[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3911":3,"related-3911":115},{"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":32,"secondary_topics":38,"classification":39,"search_phrases":82,"slug":85,"view_count":70,"doi":86,"paper":87,"created_at":114},3911,"Trustworthy agricultural autonomy integrates robot learning safe control and human robot interaction","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44430-026-00044-2","The future of modern farming is intelligent, autonomous and data-driven farming operations. This will help to address the increasing labor shortage, resource constraints and climate variability. But for deployment in unstructured agricultural settings, high-performance automation is needed, as well as trustworthy systems that can make safe decisions, have the ability to learn adaptively and collaborate effectively with human operators. In this review, we discuss recent progress in trustworthy agricultural autonomy from the perspective of three interrelated pillars: robot learning and perception, safe control and resilient planning, and human-robot interaction. This review surveys state-of-the-art perception technologies such as computer vision, LiDAR, sensor fusion and deep reinforcement learning and safety-oriented approaches including model predictive control, formal verification, failure management and resilient navigation. It also addresses human-robot collaborative systems, explainable AI, ergonomics safety and sustainability-aware robotic design and discusses ethical, regulatory and socio-economic issues related to autonomous farming. Commercial applications of autonomous weeding, robotic harvesting and broad-acre field operations are now in existence, providing real-world demonstrations of the use of these technologies, and their potential to increase productivity, improve resource efficiency and enhance environmental sustainability. Finally, the review wraps up by underlining some future research priorities like universal safety certification, edge computing, interoperability, swarm robotics, and digital twin integration. Collectively, the reviewed evidence identifies the technical, human, and governance requirements that must be addressed to support safer, more resilient, transparent, and sustainable deployment of autonomous agricultural systems. Graphical Abstract","现代农业的未来在于智能化、自主化和数据驱动的农作运营。这将有助于应对日益加剧的劳动力短缺、资源约束和气候多变性。但要在非结构化的农业环境中部署，需要高性能自动化，以及能够做出安全决策、具备自适应学习能力并与人类操作员有效协作的可信系统。在本综述中，我们从三个相互关联的支柱角度讨论了可信农业自主性的最新进展：机器人学习与感知、安全控制与韧性规划，以及人机交互。本综述考察了计算机视觉、激光雷达（LiDAR）、传感器融合和深度强化学习等最先进的感知技术，以及模型预测控制、形式化验证、故障管理和韧性导航等面向安全的方法。它还涉及人机协作系统、可解释人工智能、人因工程安全和可持续性感知机器人设计，并讨论了与自主农业相关的伦理、监管和社会经济问题。自主除草、机器人收获和大田作业的商业应用现已存在，为这些技术的使用及其在提高生产力、改善资源效率和增强环境可持续性方面的潜力提供了真实世界的展示。最后，本综述总结了若干未来研究重点，如通用安全认证、边缘计算、互操作性、群体机器人和数字孪生集成。总体而言，所综述的证据明确了为支持更安全、更具韧性、更透明和更可持续的自主农业系统部署所必须解决的技术、人力和治理要求。图形摘要",null,"Discover Robotics","2026-09-30T00:00:00Z","论文",10,false,75,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,20,17,12,8,1,"系统综述农业自主系统的感知、安全控制与人机协作三大支柱，方法梳理全面，对智慧农业技术路线有参考价值。",[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","人机协作","自主作业",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":48},[45,54,60,68,75],{"code":46,"score":47,"supported":48,"title":49,"abstract":50,"tags":53},"I1",7,true,[],[51,52],"数字孪生","digital twin",[27],{"code":33,"score":47,"supported":48,"title":55,"abstract":56,"tags":59},[],[57,58],"计算机视觉","computer vision",[28],{"code":61,"score":62,"supported":48,"title":63,"abstract":64,"tags":67},"I5",6,[],[65,66],"边缘计算","edge computing",[],{"code":69,"score":70,"supported":48,"title":71,"abstract":72,"tags":74},"F6",4,[],[73],"robotic