[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3257":3,"related-3257":94},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":9,"secondary_topics":32,"classification":33,"search_phrases":64,"slug":67,"view_count":68,"doi":69,"paper":70,"created_at":93},3257,"Blueberry flow and mass estimation from harvester conveyor videos via foundation-model-assisted labeling and vision-based sensing","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112432","Despite rising labor costs and growing labor shortages, adoption of machine harvesting in fresh market blueberry production has been limited by issues such as high rates of bruising and the significant loss of fruits on the ground. Machine settings strongly affect fruit quality and harvesting performance, yet they are manually configured based on operator experience, with no real-time performance feedback. Towards addressing these limitations, this paper presents a sensing proof-of-concept for analyzing berry flow through the harvester by estimating the pixel-wise proportion of blue vs green berries and volumetric flow rate from overhead RGB-D images of the harvester’s conveyor. An automated labeling pipeline combining a domain-specific YOLOv8 patch detector with SAM2-based mask generation was developed to generate a realistic large-scale berry dataset from unlabeled images captured during commercial over-the-row blueberry harvesting operations. Compared to a baseline SegFormer model trained on a smaller dataset of manually annotated images, our fine-tuned SegFormer – trained and validated on the large-scale automatically generated dataset – achieves superior performance, with green berry IoU improving from 0.377 to 0.817 and recall increasing from 0.414 to 0.911. A scene-level YOLOv8-l detection model trained and evaluated on the same dataset achieves mAP(50-95) of 0.966 and 0.898 for blue and green berries, respectively. Both models’ performance is further confirmed by an independent evaluation on a manually annotated subset of the validation images. We also compared two approaches for predicting harvest yields across five machine-setting trials: a depth-based method using the RGB-D sensor and a detection-based method using only RGB images, achieving R 2 = 0.989 and R 2 = 0.894 , respectively, against ground-truth load cell measurements from these trials. To support future research, we publicly release our datasets and models.","尽管劳动力成本上升且劳动力短缺日益加剧，但鲜食蓝莓生产中机器采收的采用仍受到果实瘀伤率高和落地果实损失严重等问题的限制。机器设置对果实品质和采收性能有很大影响，但目前仍依赖操作人员经验进行手动配置，且没有实时性能反馈。针对这些局限，本文提出了一种传感概念验证方法，通过估计采收机传送带上方RGB-D图像中蓝莓与绿果的逐像素比例以及体积流量，来分析通过采收机的果实流。我们开发了一种自动标注流程，将领域特定的YOLOv8小块检测器与基于SAM2的掩膜生成相结合，从商业跨行蓝莓采收作业期间采集的无标注图像中生成逼真的大规模蓝莓数据集。与在较小规模人工标注图像数据集上训练的基线SegFormer模型相比，我们经过微调的SegFormer——在大规模自动生成数据集上训练和验证——取得了更优性能，绿果IoU从0.377提升至0.817，召回率从0.414提升至0.911。在同一数据集上训练和评估的场景级YOLOv8-l检测模型，对蓝莓和绿果分别达到0.966和0.898的mAP(50-95)。两个模型的性能还通过在验证图像人工标注子集上的独立评估得到进一步确认。我们还比较了在五次机器设置试验中预测采收产量的两种方法：使用RGB-D传感器的基于深度的方法和使用仅RGB图像的基于检测的方法，相对于这些试验中来自称重传感器的真实测量值，分别达到R² = 0.989和R² = 0.894。