[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81723-en":3,"doc-seo-81723-105":29,"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":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},81723,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Memory-Native Non-Terrestrial Networks for Embodied Intelligence","Non-terrestrial networks (NTN) enable embodied intelligence by providing connectivity for robots to access cloud resources and report critical information to remote centers. In highly dynamic, resource-constrained, topology-varying task environments, memoryless NTN protocols underperform because decisions rely only on local channel conditions and instantaneous demands. The proposed memory-native NTN (MemNTN) leverages long-horizon context via a dual-memory system separating physical world state from digital historical network experience, enabling cross-layer memory-driven optimization. Experiments on satellite embodied question answering show clear performance gains over stateless NTN and terrestrial approaches.","Memory-Native Non-Terrestrial Networks for  \nEmbodied Intelligence  \nChengyang Li, Yikun Wang, Jiahui He, Yujie Wan, Shuai Wang, Yuan Wu, Yik-Chung Wu, Chengzhong Xu, Fellow, IEEE, and Huseyin Arslan, Fellow, IEEE  \narXiv :2607 .00029v1 [ cs .RO] 22 Jun 2026  \nAbstract—Non-terrestrial networks (NTN) provide ubiquitous connectivity for embodied intelligence (EI), enabling robots in wilderness to leverage cloud resources or report critical information to remote centers. However, the synergy is nontrivial due to the highly-dynamic, resource-constrained, topology-varying, and task-oriented environment. Existing memoryless NTN protocols become inefficient, since the decisions are driven by local channel conditions and instantaneous service demands. To address these limitations, this paper proposes the memory-native NTN (MemNTN) paradigm that leverages long-horizon contexts for memory augmented system optimization. To realize this paradigm shift, we establish a dual-memory architecture that distinguishes between physical memory representing the state of the world and digital memory encoding historical network experience. We develop memory acquisition, compression, valuation, update, and utilization mechanisms that facilitate cross-layer, memorynative decision-making, spanning from the physical and access layers up to the network and application layers. Experiments in satellite embodied question answering (SEQA) demonstrate that the proposed MemNTN significantly outperforms conventional stateless NTN and terrestrial approaches.  \nIndex Terms—Non-terrestrial networks, embodied intelligence, memory-native, satellite question answering.  \nI. INTRODUCTION  \nEmbodied intelligence (EI) has become a pivotal role in enhancing the safety and efficiency of emergency response, evolving from basic data collection to sophisticated search and rescue tasks [1], [2] . Realizing these EI capabilities highly depends on the resilience of the underlying communication infrastructure, which remains vulnerable in wilderness and disaster-prone scenarios. For instance, remote command centers require timely updates regarding real-time situational awareness [3], [4] . However, communication outages caused by damaged base stations or severe blockage may delay mission-critical decisions. Such disruptions not only degrade remote sensing and teleoperation performance [5], but also hinder the deployment of cloud and edge computing [6], limiting the overall timeliness and reliability of EI operations. To address these challenges, non-terrestrial networks (NTN) with satellites and high-altitude platforms become a promising solution [7]–[13] . In contrast to terrestrial networks, NTN  \nChengyang Li, Yikun Wang, and Yik-Chung Wu are with The University of Hong Kong, Hong Kong, China. Jiahui He and Yujie Wan are with the Southern University of Science and Technology, Shenzhen, China. Shuai Wang is with the Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China. Yuan Wu and Chengzhong Xu are with the University of Macau, Macau SAR, China. Huseyin Arslan is with the Istanbul Medipol University, Istanbul, Turkey.  \nCorresponding author: Shuai Wang ( [s.wang@siat.ac.cn](s.wang@siat.ac.cn)).  \noffers flexible communication links capable of covering remote areas in an on-demand manner. This capability ensures persistent connectivity for robotic operations, irrespective of terrestrial infrastructure limitations. As depicted in Fig. 1, the synergy between NTN and EI facilitates long-range semantic queries, where a user in Istanbul can retrieve spatio-temporal observations from robotic teams operating in Pittsburgh.  \nHowever, NTN-EI faces unique challenges spanning the physical layer (e.g., channel estimation), media access control (MAC) layer (e.g., access protocols), network layer (e.g., mobility management), and application layer (e.g., task awareness), resulting in a highly-dynamic, resource-constrained, topology-varying, and task-oriented ","cbCaisEUoeeNXZM1","https://ap.wps.com/l/cbCaisEUoeeNXZM1","pdf",2807859,6,1,"English","en",105,"# Introduction\n## Embodied intelligence and communication challenges\n## Memory-native NTN (MemNTN) overview\n## Dual-memory architecture and lifecycle mechanisms","[{\"question\":\"What problem does MemNTN address in non-terrestrial networks for embodied intelligence?\",\"answer\":\"MemNTN targets inefficiency of memoryless NTN protocols in dynamic, resource-constrained, topology-varying, task-oriented environments where decisions depend only on local instantaneous conditions.\"},{\"question\":\"How is the proposed dual-memory architecture structured?\",\"answer\":\"MemNTN uses physical memory to represent the state of the world and digital memory to store historical network experience such as CSI, spectrum patterns, and scheduling records.\"},{\"question\":\"What mechanisms drive the memory-native decision-making across the protocol stack?\",\"answer\":\"MemNTN defines memory acquisition, compression, valuation, update, and utilization, centered on a memory valuation function that feeds a memory policy system for cross-layer designs from physical/access layers to network and application layers.\"}]",1784175641,20,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":27},"memory-native-non-terrestrial-networks-for-embodied-intelligence","",{"@graph":35,"@context":85},[36,53,68],{"@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":52},"https://docshare.wps.com/document/memory-native-non-terrestrial-networks-for-embodied-intelligence/81723/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","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},"What problem does MemNTN address in non-terrestrial networks for embodied intelligence?","Question",{"text":75,"@type":76},"MemNTN targets inefficiency of memoryless NTN protocols in dynamic, resource-constrained, topology-varying, task-oriented environments where decisions depend only on local instantaneous conditions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the proposed dual-memory architecture structured?",{"text":80,"@type":76},"MemNTN uses physical memory to represent the state of the world and digital memory to store historical network experience such as CSI, spectrum patterns, and scheduling records.",{"name":82,"@type":73,"acceptedAnswer":83},"What mechanisms drive the memory-native decision-making across the protocol stack?",{"text":84,"@type":76},"MemNTN defines memory acquisition, compression, valuation, update, and utilization, centered on a memory valuation function that feeds a memory policy system for cross-layer designs from physical/access layers to network and application layers.","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":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,126,129,133],{"id":21,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},"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":106,"slug":136},19,"General","general"]