harvesting",[29],{"code":76,"score":77,"supported":48,"title":78,"abstract":79,"tags":81},"F4",3,[],[80],"除草",[],[83,84],"农业机器人 安全控制 人机协作","自主农业 感知 强化学习","农业机器人安全控制人机协作-3911","10.1007\u002Fs44430-026-00044-2",{"doi":86,"openalex_id":88,"authors":89,"venue":10,"cited_by_count":105,"oa_url":6,"card":106,"direction":112,"ingested_from":113},"W7214986074",[90,93,96,99,102],{"name":91,"orcid":92},"Muhammad Khizar Hayat","https:\u002F\u002Forcid.org\u002F0009-0005-4998-7138",{"name":94,"orcid":95},"Rahime Cengiz","https:\u002F\u002Forcid.org\u002F0000-0001-6355-7496",{"name":97,"orcid":98},"Muhammad Arif","https:\u002F\u002Forcid.org\u002F0000-0002-8631-4873",{"name":100,"orcid":101},"Umair Gull","https:\u002F\u002Forcid.org\u002F0000-0002-2261-8202",{"name":103,"orcid":104},"Mehmet Öten","https:\u002F\u002Forcid.org\u002F0000-0002-3737-2356",0,{"tldr":107,"method":108,"finding":109,"direction":110,"opportunity":111},"综述可信农业自主性，从机器人学习、安全控制与人机交互三支柱探讨技术进展与挑战。","综述计算机视觉、LiDAR、深度强化学习、模型预测控制、形式化验证及人机协作系统","自主除草、采摘与大田作业已商用，但需解决安全认证、边缘计算与互操作性等未来重点。","智慧农业 \u002F 农业物联网","可研究农业机器人通用安全认证框架、边缘计算实时决策及数字孪生与群体机器人协同。","数字乡村与农业信息化","openalex","2026-10-01T23:30:39.683136Z",{"total":62,"page":22,"page_size":62,"items":116},[117,180,271,329,395,464],{"id":118,"title":119,"url":120,"summary":121,"summary_zh":122,"content":9,"source_name":123,"source_url":120,"published_at":124,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":125,"score_detail":126,"sources":130,"tags":132,"primary_topic":134,"secondary_topics":135,"classification":136,"search_phrases":162,"slug":165,"view_count":166,"doi":167,"paper":168,"created_at":179},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","2026-10-13T00:00:00Z",69,{"impact":20,"substance":17,"depth":127,"authority":128,"freshness":13,"relevant":22,"comment":129},16,13,"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。",[131],{"name":123,"url":120},[27,28,29,65,133],"作物监测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":137},{"candidates":138,"agricultural_evidence":48},[139,145,149,153,158],{"code":33,"score":47,"supported":48,"title":140,"abstract":141,"tags":144},[],[142,143],"artificial intelligence","YOLO",[28],{"code":69,"score":70,"supported":48,"title":146,"abstract":147,"tags":148},[],[29],[29],{"code":46,"score":22,"supported":14,"title":150,"abstract":151,"tags":152},[],[],[27],{"code":154,"score":22,"supported":14,"title":155,"abstract":156,"tags":157},"I3",[],[],[133],{"code":61,"score":22,"supported":14,"title":159,"abstract":160,"tags":161},[],[],[65],[163,164],"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",5,"10.54254\u002F2755-2721\u002F2026.ld37676",{"doi":167,"openalex_id":169,"authors":170,"venue":123,"cited_by_count":105,"oa_url":173,"card":174,"direction":110,"ingested_from":113},"W7221561538",[171],{"name":172,"orcid":9},"Jingen Zhou","https:\u002F\u002Face.ewapub.com\u002Farticle\u002Fview\u002F37676.pdf",{"tldr":175,"method":176,"finding":177,"direction":110,"opportunity":178},"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":181,"title":182,"url":183,"summary":184,"summary_zh":185,"content":9,"source_name":186,"source_url":183,"published_at":187,"category":12,"cover_url":9,"hotness":188,"is_selected":14,"score":189,"score_detail":190,"sources":193,"tags":198,"primary_topic":202,"secondary_topics":203,"classification":214,"search_phrases":255,"slug":258,"view_count":22,"doi":259,"paper":260,"created_at":270},4573,"APPLICATION OF ARTIFICIAL INTELLIGENCE AND AUTOMATION TECHNOLOGIES IN MODERN AGRICULTURAL MACHINERY","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23255982","The