[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85914-en":3,"doc-seo-85914-105":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},85914,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Interleaved POMDP Planning for Multi Object Search in Unknown Multi Room Household Environments","Multi-object search in unknown household environments demands planning under extensive uncertainty, including unseen object locations and unobserved obstacles in cluttered spaces. While POMDPs provide a principled foundation, direct solution remains intractable for large domains due to rapidly growing belief complexity. Inter-POMDP introduces interleaved planning with an LLM-informed high-level POUCT planner and an obstacle-aware low-level motion planner, improving both quality and efficiency. Simulations and real-world tests show reduced collisions, navigation steps, and detection counts versus baseline methods.","Interleaved POMDP Planning for Multi-Object Search in Unknown Multi-Room  \nHousehold Environments  \nRuochu Yang 1 , Ziyi Xia2 , Huibo Zhang2 , Yatong Han3 , Yiming Zhao3 , Yingke Li4 , Fumin Zhang2 , Yorai Wardi 1 , Mengxue Hou5  \narXiv :2607 . 10437v1 [ cs .RO] 11 Jul 2026  \nAbstract—Multi-object search in unknown household environments requires planning under extensive uncertainty—from unknown object locations to cluttered spaces with unobserved obstacles. POMDPs offera principled framework for such problems but remain intractable in large domains. We propose Inter-POMDP, a novel interleaved POMDP planning algorithm that decomposes this challenge into two interacting levels: a high-level POUCT planner reasons over object distributions using LLM-informed histogram beliefs, while a low-level motion planner models navigation uncertainty with obstacle-aware particle beliefs as domain knowledge to guide high-level POUCT. This interleaved design balances planning quality and efficiency despite the large search space across unknown multi-room environments. Both simulation and realworld experiments show that our Inter-POMDP algorithm reduces collision counts by up to 63%, navigation steps by up to 35%, and detection counts by up to 32% compared with baseline methods. Full videos are [https://sites.google.com/view/inter-pomdp](https://sites.google.com/view/inter-pomdp)  \nI. INTRODUCTION  \nHousehold robots are a long-standing topic in robotics, with object search being a classical problem. While many works address object search in deterministic settings, real-world deployments demand reasoning under partial observability: environments are large-scale, objects’ locations vary over time, and obstacles are unknown. Planning under such uncertainty is critical for developing fully autonomous household robots. Two key challenges arise: 1) the large state-action space and long planning horizon demand efficiency, as the search tree is deep with many branching factors;  \n2) the extensive activity range in cluttered, uncertain environments makes obstacle encounters highly likely, demanding planning quality and robustness. Partially observable Markov decision processes (POMDPs) provide a principled framework for sequential decisionmaking under uncertainty [1] . However, POMDPs are computationally intractable in large domains [2], as belief space dimensionality grows with the number of possible states—exponentially so with the number of objects in search tasks [3] . When the environment is only partially observed, the full state-action space is unknown and vast, making long-horizon planning especially difficult.  \nWe focus on cluttered multi-room household environments such as research laboratories or shared office workspaces, characterized by large open floors with similar furniture (e.g., tables, shelves) and miscellaneous objects (e.g., equipment, monitors, personal items) . In such settings, digging more informative object-level and objectfurniture relations is significant for efficient search [4] . Target objects may rest on the ground, serving simultaneously as obstacles and search targets, necessitating the integration of high-level semantic information into low-level navigation costs—beyond approaches that only consider distance-based reachability [5] . Moreover, large household environments emphasize an inevitable challenge: cluttered navigational space. Arbitrary arrangements of tables, chairs, and objects make it insufficient to simply partition rooms and expect  \n1 Georgia Institute of Technology, USA. 2The Hong Kong University of Science and Technology, China. 3Ising AI, China. 4MIT, USA. 5Notre Dame University, USA.  \nobstacle-free navigation between them. We aim to systematically incorporate grounded navigation information into the belief update process to make planning under uncertainty more robust. To achieve this, we treat uncertainty as physical rather than purely semantic. Many existing works [6]–[8] rely on high-level task pl","cbCaicZ4mAUPQ41I","https://ap.wps.com/l/cbCaicZ4mAUPQ41I","pdf",6074072,2,1,"English","en",105,"# Introduction\n## Challenges in multi-object search under partial observability\n## POMDP planning background and limitations\n## Problem setting: cluttered multi-room households\n## Proposed interleaved framework and contributions","[{\"question\":\"What core problem does the paper address in multi-object search?\",\"answer\":\"It addresses multi-object search in unknown household environments where object locations are uncertain and obstacles are unobserved, requiring robust planning under partial observability.\"},{\"question\":\"Why are standard POMDP approaches difficult for large multi-object search tasks?\",\"answer\":\"POMDP computation becomes intractable as belief-space dimensionality grows rapidly with the number of possible states, and this complexity increases exponentially with multiple objects.\"},{\"question\":\"How does Inter-POMDP combine high-level and low-level planning to improve performance?\",\"answer\":\"Inter-POMDP uses a high-level POUCT planner to reason over object distributions with LLM-informed histogram beliefs, while a low-level motion planner models navigation uncertainty using obstacle-aware particle beliefs; the two levels interact iteratively so low-level knowledge guides high-level action selection.\"}]",1784207146,20,{"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},"interleaved-pomdp-planning-for-multi-object-search-in-unknown-multi-room-household-environments","",{"@graph":35,"@context":84},[36,52,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,46,49],{"item":40,"name":41,"@type":42,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":20},"https://docshare.wps.com/document/","Document",{"item":47,"name":12,"@type":42,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/interleaved-pomdp-planning-for-multi-object-search-in-unknown-multi-room-household-environments/85914/",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 core problem does the paper address in multi-object search?","Question",{"text":74,"@type":75},"It addresses multi-object search in unknown household environments where object locations are uncertain and obstacles are unobserved, requiring robust planning under partial observability.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Why are standard POMDP approaches difficult for large multi-object search tasks?",{"text":79,"@type":75},"POMDP computation becomes intractable as belief-space dimensionality grows rapidly with the number of possible states, and this complexity increases exponentially with multiple objects.",{"name":81,"@type":72,"acceptedAnswer":82},"How does Inter-POMDP combine high-level and low-level planning to improve performance?",{"text":83,"@type":75},"Inter-POMDP uses a high-level POUCT planner to reason over object distributions with LLM-informed histogram beliefs, while a low-level motion planner models navigation uncertainty using obstacle-aware particle beliefs; the two levels interact iteratively so low-level knowledge guides high-level action selection.","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":20,"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"]