为支持未来研究，我们公开了数据集和模型。",null,"Computers and Electronics in Agriculture","2026-09-22T00:00:00Z","论文",10,false,83,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,23,19,14,9,1,"该研究提出基于基础模型辅助标注与视觉传感的蓝莓流量与产量估计方法，方法新颖、数据规模大且公开数据集与模型，对智慧农业与农业机器人领域有较高参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","农业机器人","机器视觉","蓝莓采收",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":14,"reason":63},[39,47,53,58],{"code":40,"score":41,"supported":42,"title":43,"abstract":45,"tags":46},"F5",11,true,[44],"harvester",[44],[],{"code":48,"score":49,"supported":14,"title":50,"abstract":51,"tags":52},"I2",2,[],[],[28,30],{"code":54,"score":22,"supported":14,"title":55,"abstract":56,"tags":57},"F6",[],[],[29],{"code":59,"score":22,"supported":14,"title":60,"abstract":61,"tags":62},"I1",[],[],[27],"农业相关性需要复核",[65,66],"蓝莓采收 机器视觉 产量估计","蓝莓收获机 传送带 视觉检测","蓝莓采收机器视觉产量估计-3257",4,"10.1016\u002Fj.compag.2026.112432",{"doi":69,"openalex_id":71,"authors":72,"venue":10,"cited_by_count":85,"oa_url":6,"card":86,"direction":90,"ingested_from":92},"W7214013690",[73,75,77,79,82],{"name":74,"orcid":9},"A. M. Aahad",{"name":76,"orcid":9},"Pico Sankari",{"name":78,"orcid":9},"Wei Q. Yang",{"name":80,"orcid":81},"Siniša Todorović","https:\u002F\u002Forcid.org\u002F0000-0001-5793-5921",{"name":83,"orcid":84},"Joseph R. Davidson","https:\u002F\u002Forcid.org\u002F0000-0003-4388-2210",0,{"tldr":87,"method":88,"finding":89,"direction":90,"opportunity":91},"用收割机传送带RGB-D视频估计蓝莓流量与质量，并公开数据集和模型。","YOLOv8+SAM2自动标注，SegFormer分割，RGB-D深度与检测法估","自动标注使绿果IoU从0.377升至0.817，深度法估产R²达0.989。","农业人工智能与决策模型","可延伸至收割机参数实时闭环调控，用视觉反馈优化机器设置以减损提质。","openalex","2026-09-23T23:30:01.713624Z",{"total":95,"page":22,"page_size":95,"items":96},6,[97,155,241,301,374,437],{"id":98,"title":99,"url":100,"summary":101,"summary_zh":9,"content":9,"source_name":102,"source_url":100,"published_at":103,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":104,"score_detail":105,"sources":109,"tags":111,"primary_topic":114,"secondary_topics":119,"classification":120,"search_phrases":134,"slug":137,"view_count":85,"doi":138,"paper":139,"created_at":154},5539,"Robust and transparent crop-row detection from RGB field imagery for vision-based agricultural guidance systems","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10473-z","Robust and transparent crop-row detection from RGB field imagery for vision-based agricultural guidance systems。Precision Agriculture","Precision Agriculture","2026-10-22T00:00:00Z",79,{"impact":106,"substance":107,"depth":17,"authority":20,"freshness":13,"relevant":22,"comment":108},16,21,"核心期刊新论文，提出鲁棒且可解释的RGB作物行检测方法，对视觉导航农机具参考价值明确，但属细分技术进展，未达重大突破层级。",[110],{"name":102,"url":100},[27,28,112,30,113],"精准农业","作物行检测",{"code":59,"slug":115,"name":116,"path":117,"parent_code":118},"smart-agriculture","智慧农业总论","\u002Ftopic\u002Fdigital-agriculture\u002Fsmart-agriculture","I",[],{"status":121,"locked":14,"version":35,"method":36,"evidence":122},"classified",{"candidates":123,"agricultural_evidence":42},[124,130],{"code":59,"score":125,"supported":42,"title":126,"abstract":127,"tags":129},5,[],[128],"precision