rapid development of artificial intelligence (AI), robotics, computer vision, Internet of Things (IoT), satellite navigation, remote sensing, and autonomous control systems is transforming the design and operation of modern agricultural machinery. Agricultural machinery is increasingly evolving from conventional mechanical equipment into intelligent cyber-physical systems capable of sensing field conditions, processing large volumes of data, making operational decisions, and executing agricultural tasks with limited human intervention. This article examines the application of artificial intelligence and automation technologies in tractors, harvesters, sprayers, robotic platforms, unmanned aerial vehicles, and other agricultural machinery. The study is based on a systematic analysis of scientific publications, international institutional reports, and documented agricultural technology adoption data. Particular attention is given to autonomous navigation, machine vision, precision spraying, variable-rate application, crop monitoring, yield prediction, robotic weeding, harvesting, and safety systems. Evidence from the United States demonstrates substantial growth in precision-agriculture adoption: automated guidance systems were used on more than half of the acreage planted to several major crops, while in 2023 guidance autosteering was used by 52 percent of midsize farms and 70 percent of large-scale crop-producing farms. Scientific literature also demonstrates the growing role of machine learning in yield estimation, nitrogen management, disease detection, and robotic perception. However, high acquisition costs, inadequate rural connectivity, data governance issues, cybersecurity, technical complexity, and safety risks remain significant barriers. The study concludes that AI-enabled agricultural machinery can contribute to higher operational efficiency, more precise input application, reduced operator fatigue, improved resource management, and greater agricultural sustainability, provided that technological development is accompanied by appropriate infrastructure, human-capacity development, interoperability standards, and safety regulation.","人工智能（AI）、机器人技术、计算机视觉、物联网（IoT）、卫星导航、遥感及自主控制系统的快速发展，正在深刻改变现代农业机械的设计与运行方式。农业机械正日益从传统机械设备演变为智能信息物理系统，能够感知田间条件、处理海量数据、做出作业决策，并在有限人工干预下执行农业任务。本文探讨了人工智能与自动化技术在拖拉机、联合收割机、喷雾机、机器人平台、无人机及其他农业机械中的应用。研究基于对科学文献、国际机构报告及已记录的农业技术采用数据的系统分析。重点关注自主导航、机器视觉、精准喷雾、变量施用、作物监测、产量预测、机器人除草、收获及安全系统。来自美国的证据表明，精准农业的采用率大幅增长：自动导航系统已应用于多种主要作物一半以上的种植面积，而2023年，52%的中型农场和70%的大型作物生产农场使用了导航自动转向技术。科学文献也表明，机器学习在产量估算、氮素管理、病害检测和机器人感知中的作用日益增强。然而，高昂的购置成本、农村网络连接不足、数据治理问题、网络安全、技术复杂性及安全风险仍是重要障碍。研究结论认为，在技术发展的同时配套适当的基础设施、人力能力建设、互操作性标准和安全监管，人工智能赋能的农业机械能够有助于提高作业效率、实现更精准的投入施用、减轻操作人员疲劳、改善资源管理并增强农业可持续性。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-09T00:00:00Z",25,81,{"impact":191,"substance":18,"depth":17,"authority":128,"freshness":21,"relevant":22,"comment":192},22,"系统梳理AI与自动化在农机领域应用的综述性论文，含美国精准农业采纳率等实证数据，对智慧农业主题聚合有较高参考价值。",[194,195],{"name":186,"url":183},{"name":196,"url":197},"International Bulletin of Engineering and Technology","https:\u002F\u002Finternationalbulletins.com\u002Fintjour\u002Findex.php\u002Fibet\u002Farticle\u002Fview\u002F2468",[27,28,29,199,200,201],"农业物联网","精准农业","自动驾驶农机",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[204,210],{"code":205,"slug":206,"name":207,"path":208,"parent_code":209},"F5","machinery","农机装备与机械化","\u002Ftopic\u002Finputs-equipment\u002Fmachinery","F",{"code":61,"slug":211,"name":212,"path":213,"parent_code":37},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":40,"locked":14,"version":41,"method":42,"evidence":215},{"candidates":216,"agricultural_evidence":48},[217,223,230,237,243,247,251],{"code":33,"score":17,"supported":48,"title":218,"abstract":219,"tags":222},[142],[220,57,221,142,58],"机器学习","machine