[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127137-en":3,"doc-seo-127137-105":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":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":27,"seo_description":14,"update_tm":28,"read_time":29},127137,687207022233,"Riley","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Edge Acceleration of LiDAR Frame Transmission with In-network Machine Learning - Abstract","Real-time vehicle perception depends on timely, stable LiDAR data delivery between vehicles and the network edge, yet wireless variability and vehicle mobility create packet loss and latency jitter that degrade detection quality. This work proposes an in-network machine learning–driven packet duplication mechanism across dual wireless links, enabling real-time monitoring of performance degradation and dynamic activation. Practical implementation and extensive evaluation show the approach improves robustness to transmission uncertainties while reducing transmission times by about 50%, supporting strict millisecond requirements.","Edge Acceleration of LiDAR Frame Transmission with In-network  \nMachine Learning  \nPeng Qian  \n[peng.qian@eng.ox.ac.uk](peng.qian@eng.ox.ac.uk)[ ](peng.qian@eng.ox.ac.uk)Department of Engineering Science, University of Oxford Oxford, United Kingdom  \nChanggang Zheng  \n[changgang.zheng@eng.ox.ac.uk](changgang.zheng@eng.ox.ac.uk)[ ](changgang.zheng@eng.ox.ac.uk)Department of Engineering Science, University of Oxford Oxford, United Kingdom  \nNoa Zilberman  \n[noa.zilberman@eng.ox.ac.uk](noa.zilberman@eng.ox.ac.uk)[ ](noa.zilberman@eng.ox.ac.uk)Department of Engineering Science, University of Oxford Oxford, United Kingdom  \nABSTRACT  \nIn real-time vehicle perception scenarios, ensuring timely and stable transmission of LiDAR data between vehicles and the network edge is crucial for accurate object detection. However, the inherent variability of wireless links, coupled with the added impact of vehicle mobility, leads to inevitable packet loss and latency jitter, compromising both the timeliness and accuracy of vehicle perception. To address this challenge, we introduce a packet duplication mechanism on dual wireless links, improving LiDAR frame transmission performance. The solution is driven by an integrated In-Network Machine Learning module at a programmable edge device that dynamically detects performance degradation and controls packet duplication. Through practical implementation and extensive evaluation, it is demonstrated that the proposed packet duplication function can effectively address uncertainties in LiDAR frame transmission, while achieving 50% reduction in transmission times.  \nKEYWORDS  \nIn-network Machine Learning, P4, Edge computing, Vehicle perception  \n1 INTRODUCTION  \nThe past decade has witnessed significant advancements in the field of autonomous driving, particularly in real-time vehicle perception, which relies on timely Light Detection and Ranging (LiDAR) data transmission and processing. On the one hand, due to the rapid development of deep neural networks, core tasks such as scene and object recognition, can now be performed in real-time with milliseconds-level latency. On the other hand, the deployment of new wireless communication technologies (e.g., the new 5G radio) lays a robust foundation for enabling Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication. However, the inherent uncertainty of wireless networks in vehicular environments presents a significant challenge for ensuring the real-time delivery of LiDAR data, which remains an issue that has not been thoroughly evaluated and addressed.  \nA glance at recent works [3] [10] shows that while various Vehicle-to-Everything (V2X) frameworks have been deployed and tested across real-world networks, these studies primarily focused on reducing data size through redundancy elimination or vehicleedge collaboration across different access network types. For instance, EMP [10] tackled visual redundancy by merging framesand offloading real-time perception tasks to the edge via 4G link, achieving vehicle recognition in milliseconds. Soar [3] introduced a WiFi-based approach that clusters adjacent WiFi access nodes to  \nimprove mobility support, enabling real-time LiDAR frame transmission to vehicles within campus area. However, a common limitation of these approaches is the lack of feasible solutions addressing sluggish and unstable LiDAR frame transmissions, which are often caused by unavoidable network fluctuations.  \nInspired by these advancements in wireless network frameworks, towards a fast and robust LiDAR frame transmission performance, we propose an In-Network Machine-Learning (IN-ML) driven duallink packet duplication mechanism. The mechanism has two key components: 1) Packet duplication on dual links. Each packet ina LiDAR frame can be directly cloned on sender side across both Wi-Fi and cellular links, then the receiver keeps only the first arrival replica of each packet, mitigating the uncertainties of wireless links.  \n2)","cbCaifCYaCHOPYTc","https://ap.wps.com/l/cbCaifCYaCHOPYTc","pdf",1268384,1,6,"English","en",105,"# Abstract\n# Keywords\n# 1 Introduction","[{\"question\":\"Why is LiDAR data transmission difficult in real-time vehicle perception scenarios?\",\"answer\":\"Wireless links in vehicular environments are inherently unstable, and vehicle mobility amplifies packet loss and latency jitter, harming timeliness and perception accuracy.\"},{\"question\":\"What is the proposed packet duplication mechanism and how does it work?\",\"answer\":\"Each LiDAR packet is duplicated across dual links (Wi-Fi and cellular) at the sender, and the receiver keeps only the first arrival replica to mitigate link uncertainty.\"},{\"question\":\"How does in-network machine learning affect the duplication activation?\",\"answer\":\"An in-network machine learning module at a programmable edge device detects performance degradation in real time and dynamically activates packet duplication only when needed.\"}]","Edge Acceleration of LiDAR Frame Transmission with In-network Machine Learning - Abstract | PDF",1785937105,15,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"edge-acceleration-of-lidar-frame-transmission-with-in-network-machine-learning-abstract","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"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":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/edge-acceleration-of-lidar-frame-transmission-with-in-network-machine-learning-abstract/127137/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is LiDAR data transmission difficult in real-time vehicle perception scenarios?","Question",{"text":75,"@type":76},"Wireless links in vehicular environments are inherently unstable, and vehicle mobility amplifies packet loss and latency jitter, harming timeliness and perception accuracy.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the proposed packet duplication mechanism and how does it work?",{"text":80,"@type":76},"Each LiDAR packet is duplicated across dual links (Wi-Fi and cellular) at the sender, and the receiver keeps only the first arrival replica to mitigate link uncertainty.",{"name":82,"@type":73,"acceptedAnswer":83},"How does in-network machine learning affect the duplication activation?",{"text":84,"@type":76},"An in-network machine learning module at a programmable edge device detects performance degradation in real time and dynamically activates packet duplication only when needed.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":20,"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":53,"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":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]