agriculture",[27,112],{"code":48,"score":49,"supported":14,"title":131,"abstract":132,"tags":133},[],[],[28,30],[135,136],"RGB 作物行检测","农业人工智能 作物行检测 智慧农业 机器视觉","RGB作物行检测-5539","10.1007\u002Fs11119-026-10473-z",{"doi":138,"openalex_id":140,"authors":141,"venue":102,"cited_by_count":85,"oa_url":9,"card":9,"direction":9,"ingested_from":92},"W7223117828",[142,145,148,151],{"name":143,"orcid":144},"Esther Gascó","https:\u002F\u002Forcid.org\u002F0000-0003-1798-4483",{"name":146,"orcid":147},"Clara I. López-González","https:\u002F\u002Forcid.org\u002F0000-0002-2755-1692",{"name":149,"orcid":150},"Eva Besada-Portas","https:\u002F\u002Forcid.org\u002F0000-0001-6129-4653",{"name":152,"orcid":153},"Gonzalo Pájares","https:\u002F\u002Forcid.org\u002F0000-0003-0915-6282","2026-10-22T11:20:09.678587Z",{"id":156,"title":157,"url":158,"summary":159,"summary_zh":160,"content":9,"source_name":161,"source_url":158,"published_at":162,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":163,"score_detail":164,"sources":167,"tags":169,"primary_topic":171,"secondary_topics":176,"classification":177,"search_phrases":215,"slug":218,"view_count":219,"doi":220,"paper":221,"created_at":240},4877,"IoT-Enabled Autonomous Agriculture Monitoring Rover for Smart Farming: A Comprehensive Literature Review","https:\u002F\u002Fdoi.org\u002F10.22214\u002Fijraset.2026.85108","The rapid development of the Internet of Things (IoT), autonomous robotics, artificial intelligence (AI), embedded systems, wireless communication, and precision agriculture has created new opportunities for improving agricultural productivity and resource utilization. Conventional agricultural monitoring relies extensively on manual field inspection, which is time-consuming, labor-intensive, and often unable to provide continuous information about crop and soil conditions. Autonomous agricultural rovers provide an alternative approach by enabling mobile sensing, real-time environmental monitoring, crop observation, navigation, and precision agricultural operations. This paper presents a comprehensive literature review of IoT-enabled autonomous agricultural rovers for smart farming, with particular emphasis on recent developments reported in IEEE literature. Existing research is analyzed according to rover architecture, sensing technologies, navigation techniques, communication technologies, IoT platforms, agricultural applications, AI integration, and autonomy levels. Recent studies have demonstrated the feasibility of ESP32-based IoT rovers, ROS-based agricultural monitoring robots, autonomous navigation systems, precision irrigation platforms, soil-monitoring robots, and AI-enabled agricultural rovers. However, several limitations remain, including restricted autonomous navigation in unstructured environments, limited multi-parameter sensing, communication reliability in rural areas, high computational requirements for AI, energy limitations, and insufficient integration of monitoring with autonomous decision-making. Based on the reviewed literature, a research gap is identified for a low-cost, modular, IoT-enabled autonomous agricultural monitoring rover capable of simultaneously performing soil and environmental sensing, crop monitoring, obstacle avoidance, real-time wireless communication, location-aware operation, and intelligent decision support.","物联网（IoT）、自主机器人、人工智能（AI）、嵌入式系统、无线通信和精准农业的快速发展，为提升农业生产率和资源利用率创造了新的机遇。