learning",[28],{"code":205,"score":19,"supported":48,"title":224,"abstract":226,"tags":229},[225],"agricultural machinery",[227,228,225],"农业机械","收割机",[],{"code":61,"score":13,"supported":48,"title":231,"abstract":232,"tags":236},[],[233,234,235],"物联网","internet of things","IoT",[199],{"code":154,"score":62,"supported":48,"title":238,"abstract":239,"tags":242},[],[240,241],"遥感","remote sensing",[],{"code":46,"score":166,"supported":48,"title":244,"abstract":245,"tags":246},[],[200],[27,200],{"code":76,"score":77,"supported":48,"title":248,"abstract":249,"tags":250},[],[80],[],{"code":69,"score":22,"supported":14,"title":252,"abstract":253,"tags":254},[],[],[29],[256,257],"农业机械 人工智能 自动化","精准农业 自动驾驶 农机","农业机械人工智能自动化-4573","10.5281\u002Fzenodo.23255982",{"doi":259,"openalex_id":261,"authors":262,"venue":186,"cited_by_count":105,"oa_url":183,"card":265,"direction":110,"ingested_from":113},"W7221138004",[263],{"name":264,"orcid":9},"Rahimjonov Shoxrux Shuhratjon o'g'li",{"tldr":266,"method":267,"finding":268,"direction":110,"opportunity":269},"系统综述AI与自动化技术在现代农机中的应用现状、效益与障碍。","系统分析科学文献、国际机构报告及美国精准农业采用数据。","AI农机可提升效率与可持续性，但成本、连接性、数据治理与安全仍是主要障碍。","可研究低成本AI农机方案、农村连接与数据治理标准，及人机协同安全监管框架。","2026-10-10T23:30:13.826410Z",{"id":272,"title":273,"url":274,"summary":275,"summary_zh":9,"content":9,"source_name":276,"source_url":9,"published_at":11,"category":277,"cover_url":9,"hotness":13,"is_selected":14,"score":278,"score_detail":279,"sources":283,"tags":285,"primary_topic":288,"secondary_topics":289,"classification":290,"search_phrases":324,"slug":327,"view_count":47,"doi":9,"paper":9,"created_at":328},4124,"农民日报《对话》栏目「用算法种好地 让AI扛农活」——杜志雄、李想、孔德栋三位专家谈农业AI落地","https:\u002F\u002Fwww.farmer.com.cn\u002F2026\u002F09\u002F30\u002F991030099.html","农民日报全媒体记者李克欣对话中国社科院杜志雄、中国农业大学李想、雄安集团孔德栋三位专家。专家指出当前我国智慧农业正从早期试点示范迈向规模化、体系化推广应用新阶段，人工智能赋能农业的关键技术包括机器学习与深度学习、计算机视觉与智能感知（如200万张高清图像训练的AI作物表型模型识别精度达95%以上）、农业大模型（如中化iMAP节约水肥10%~20%、增产8%~10%）和智能农机与农业机器人（如土壤高通量检测机器人实现42项指标检测误差控制在5%以内）。","中国农网（农民日报）·2026年9月30日","报道",83,{"impact":280,"substance":191,"depth":17,"authority":281,"freshness":166,"relevant":22,"comment":282},24,14,"央媒多方专家对话，含AI作物表型、农业大模型、农业机器人等具体数据与结论，信息增量足，但发布已过一周，时效性略降。",[284],{"name":276,"url":274},[27,28,286,29,287],"农业大模型","智能农机",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":291},{"candidates":292,"agricultural_evidence":48},[293,300,305,309,313,319],{"code":33,"score":294,"supported":48,"title":295,"abstract":296,"tags":299},11,[],[297,298,220,57],"大模型","深度学习",[28,286],{"code":205,"score":70,"supported":48,"title":301,"abstract":302,"tags":304},[],[303],"农机",[287],{"code":69,"score":70,"supported":48,"title":306,"abstract":307,"tags":308},[],[29],[29],{"code":46,"score":70,"supported":48,"title":310,"abstract":311,"tags":312},[],[27],[27],{"code":314,"score":77,"supported":48,"title":315,"abstract":316,"tags":318},"H2",[],[317],"土壤",[],{"code":154,"score":77,"supported":48,"title":320,"abstract":321,"tags":323},[],[322],"作物表型",[],[325,326],"中化 iMAP 大模型","AI 作物表型 识别精度","中化iMAP大模型-4124","2026-10-04T00:09:05.162758Z",{"id":330,"title":331,"url":332,"summary":333,"summary_zh":334,"content":9,"source_name":335,"source_url":332,"published_at":336,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":337,"score_detail":338,"sources":340,"tags":342,"primary_topic":343,"secondary_topics":344,"classification":345,"search_phrases":373,"slug":376,"view_count":377,"doi":378,"paper":379,"created_at":394},4063,"An