[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85965-en":3,"doc-seo-85965-105":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},85965,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","SLIDER Sparse History-Guided Aerial Robot Target Search using Sliding Local Maps","Efficient exploration and aerial target search in large-scale unknown environments are constrained by broad spatial coverage needs, fine-grained perception, and real-time decision-making requirements. SLIDER introduces a lightweight, memory-efficient framework that avoids globally dense maps by combining a local sliding map with sparse global history information. A historical-pose and sensor-model based observation quality evaluation enables real-time frontier detection. Incremental viewpoint clustering and an incremental sparse topological map reduce candidate targets and computational load, improving memory use, latency, and search efficiency in simulations and real-world experiments.","arXiv :2607 . 10553v1 [ cs .RO] 12 Jul 2026  \nSLIDER: Sparse History-Guided Aerial Robot Target Search using Sliding Local Maps  \nXiaolei Hou†, Zheng Pan†,∗ , Hua Lan, Zhenghao Zou, Yinhong Chen, Chenxi Zhu,  \nYang Lyu, Jinwen Hu, Chunhui Zhao  \nFig. 1: Autonomous exploration of a large-scale, cluttered environment spanning several thousand square meters. The central image shows the exploration result, including the online-generated point cloud map, detected AprilTags, and the aerial robot’s flight trajectory. The side images provide two snapshots during the search process, illustrating the robot’s first-person view, current pose, and locally planned trajectories.  \nAbstract—Efficient exploration and target search in largescale unknown environments remain challenging for aerial robots due to the demands of broad spatial coverage, fine-grained perception, and real-time decision-making. This paper presents SLIDER, a lightweight and memory-efficient framework that avoids reliance on globally dense maps by combining a local sliding map with sparse global history information. A novel observation quality evaluation method is proposed, leveraging historical poses and sensor models to assess point cloud data in real-time, enabling efficient frontier detection. To support scalable and responsive planning, an incremental viewpoint clustering strategy dynamically adapts to local updates, significantly reducing the number of candidate targets and decreasing computational load. A sparse global topological map is incrementally maintained to assist global planning and cost evaluation. Extensive simulations and real-world experiments demonstrate that the proposed system outperforms state-of-the-art methods in memory usage, decision latency, and search efficiency.  \nIndex Terms—Aerial Systems: Perception and Autonomy; Aerial Systems: Applications; Search and Rescue Robots  \nI. INTRODUCTION  \nAERIAL robots have shown strong autonomous capabili  \nties in tasks such as post-disaster search and rescue as well as security patrols [1] . In unknown environments, aerial robots show great potential for replacing humans in exploration and target search, which demand large-scale mapping  \nThis work was supported in part by the Key Research and Development Program of Shaanxi Province under Grant 2024CY2-GJHX-42 and in part by the National Natural Science Foundation of China under Grants 62371398, 62293543, and 62322605 .  \n†Equal contribution. ∗ Corresponding author: [poao@mail.nwpu.edu.cn](poao@mail.nwpu.edu.cn).  \nThis article has been accepted for publication in IEEE Robotics and Automation Letters. Copyright 2026 IEEE. Personal use of this material is permitted.  \nProject page: [https://github.com/Poaos/SLIDER](https://github.com/Poaos/SLIDER).  \nand fine-grained perception—posing challenges in coverage, accuracy, and real-time decision-making.  \nTo address these challenges, environmental representation serves as a critical foundation for guiding robotic perception and decision-making. Most existing exploration methods rely on occupancy grid maps [2] or octree-based structures [3] to model space, selecting candidate targets from the boundaries between known and unknown regions. Some methods further refine this strategy by sampling viewpoints near detected obstacle boundaries [4], enabling more focused observations in areas with a higher likelihood of target presence. While these strategies enhance exploration performance, grid-based methods incur increasing memory costs as the environment grows, limiting their scalability under real-time constraints [5] . Although several studies have proposed more memoryefficient representations through geometric simplification [6] or point cloud compression [7], these approaches often lack sufficient spatial fidelity and adaptability for motion planning.  \nIn addition to environmental representation, efficient target selection is crucial for exploration performance. Early methods often rely on greedy strategies that","cbCaifQprOLQsAJq","https://ap.wps.com/l/cbCaifQprOLQsAJq","pdf",3923691,4,1,"English","en",105,"# Introduction\n## Challenges in large-scale aerial exploration\n## Prior approaches and limitations\n## SLIDER: Sparse history-guided target search","[{\"question\":\"What is the main idea behind SLIDER?\",\"answer\":\"SLIDER avoids globally dense maps by fusing a local sliding map with sparse global history information, using historical poses and a sensor model to evaluate observation quality in real time.\"},{\"question\":\"How does SLIDER perform real-time frontier or target identification?\",\"answer\":\"It introduces an observation quality evaluation method that leverages historical robot poses and sensor models to score point cloud data and enable efficient frontier detection.\"},{\"question\":\"Which strategies help SLIDER reduce computational cost and memory usage?\",\"answer\":\"An incremental viewpoint clustering strategy updates clusters online without costly global re-clustering, and a sparse global topological map is incrementally maintained for lightweight long-horizon planning and cost evaluation.\"}]",1784207421,20,{"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},"slider-sparse-history-guided-aerial-robot-target-search-using-sliding-local-maps","",{"@graph":35,"@context":84},[36,52,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"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":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":20},"https://docshare.wps.com/document/slider-sparse-history-guided-aerial-robot-target-search-using-sliding-local-maps/85965/",{"url":51,"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 is the main idea behind SLIDER?","Question",{"text":74,"@type":75},"SLIDER avoids globally dense maps by fusing a local sliding map with sparse global history information, using historical poses and a sensor model to evaluate observation quality in real time.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does SLIDER perform real-time frontier or target identification?",{"text":79,"@type":75},"It introduces an observation quality evaluation method that leverages historical robot poses and sensor models to score point cloud data and enable efficient frontier detection.",{"name":81,"@type":72,"acceptedAnswer":82},"Which strategies help SLIDER reduce computational cost and memory usage?",{"text":83,"@type":75},"An incremental viewpoint clustering strategy updates clusters online without costly global re-clustering, and a sparse global topological map is incrementally maintained for lightweight long-horizon planning and cost evaluation.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"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":20,"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"]