传统农业监测在很大程度上依赖人工田间巡检，这种方式耗时、费力，且往往无法持续提供作物和土壤状况的信息。自主农业巡田机器人通过实现移动传感、实时环境监测、作物观测、导航和精准农业作业，提供了一种替代方案。本文对面向智慧农业的物联网赋能自主农业巡田机器人进行了全面的文献综述，特别关注IEEE文献中报道的最新进展。现有研究按照巡田机器人架构、传感技术、导航技术、通信技术、物联网平台、农业应用、人工智能集成和自主性水平进行了分析。近期研究已证明基于ESP32的物联网巡田机器人、基于ROS的农业监测机器人、自主导航系统、精准灌溉平台、土壤监测机器人和人工智能赋能农业巡田机器人的可行性。然而，仍存在若干局限，包括非结构化环境中的自主导航受限、多参数传感能力有限、农村地区通信可靠性不足、人工智能的高计算需求、能量限制，以及监测与自主决策的集成不充分。基于所综述的文献，本文识别出一个研究空白，即缺乏一种低成本、模块化、物联网赋能的自主农业监测巡田机器人，能够同时执行土壤与环境传感、作物监测、避障、实时无线通信、位置感知作业和智能决策支持。","International Journal for Research in Applied Science and Engineering Technology","2026-10-13T00:00:00Z",52,{"impact":165,"substance":20,"depth":106,"authority":95,"freshness":165,"relevant":22,"comment":166},8,"综述性论文，系统梳理IoT自主农业巡检机器人架构与瓶颈，但来源期刊影响力有限，属细分领域参考价值。",[168],{"name":161,"url":158},[27,28,29,170,112],"物联网",{"code":172,"slug":173,"name":174,"path":175,"parent_code":118},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",[],{"status":121,"locked":14,"version":35,"method":36,"evidence":178},{"candidates":179,"agricultural_evidence":42},[180,186,190,197,204,211],{"code":172,"score":17,"supported":42,"title":181,"abstract":183,"tags":185},[182],"IoT",[170,184,182],"internet of things",[170],{"code":59,"score":41,"supported":42,"title":187,"abstract":188,"tags":189},[],[27,112,128],[27,112],{"code":48,"score":191,"supported":42,"title":192,"abstract":193,"tags":196},7,[],[194,195],"artificial intelligence","decision support",[28],{"code":198,"score":95,"supported":42,"title":199,"abstract":200,"tags":203},"H2",[],[201,202],"土壤","soil",[],{"code":205,"score":95,"supported":42,"title":206,"abstract":207,"tags":210},"H3",[],[208,209],"灌溉","irrigation",[],{"code":54,"score":22,"supported":14,"title":212,"abstract":213,"tags":214},[],[],[29],[216,217],"ESP32 ROS 农业机器人","农业人工智能 农业机器人 智慧农业 精准农业","ESP32ROS农业机器人-4877",3,"10.22214\u002Fijraset.2026.85108",{"doi":220,"openalex_id":222,"authors":223,"venue":161,"cited_by_count":85,"oa_url":158,"card":234,"direction":238,"ingested_from":92},"W7221682750",[224,226,228,230,232],{"name":225,"orcid":9},"Chaitra A S",{"name":227,"orcid":9},"Venugopal Gowda V",{"name":229,"orcid":9},"Vinay H",{"name":231,"orcid":9},"Jeevan T",{"name":233,"orcid":9},"Puneeth M",{"tldr":235,"method":236,"finding":237,"direction":238,"opportunity":239},"综述了物联网赋能的自主农业监测机器人，分析架构、传感、导航与AI集成，指出低成本模块化系统的研究空白","文献综述，聚焦IEEE近期研究，按架构、传感、导航、通信、AI与自主等级分类分析","现有系统在非结构化导航、多参数传感、农村通信、AI算力与能耗上存在局限，缺乏监测与决策一体化。","智慧农业 \u002F 农业物联网","可研发低成本模块化IoT自主巡田机器人，融合多传感、避障、实时通信与智能决策，填补集成空白。","2026-10-14T23:30:08.717386Z",{"id":242,"title":243,"url":244,"summary":245,"summary_zh":9,"content":9,"source_name":246,"source_url":9,"published_at":247,"category":248,"cover_url":9,"hotness":13,"is_selected":14,"score":249,"score_detail":250,"sources":253,"tags":255,"primary_topic":258,"secondary_topics":263,"classification":264,"search_phrases":296,"slug":299,"view_count":85,"doi":9,"paper":9,"created_at":300},4837,"山东出台数字强省建设'十五五'规划 建设特色农业'大脑'支持30个智慧农业应用场景","https:\u002F\u002Fnew.qq.com\u002Frain\u002Fa\u002F20261012A08ZIW00","山东发布数字强省建设'十五五'规划,在农业数智化方面,实施'人工智能+农业'行动,开展农业传感器与专用芯片、模型算法等研发攻关,大力发展智能农机与农业机器人,支持'无人农场'建设。