Intelligent LLM–Fuzzy Decision Support and Digital Twin Framework for Adaptive Agricultural Robotics Systems","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriengineering8100423","This study develops an integrated LLM–fuzzy decision-support and digital twin framework for adaptive agricultural robotics, combining semantic reasoning, fuzzy inference, multi-objective optimization, and feedback-driven state updating. Numerical sensor data, operational information, and textual field knowledge are transformed into validated decision rules and model-ready parameters, enabling coordinated decisions across economic, operational, crop-stress, and sustainability-related objectives. The framework is evaluated as a simulation-based proof of concept calibrated with real observations from a semi-smart tomato farm, while controlled digital twin scenarios are used to assess its behavior under environmental and operational disturbances. Compared with numerical optimization alone, the complete LLM–fuzzy framework reduces operational cost by 3.35% and crop stress by 7.98%, while improving operational performance by 4.45%. Ablation, repeated-run, scenario, sensitivity, and dynamic-adaptation analyses further demonstrate consistent computational performance under the evaluated conditions. Sustainability is assessed through a model-based measure integrating water use, energy consumption, and soil-compaction-related impacts. These findings demonstrate the potential of combining semantic reasoning, uncertainty processing, optimization, and digital-twin feedback for adaptive agricultural decision support. However, the results represent a calibrated simulation-based proof of concept rather than validation through a full-scale autonomous field deployment; broader multi-season and field-scale validation is therefore required before generalizing the reported operational and sustainability benefits.","本研究开发了一个面向自适应农业机器人（adaptive agricultural robotics）的集成式LLM-模糊决策支持与数字孪生框架，融合了语义推理、模糊推理、多目标优化和反馈驱动的状态更新。数值传感器数据、运营信息和文本田间知识被转化为经过验证的决策规则和模型就绪参数，从而支持在经济、运营、作物胁迫和可持续性相关目标之间进行协调决策。该框架以基于仿真的概念验证形式进行评估，并利用半智能番茄农场的真实观测数据进行校准，同时使用受控数字孪生场景评估其在环境和运营扰动下的行为表现。与仅使用数值优化相比，完整的LLM-模糊框架将运营成本降低了3.35%，作物胁迫降低了7.98%，同时将运营性能提升了4.45%。消融实验、重复运行、场景、敏感性和动态自适应分析进一步表明，在所评估条件下该框架具有一致的计算性能。可持续性通过一个基于模型的度量进行评估，该度量综合了用水量、能源消耗和土壤压实相关影响。这些发现表明，将语义推理、不确定性处理、优化和数字孪生反馈相结合用于自适应农业决策支持具有潜力。然而，这些结果代表的是一种经过校准的基于仿真的概念验证，而非通过全尺度自主田间部署所进行的验证；因此，在将所报告的运营和可持续性效益加以推广之前，仍需开展更广泛的多季节和田间尺度验证。","AgriEngineering","2026-10-02T00:00:00Z",77,{"impact":127,"substance":191,"depth":17,"authority":128,"freshness":21,"relevant":22,"comment":339},"方法新颖、结论有量化支撑，但仅为仿真验证的概念验证，尚未田间落地，属细分领域前沿进展。",[341],{"name":335,"url":332},[27,28,29,51,200],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":346},{"candidates":347,"agricultural_evidence":48},[348,352,357,364,369],{"code":46,"score":19,"supported":48,"title":349,"abstract":350,"tags":351},[52],[51,52],[51,27,200],{"code":33,"score":20,"supported":48,"title":353,"abstract":355,"tags":356},[354],"decision support",[354],[28],{"code":358,"score":62,"supported":48,"title":359,"abstract":360,"tags":363},"B1",[],[361,362],"番茄","tomato",[],{"code":314,"score":62,"supported":48,"title":365,"abstract":366,"tags":368},[],[317,367],"soil",[],{"code":69,"score":70,"supported":48,"title":370,"abstract":371,"tags":372},[],[29],[29],[374,375],"LLM 模糊决策 农业机器人","数字孪生 番茄农场","LLM模糊决策农业机器人-4063",2,"10.3390\u002Fagriengineering8100423",{"doi":378,"openalex_id":380,"authors":381,"venue":335,"cited_by_count":105,"oa_url":332,"card":388,"direction":110,"ingested_from":113},"W7216447671",[382,385],{"name":383,"orcid":384},"Hamed