outdoor environments often plan from scene reconstructions collected before deployment because operators cannot remap large or remote sites before every mission. As a result, robots must make long-horizon planning decisions using stale maps that assume the terrain remains unchanged, even though physical changes to the environment may render previously feasible routes unsafe or unreachable at execution time. We present a physically viable world model for evaluating what-if queries for robot navigation under future terrain change. The system augments reconstructed 3D Gaussian splat scenes with physics-based simulation to generate physically modified versions of the same environment without recollecting sensor data or rebuilding the map. We then implement a terrain-aware planner that accounts for physical events, obstacles, and deformations that are simulated by the world model. This allows robots and human operators to evaluate whether planned routes remain feasible before committing to a planned route, particularly in constrained environments where retreat or recovery may become impossible once conditions change. We evaluate the system on a real outdoor field site in Central Texas using simulated flooding across multiple severity levels. We measure route and mission feasibility as terrain conditions deteriorate under physically simulated interventions. Our results show that physically viable world models expose long-horizon route failuresand rerouting behavior that are not apparent when planning only on the original reconstructed environment, allowing robots to evaluate how future terrain changes may affect route feasibility before deployment.  \nKeywords: Physically Viable World Models, Field Robotics, Path Planning  \n1 Introduction  \nMost path planning algorithms reason over a single, fixed representation of the environment. Given a map, the planner searches for a feasible or optimal route and assumes that the represented world remains unchanged throughout the mission. This limits planning to asking which path is best in the observed environment, rather than whether the mission remains feasible under a specified physical change. That distinction is critical in off-road autonomy, disaster response, and field robotics, where flooding, terrain collapse, and debris accumulation can alter traversability after a map has been built. In constrained terrain, the cost of this limitation is severe: once a robot commits to a crossing, discovering during execution that it has flooded may leave no safe way back. Planning in such settings therefore requires more than a static map—it requires a physically viable world model (PVWM) that supports query-driven reasoning over families of physically modified scenes [1] .  \nWe present a method for path planning for off-road autonomous robots in physically viable world models. A physically viable world model transforms a reconstructed scene into query-conditioned environments generated by specified physical interventions. Such models answer what would happen under a given intervention, allowing a robot to evaluate conditions that have not yet occurred. We instantiate this framework using Gaussian splat reconstructions built from historical observations,  \nFigure 1: A physically viable world model generates scenes given different queries, and a traversability-aware path planner optimizes for routes under physical viability constraints","cbCaiajqlcnnuSWc","https://ap.wps.com/l/cbCaiajqlcnnuSWc","pdf",7838764,3,1,18,"English","en",105,"# Introduction\n## Physically Viable World Models for Query-Based Planning\n## Terrain-Aware Planning Under Physical Viability Constraints","[{\"question\":\"Why do robots need physically viable world models for outdoor path planning?\",\"answer\":\"Robots often plan using stale reconstructions that assume unchanged terrain, but physical changes like flooding or deformation can invalidate previously feasible routes during execution. A PVWM supports evaluating whether a route stays feasible under specified physical changes before committing.\"},{\"question\":\"How does the proposed system generate what-if environments without re-sensing?\",\"answer\":\"It augments reconstructed 3D Gaussian splat scenes with physics-based simulation, producing physically modified versions of the same environment for given intervention queries. This avoids recollecting sensor data or rebuilding the map.\"},{\"question\":\"What does the terrain-aware planner do to ensure physically realizable routes?\",\"answer\":\"It accounts for physical events and simulated obstacles and constrains routes to the terrain surface, blocks intervention-affected regions according to simulated severity, and enforces ground-contact constraints to produce realizable paths.\"}]",1784188590,45,{"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},"path-planning-in-physically-viable-world-models","",{"@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/path-planning-in-physically-viable-world-models/83519/",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","2026-07-26","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 do robots need physically viable world models for outdoor path planning?","Question",{"text":75,"@type":76},"Robots often plan using stale reconstructions that assume unchanged terrain, but physical changes like flooding or deformation can invalidate previously feasible routes during execution. A PVWM supports evaluating whether a route stays feasible under specified physical changes before committing.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed system generate what-if environments without re-sensing?",{"text":80,"@type":76},"It augments reconstructed 3D Gaussian splat scenes with physics-based simulation, producing physically modified versions of the same environment for given intervention queries. This avoids recollecting sensor data or rebuilding the map.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the terrain-aware planner do to ensure physically realizable routes?",{"text":84,"@type":76},"It accounts for physical events and simulated obstacles and constrains routes to the terrain surface, blocks intervention-affected regions according to simulated severity, and enforces ground-contact constraints to produce realizable paths.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]