建设特色农业'大脑',省级每年支持建设30个智慧农业应用场景,支持德州、聊城'吨半粮'等引领区数智化建设。建好用好'齐鲁农云''齐鲁农超''好粮有网'等平台,打造农业农村'数字大脑',建设80个数字农业发展县。","腾讯新闻 2026 年 10 月 12 日","2026-10-12T00:00:00Z","政策",77,{"impact":251,"substance":18,"depth":17,"authority":95,"freshness":165,"relevant":22,"comment":252},22,"省级数字强省规划含农业数智化具体条款与量化目标，信息增量足，值得进入每日精选。",[254],{"name":246,"url":244},[256,27,257,28,29],"数字乡村","无人农场",{"code":54,"slug":259,"name":260,"path":261,"parent_code":262},"agricultural-robots","机器人与无人农场","\u002Ftopic\u002Finputs-equipment\u002Fagricultural-robots","F",[],{"status":121,"locked":14,"version":35,"method":36,"evidence":265},{"candidates":266,"agricultural_evidence":42},[267,273,277,282,287,291],{"code":59,"score":268,"supported":42,"title":269,"abstract":270,"tags":272},15,[27],[27,271],"数字农业",[27],{"code":54,"score":165,"supported":42,"title":274,"abstract":275,"tags":276},[],[29,257],[29,257],{"code":40,"score":219,"supported":42,"title":278,"abstract":279,"tags":281},[],[280],"农机",[],{"code":172,"score":219,"supported":42,"title":283,"abstract":284,"tags":286},[],[285],"农业传感",[],{"code":48,"score":22,"supported":14,"title":288,"abstract":289,"tags":290},[],[],[28],{"code":292,"score":22,"supported":14,"title":293,"abstract":294,"tags":295},"I6",[],[],[256],[297,298],"山东 数字强省 十五五规划","齐鲁农云 智慧农业应用场景","山东数字强省十五五规划-4837","2026-10-14T00:04:01.888905Z",{"id":302,"title":303,"url":304,"summary":305,"summary_zh":306,"content":9,"source_name":307,"source_url":304,"published_at":247,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":308,"score_detail":309,"sources":313,"tags":315,"primary_topic":318,"secondary_topics":322,"classification":323,"search_phrases":351,"slug":354,"view_count":49,"doi":355,"paper":356,"created_at":373},4810,"Smart water management in agriculture: convergence of sensors, imaging, AI, precision irrigation, and robotics systems","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrwa.2026.1973897","Agricultural irrigation systems can bear the heavy losses of water through runoff, evaporation, and deep percolation. Crop water requirements vary with crop species, growth stage, soil properties, evapotranspiration, weather, and plant water status; therefore, irrigation scheduling based on a single parameter is insufficient. Conventional water management systems often rely on uniform application, fixed scheduling, and limited real-time information, which overlooks spatial and temporal variation in soil, crop, and weather conditions and can result in water loss, over-irrigation, and under-irrigation. This review highlights studies on the integration of AI-driven sensing and imaging technologies, IoT-based precision