Nozari","https:\u002F\u002Forcid.org\u002F0000-0002-6500-6708",{"name":386,"orcid":387},"Zornitsa B. Yordanova","https:\u002F\u002Forcid.org\u002F0000-0002-6056-8445",{"tldr":389,"method":390,"finding":391,"direction":392,"opportunity":393},"提出LLM-模糊决策与数字孪生框架，用于自适应农业机器人协同决策。","LLM语义推理、模糊推理、多目标优化与数字孪生仿真，基于半智能番茄农场数据。","相比纯数值优化，运营成本降3.35%、作物胁迫降7.98%、运营性能升4.45%。","农业人工智能与决策模型","可开展多季节田间规模化验证，并融合实时物联网数据提升数字孪生自适应能力。","2026-10-03T23:30:10.334001Z",{"id":396,"title":397,"url":398,"summary":399,"summary_zh":400,"content":9,"source_name":401,"source_url":398,"published_at":336,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":402,"score_detail":403,"sources":406,"tags":408,"primary_topic":411,"secondary_topics":412,"classification":413,"search_phrases":444,"slug":447,"view_count":77,"doi":448,"paper":449,"created_at":463},4059,"Smart Agriculture Technology: A Review of Robotic Platforms, Sensing Modalities, Artificial Intelligence, Datasets, Evaluation Metrics, and Future Research Directions","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriculture16192137","Smart agriculture has moved beyond isolated precision-farming tools toward integrated cyber–physical systems that combine robotics, multimodal sensing, connectivity, artificial intelligence, and data-driven decision support. This review synthesizes recent developments in the field using a systematic critical review approach. It proposes a systems-level framework for analyzing smart agriculture across robotic platforms, sensing and digital infrastructure, AI methods, public datasets and benchmarks, evaluation metrics, application domains, and deployment maturity. The review covers ground robots, UAVs, harvesting manipulators, multi-robot systems, RGB and spectral sensing, LiDAR, IoT networks, edge\u002Fcloud platforms, AI-based perception and decision-making, and multimodal vision–language models. The analysis shows that the literature has made clear progress in prototypes, datasets, and task-specific performance, but several gaps still limit practical deployment. These include weak cross-season and cross-region validation, fragmented benchmarking practices, limited deployment-oriented metrics, insufficient techno-economic reporting, and unresolved challenges related to interoperability and human–robot interaction. Public datasets and emerging multimodal benchmarks show that the field is moving toward greater standardization; however, strong benchmark performance does not yet consistently translate into reliable field operation. The review concludes by outlining future research directions in benchmark realism, field-robust AI, edge deployment, digital twins, privacy-preserving learning, human-centered autonomy, and long-term agronomic and economic validation.","智慧农业已超越孤立的精准农业工具，迈向集机器人、多模态感知、连接性、人工智能和数据驱动决策支持于一体的信息物理系统。本综述采用系统性批判性综述方法，梳理了该领域的最新进展，提出了一个系统级框架，从机器人平台、感知与数字基础设施、人工智能方法、公共数据集与基准、评估指标、应用领域和部署成熟度等维度分析智慧农业。综述涵盖地面机器人、无人机、采摘机械臂、多机器人系统、RGB与光谱感知、激光雷达、物联网网络、边缘\u002F云平台、基于人工智能的感知与决策以及多模态视觉-语言模型。分析表明，文献在原型、数据集和特定任务性能方面已取得明显进展，但若干差距仍制约着实际部署，包括跨季节与跨区域验证薄弱、基准测试实践碎片化、面向部署的指标有限、技术经济报告不足，以及互操作性和人机交互方面的挑战尚未解决。公共数据集和新兴多模态基准表明该领域正朝着更高标准化方向迈进；然而，优异的基准性能尚未能一致地转化为可靠的田间作业。