irrigation, variable-rate technologies, digital twins, and agricultural robotics for crop water management. These approaches integrate field, crop, weather, and spatial information to support water-demand assessment, crop-stress monitoring, irrigation scheduling, site-specific application, and automated water management. The reviewed studies report water savings, improved water-use efficiency, crop performance, and more site-specific irrigation and input application across different crops and irrigation systems. The review also highlights the limitations of these systems, including sensing reliability, model transferability, connectivity, interoperability, cybersecurity, investment costs, and environmental effects. Overall, the integration of these technologies provides potential for timely and field-specific irrigation decisions and supports efficient and climate-resilient water management in agriculture.","农业灌溉系统会因径流、蒸发和深层渗漏而承受严重的水量损失。作物需水量随作物种类、生长阶段、土壤性质、蒸散量、天气和植株水分状况而变化；因此，仅基于单一参数的灌溉调度是不够的。传统的水管理系统往往依赖均匀灌溉、固定调度和有限的实时信息，忽视了土壤、作物和天气条件的时空变异，可能导致水分损失、过度灌溉和灌溉不足。本文综述了将人工智能驱动的传感与成像技术、基于物联网的精准灌溉、变量灌溉技术、数字孪生和农业机器人集成应用于作物水分管理的研究。这些方法整合了田块、作物、天气和空间信息，以支持需水评估、作物胁迫监测、灌溉调度、定点变量灌溉和自动化水分管理。所综述的研究报告了在不同作物和灌溉系统中实现的节水、水分利用效率提升、作物表现改善以及更具田块针对性的灌溉和投入品施用。本文还指出了这些系统的局限性，包括传感可靠性、模型可迁移性、连通性、互操作性、网络安全、投资成本和环境影响。总体而言，这些技术的集成可为及时且针对具体田块的灌溉决策提供可能，并支持农业中高效且具有气候韧性的水分管理。","Frontiers in Water",78,{"impact":17,"substance":310,"depth":17,"authority":311,"freshness":21,"relevant":22,"comment":312},20,13,"系统综述AI传感、物联网精准灌溉与农业机器人集成，方法视角新、结论可靠，对智慧农业水资源管理有参考价值。",[314],{"name":307,"url":304},[27,28,29,316,317],"数字孪生","精准灌溉",{"code":205,"slug":209,"name":319,"path":320,"parent_code":321},"水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[],{"status":121,"locked":14,"version":35,"method":36,"evidence":324},{"candidates":325,"agricultural_evidence":42},[326,331,335,339,343,347],{"code":205,"score":17,"supported":42,"title":327,"abstract":328,"tags":330},[209],[208,209,329],"evapotranspiration",[317],{"code":198,"score":95,"supported":42,"title":332,"abstract":333,"tags":334},[],[201,202],[],{"code":172,"score":95,"supported":42,"title":336,"abstract":337,"tags":338},[],[170,182],[],{"code":59,"score":125,"supported":42,"title":340,"abstract":341,"tags":342},[],[316],[316,27],{"code":54,"score":68,"supported":42,"title":344,"abstract":345,"tags":346},[],[29],[29],{"code":48,"score":22,"supported":14,"title":348,"abstract":349,"tags":350},[],[],[28],[352,353],"精准灌溉 传感器 人工智能","农业机器人 水资源管理","精准灌溉传感器人工智能-4810","10.3389\u002Ffrwa.2026.1973897",{"doi":355,"openalex_id":357,"authors":358,"venue":307,"cited_by_count":85,"oa_url":367,"card":368,"direction":238,"ingested_from":92},"W7221563526",[359,362,364],{"name":360,"orcid":361},"Sachin Ghanghas","https:\u002F\u002Forcid.org\u002F0000-0001-9231-2527",{"name":363,"orcid":9},"Naveen Sihag",{"name":365,"orcid":366},"Parveen Dhanger","https:\u002F\u002Forcid.org\u002F0000-0001-5250-0275","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fwater\u002Farticles\u002F10.3389\u002Ffrwa.2026.1973897\u002Fpdf",{"tldr":369,"method":370,"finding":371,"direction":238,"opportunity":372},"综述AI传感、成像、物联网精准灌溉、数字孪生与机器人集成用于作物水分管理。","综述融合AI传感成像、IoT精准灌溉、变量技术、数字孪生与农业机器人。","集成方案可节水、提升水分利用效率与作物表现，但存在传感可靠性、模型迁移等局限。","可研究多源传感与数字孪生融合的跨区域模型迁移及低成本、安全互操作的灌溉决策系统。","2026-10-13T23:30:10.375774Z",{"id":375,"title":376,"url":377,"summary":378,"summary_zh":379,"content":9,"source_name":380,"source_url":377,"published_at":162,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":381,"score_detail":382,"sources":385,"tags":387,"primary_topic":390,"secondary_topics":394,"classification":395,"search_phrases":420,"slug":423,"view_count":125,"doi":424,"paper":425,"created_at":436},4798,"Adaptability of Lightweight AI Models for Embedded Deployment: A Case Study of an Agricultural Monitoring Robot","https:\u002F\u002Fdoi.org\u002F10.54254\u002F2755-2721\u002F2026.ld37676","Many artificial intelligence programs require powerful computing hardware, whereas agricultural robots, drones, and smart cameras rely on small embedded devices with limited computing power, battery capacity, and heat dissipation. Lightweight models reduce parameters and computational costs while maintaining acceptable accuracy, enabling AI deployment on resource-constraint network devices. This paper reviews key lightweighting methods, including compact network architectures, model pruning, model quantization, and knowledge distillation. It compares common platforms such as Jetson, Raspberry Pi, and microcontrollers. Using an agricultural monitoring robot as an example, this study proposes a system combining a camera, a lightweight YOLO model, Jetson, and a microcontroller for real-time crop monitoring. Experiments are designed to evaluate accuracy, speed, power consumption, temperature, and battery life. Rather than pursuing maximum model complexity, this paper focuses on explaining how to select a model that is truly suitable for the actual device. For agricultural robots, effective deployment requires sufficient accuracy, real-time performance, and low energy consumption.","许多人工智能程序需要强大的计算硬件，而农业机器人、无人机和智能摄像头则依赖于计算能力、电池容量和散热能力均有限的小型嵌入式设备。轻量级模型在保持可接受精度的同时减少参数和计算成本，使人工智能能够部署在资源受限的网络设备上。本文综述了关键的轻量化方法，包括紧凑网络架构、模型剪枝、模型量化和知识蒸馏。本文比较了Jetson、树莓派和微控制器等常见平台。以农业监测机器人为例，本研究提出了一种结合摄像头、轻量级YOLO模型、Jetson和微控制器的系统，用于实时作物监测。实验旨在评估精度、速度、功耗、温度和电池寿命。本文并非追求最大化的模型复杂度，而是着重解释如何选择真正适合实际设备的模型。对于农业机器人而言，有效部署需要足够的精度、实时性能和低能耗。","Applied and Computational Engineering",69,{"impact":383,"substance":17,"depth":106,"authority":311,"freshness":13,"relevant":22,"comment":384},12,"系统梳理轻量化模型在农业嵌入式设备上的部署路径，并以监测机器人案例给出可复现方案，对智慧农业工程落地有参考价值。",[386],{"name":380,"url":377},[27,28,29,388,389],"边缘计算","作物监测",{"code":48,"slug":391,"name":392,"path":393,"parent_code":118},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[],{"status":121,"locked":14,"version":35,"method":36,"evidence":396},{"candidates":397,"agricultural_evidence":42},[398,403,407,411,416],{"code":48,"score":191,"supported":42,"title":399,"abstract":400,"tags":402},[],[194,401],"YOLO",[28],{"code":54,"score":68,"supported":42,"title":404,"abstract":405,"tags":406},[],[29],[29],{"code":59,"score":22,"supported":14,"title":408,"abstract":409,"tags":410},[],[],[27],{"code":412,"score":22,"supported":14,"title":413,"abstract":414,"tags":415},"I3",[],[],[389],{"code":172,"score":22,"supported":14,"title":417,"abstract":418,"tags":419},[],[],[388],[421,422],"农业监测机器人 