综述最后展望了未来研究方向，包括基准现实性、田间鲁棒人工智能、边缘部署、数字孪生、隐私保护学习、以人为中心的自主性以及长期农艺与经济验证。","Agriculture",80,{"impact":17,"substance":191,"depth":404,"authority":128,"freshness":21,"relevant":22,"comment":405},19,"系统梳理智慧农业机器人、感知、AI与基准评测的综述，指出跨季节验证与部署指标缺口，对农业信息化研究有较高参考价值。",[407],{"name":401,"url":398},[27,28,29,51,409,410],"多模态感知","农业数据集",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":414},{"candidates":415,"agricultural_evidence":48},[416,421,425,429,435,439],{"code":46,"score":404,"supported":48,"title":417,"abstract":419,"tags":420},[418],"smart agriculture",[27,200,51,418],[51,27],{"code":33,"score":127,"supported":48,"title":422,"abstract":423,"tags":424},[142],[142,354],[28,409],{"code":61,"score":62,"supported":48,"title":426,"abstract":427,"tags":428},[],[233,235],[],{"code":430,"score":77,"supported":48,"title":431,"abstract":432,"tags":434},"A7",[],[433],"间作",[],{"code":69,"score":22,"supported":14,"title":436,"abstract":437,"tags":438},[],[],[29],{"code":440,"score":22,"supported":14,"title":441,"abstract":442,"tags":443},"I6",[],[],[410],[445,446],"农业机器人 多模态感知 评测基准","智慧农业 数字孪生 边缘部署","农业机器人多模态感知评测基准-4059","10.3390\u002Fagriculture16192137",{"doi":448,"openalex_id":450,"authors":451,"venue":401,"cited_by_count":105,"oa_url":398,"card":458,"direction":110,"ingested_from":113},"W7216116945",[452,455],{"name":453,"orcid":454},"Ghaith Al-refai","https:\u002F\u002Forcid.org\u002F0000-0002-8505-9719",{"name":456,"orcid":457},"Mahmoud Al-Sarayreh","https:\u002F\u002Forcid.org\u002F0000-0001-8711-0453",{"tldr":459,"method":460,"finding":461,"direction":110,"opportunity":462},"系统综述智慧农业机器人、传感、AI、数据集与评估指标，指出落地瓶颈并展望方向。","系统批判性综述，提出系统级框架，覆盖机器人、多模态传感、AI与基准。","原型与数据集进展明显，但跨季节验证、基准碎片化与部署指标不足阻碍落地。","可研究跨季节跨区域鲁棒AI、部署导向评估指标及数字孪生与隐私保护学习。","2026-10-03T23:30:10.036723Z",{"id":465,"title":466,"url":467,"summary":468,"summary_zh":469,"content":9,"source_name":470,"source_url":467,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":471,"score_detail":472,"sources":476,"tags":478,"primary_topic":480,"secondary_topics":481,"classification":482,"search_phrases":501,"slug":504,"view_count":77,"doi":505,"paper":506,"created_at":561},4039,"WeedNet: a foundation model-based global-to-local AI approach for weed species identification and classification","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41467-026-78044-4","Early weed identification is crucial for effective management and control, and researchers, agronomists, and technology developers are increasingly interested in automating this process using computer vision and artificial intelligence; however, limited expert-verified data and variable morphological features have hindered the development of AI-based weed identification models. To address these issues, we present WeedNet, a global-scale weed identification model that can recognize an extensive set of weed species. WeedNet is an end-to-end weed identification pipeline that uses self-supervised learning, fine-tuning, and enhanced trustworthiness strategies. WeedNet achieved 91.02% accuracy across 1,593 weed species, with 41% of species achieving 100% accuracy. Using a fine-tuning approach, the local Iowa WeedNet model achieved 97.38% overall accuracy for 84 Iowa weeds. Testing across intra-species dissimilarity and inter-species similarity suggests that diversity in the images collected, spanning all the growth stages and distinguishable plant characteristics, is crucial in driving model performance. The global WeedNet model serves as a foundation, and the global-to-local strategy enables targeted fine-tuning to improve performance in regional weed communities. Additional validation of drone- and ground-rover-based images highlights WeedNet’s potential for integration into robotic platforms. Furthermore, integration with artificial intelligence for conversational use provides intelligent agricultural and ecological conservation consulting tools for farmers, researchers, and government agencies across diverse landscapes. Weeds consistently threaten crop yields worldwide, making early and accurate identification essential for effective management. Trained on 14 million images representing 1,593 weed species, WeedNet achieved 91% global accuracy and, through global-to-local fine-tuning, reached 97% accuracy for Iowa weeds.","早期杂草识别对有效管理和控制至关重要，研究人员、农艺学家和技术开发者对利用计算机视觉和人工智能实现该过程自动化的兴趣日益浓厚；然而，专家验证数据有限以及形态特征多变，阻碍了基于人工智能的杂草识别模型的发展。