轻量YOLO Jetson","嵌入式AI 模型轻量化","农业监测机器人轻量YOLOJetson-4798","10.54254\u002F2755-2721\u002F2026.ld37676",{"doi":424,"openalex_id":426,"authors":427,"venue":380,"cited_by_count":85,"oa_url":430,"card":431,"direction":238,"ingested_from":92},"W7221561538",[428],{"name":429,"orcid":9},"Jingen Zhou","https:\u002F\u002Face.ewapub.com\u002Farticle\u002Fview\u002F37676.pdf",{"tldr":432,"method":433,"finding":434,"direction":238,"opportunity":435},"综述轻量化AI方法，并以农业监测机器人为例，提出相机+轻量YOLO+Jetson+单片机的嵌入式部署","综述网络压缩、剪枝、量化、蒸馏，对比Jetson、树莓派、单片机，设计农业机器人","农业机器人部署需兼顾足够精度、实时性与低能耗，而非追求最大模型复杂度。","可研究面向田间多变环境的轻量化模型自适应选择与能效-精度联合优化部署策略。","2026-10-13T23:30:08.379081Z",{"id":438,"title":439,"url":440,"summary":441,"summary_zh":9,"content":9,"source_name":442,"source_url":9,"published_at":9,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":443,"score_detail":444,"sources":447,"tags":449,"primary_topic":9,"secondary_topics":451,"classification":452,"search_phrases":476,"slug":479,"view_count":22,"doi":480,"paper":481,"created_at":489},4785,"Food's future: sustainability and agricultural robotics","https:\u002F\u002Fwww.frontiersin.org\u002Farticles\u002F10.3389\u002Ffrobt.2025.1696483\u002Ffull","Nleya等学者发表于Frontiers in Robotics and AI,围绕全球粮食系统面临的可持续挑战,系统梳理农业机器人如何助力农业可持续转型。文章提出五维分析框架:危机视角、技术分类、与精准农业IoT与AI与大数据的融合、环境经济社会可持续性评估,以及澳大利亚、美国、巴西、印度、中国等全球案例对比。文章指出机器人在降低化学品投入、节水、土壤改良、劳动力替代方面有显著效益。","Frontiers in Robotics and AI 2026",72,{"impact":17,"substance":310,"depth":445,"authority":20,"freshness":219,"relevant":22,"comment":446},17,"核心期刊综述，提出五维分析框架并含多国案例，对智慧农业与农业机器人方向有参考价值，但时效性偏弱。",[448],{"name":442,"url":440},[27,28,29,450,112],"农业物联网",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":453},{"candidates":454,"agricultural_evidence":42,"reason":475},[455,459,463,467,471],{"code":59,"score":125,"supported":42,"title":456,"abstract":457,"tags":458},[],[112],[27,112],{"code":54,"score":68,"supported":42,"title":460,"abstract":461,"tags":462},[],[29],[29],{"code":172,"score":68,"supported":42,"title":464,"abstract":465,"tags":466},[],[182],[450],{"code":198,"score":219,"supported":42,"title":468,"abstract":469,"tags":470},[],[201],[],{"code":48,"score":22,"supported":14,"title":472,"abstract":473,"tags":474},[],[],[28],"多个产业证据相当，需要确认主归属",[477,478],"Frontiers in Robotics and AI 农业机器人","农业机器人 粮食系统 可持续","FrontiersinRoboticsandAI农业机器人-4785","10.3389\u002Ffrobt.2025.1696483\u002Ffull",{"doi":480,"openalex_id":9,"authors":482,"venue":9,"cited_by_count":85,"oa_url":9,"card":483,"direction":238,"ingested_from":488},[],{"tldr":484,"method":485,"finding":486,"direction":238,"opportunity":487},"系统梳理农业机器人助力粮食系统可持续转型的路径与全球案例。","文献综述与五维分析框架，结合多国案例对比。","农业机器人在减药、节水、改土和替代劳动力方面效益显著。","可量化评估机器人对减药节水贡献，并研究小农户采纳与成本效益。","agent","2026-10-13T00:08:38.520864Z"]