为解决这些问题，我们提出了WeedNet，一个能够识别大量杂草物种的全球尺度杂草识别模型。WeedNet是一个端到端的杂草识别流程，采用自监督学习、微调以及增强可信度策略。WeedNet在1,593种杂草上实现了91.02%的准确率，其中41%的物种达到100%准确率。采用微调方法，爱荷华本地WeedNet模型对84种爱荷华杂草实现了97.38%的总体准确率。对种内差异性和种间相似性的测试表明，所采集图像中涵盖所有生长阶段和可区分植物特征的多样性，对驱动模型性能至关重要。全球WeedNet模型作为基础，全球到本地策略能够实现有针对性的微调，以提升区域杂草群落中的性能。对无人机和地面巡游机器人图像进行的额外验证，凸显了WeedNet集成到机器人平台中的潜力。此外，与人工智能集成用于对话式使用，可为农民、研究人员和政府机构在不同景观中提供智能农业和生态保护咨询工具。杂草持续威胁全球作物产量，因此早期准确识别对有效管理至关重要。WeedNet在代表1,593种杂草的1,400万张图像上训练，实现了91%的全球准确率，并通过全球到本地微调，对爱荷华杂草达到97%的准确率。","Nature Communications",89,{"impact":280,"substance":473,"depth":404,"authority":474,"freshness":21,"relevant":22,"comment":475},23,15,"基于1400万图像、覆盖1593种杂草的全球基础模型，全局到局部微调思路清晰，对智慧农业与农业机器人有实质参考价值。",[477],{"name":470,"url":467},[27,28,57,29,479],"杂草识别",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":483},{"candidates":484,"agricultural_evidence":48},[485,489,493,497],{"code":33,"score":294,"supported":48,"title":486,"abstract":487,"tags":488},[],[57,142,58],[28,57],{"code":76,"score":22,"supported":14,"title":490,"abstract":491,"tags":492},[],[],[479],{"code":69,"score":22,"supported":14,"title":494,"abstract":495,"tags":496},[],[],[29],{"code":46,"score":22,"supported":14,"title":498,"abstract":499,"tags":500},[],[],[27],[502,503],"WeedNet 杂草识别","Nature Communications 杂草识别模型","WeedNet杂草识别-4039","10.1038\u002Fs41467-026-78044-4",{"doi":505,"openalex_id":507,"authors":508,"venue":470,"cited_by_count":105,"oa_url":467,"card":556,"direction":392,"ingested_from":113},"W7214939964",[509,512,515,518,521,523,525,528,531,534,536,539,540,542,545,547,550,553,555],{"name":510,"orcid":511},"Yanben Shen","https:\u002F\u002Forcid.org\u002F0000-0002-2847-3198",{"name":513,"orcid":514},"Timilehin T. Ayanlade","https:\u002F\u002Forcid.org\u002F0000-0003-4792-5337",{"name":516,"orcid":517},"Venkata Naresh Boddepalli","https:\u002F\u002Forcid.org\u002F0009-0008-0216-9156",{"name":519,"orcid":520},"Mojdeh Saadati","https:\u002F\u002Forcid.org\u002F0000-0002-9092-8464",{"name":522,"orcid":9},"Ashlyn Rairdin",{"name":524,"orcid":9},"Zi Kang Deng",{"name":526,"orcid":527},"Muhammad Arshad","https:\u002F\u002Forcid.org\u002F0000-0003-1574-7097",{"name":529,"orcid":530},"Baskar Ganapathysubramanian","https:\u002F\u002Forcid.org\u002F0000-0003-4042-066X",{"name":532,"orcid":533},"Aditya Balu","https:\u002F\u002Forcid.org\u002F0000-0003-2005-2548",{"name":535,"orcid":9},"Daren Mueller",{"name":537,"orcid":538},"Asheesh Kumar Singh","https:\u002F\u002Forcid.org\u002F0000-0002-7522-037X",{"name":537,"orcid":538},{"name":541,"orcid":9},"Wesley Everman",{"name":543,"orcid":544},"Nirav Merchant","https:\u002F\u002Forcid.org\u002F0000-0002-1988-8180",{"name":529,"orcid":546},"https:\u002F\u002Forcid.org\u002F0000-0002-8931-4852",{"name":548,"orcid":549},"Meaghan J. B. Anderson","https:\u002F\u002Forcid.org\u002F0009-0001-5904-1574",{"name":551,"orcid":552},"Soumik Sarkar","https:\u002F\u002Forcid.org\u002F0000-0002-6775-9199",{"name":554,"orcid":9},"Arti Singh",{"name":554,"orcid":9},{"tldr":557,"method":558,"finding":559,"direction":392,"opportunity":560},"提出WeedNet基础模型，实现全球杂草物种识别与区域微调。","自监督学习、微调与可信策略，基于1400万张图像训练。","全球1593种杂草识别准确率91%，爱荷华84种微调后达97%。","可探索跨区域杂草基础模型微调与无人机\u002F机器人平台集成。","2026-10-02T23:30:41.979601Z"]