[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3132":3,"related-3132":66},{"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":23,"tags":25,"search_phrases":31,"slug":34,"view_count":35,"doi":36,"paper":37,"created_at":65},3132,"Vision-guided real-time hoof spraying robot for lameness prevention in rotary milking parlors","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112445","Vision-guided real-time hoof spraying robot for lameness prevention in rotary milking parlors。Computers and Electronics in Agriculture","旋转式挤奶厅中用于预防跛行的视觉引导实时蹄部喷药机器人。《计算机与电子农业》",null,"Computers and Electronics in Agriculture","2026-09-21T00:00:00Z","论文",10,false,81,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,14,9,1,"核心期刊发表的视觉引导蹄部喷药机器人研究，方法新颖、面向奶牛跛行防控，属智慧养殖细分领域实质进展。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业机器人","奶牛养殖","机器视觉","蹄病防控",[32,33],"蹄部喷药机器人 旋转挤奶厅","机器视觉 奶牛蹄病","蹄部喷药机器人旋转挤奶厅-3132",0,"10.1016\u002Fj.compag.2026.112445",{"doi":36,"openalex_id":38,"authors":39,"venue":10,"cited_by_count":35,"oa_url":9,"card":58,"direction":62,"ingested_from":64},"W7213890211",[40,43,46,48,50,52,55],{"name":41,"orcid":42},"Sicheng Li","https:\u002F\u002Forcid.org\u002F0000-0003-1174-3670",{"name":44,"orcid":45},"Wenshuai Ye","https:\u002F\u002Forcid.org\u002F0009-0006-8008-1788",{"name":47,"orcid":9},"Cifu Xu",{"name":49,"orcid":9},"Arshed Ahmed",{"name":51,"orcid":9},"Xiaowen Liu",{"name":53,"orcid":54},"Kun Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-5166-2245",{"name":56,"orcid":57},"Gang Liu","https:\u002F\u002Forcid.org\u002F0000-0002-1004-1653",{"tldr":59,"method":60,"finding":61,"direction":62,"opportunity":63},"研发视觉引导的实时蹄部喷药机器人，用于转盘式挤奶厅预防奶牛跛行。","机器视觉识别蹄部，结合机器人实时喷药控制。","视觉引导机器人可在转盘挤奶厅实时精准喷药，预防跛行。","智慧农业 \u002F 农业物联网","可延伸至多目标识别、动态跟踪与药量自适应优化，提升复杂场景鲁棒性。","openalex","2026-09-22T23:30:02.231112Z",{"total":67,"page":21,"page_size":67,"items":68},6,[69,100,132,158,184,219],{"id":70,"title":71,"url":72,"summary":73,"summary_zh":9,"content":9,"source_name":74,"source_url":9,"published_at":75,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":76,"score_detail":77,"sources":80,"tags":82,"search_phrases":86,"slug":89,"view_count":35,"doi":9,"paper":90,"created_at":99},3253,"Visuomotor Robotic Pruning in Planar Orchills Using Hybrid Reinforcement Learning（基于混合强化学习的平面果园视觉运动机器人修剪）","https:\u002F\u002Farxivtldr.org\u002Fabs\u002F2609.24906","arXiv发表研究：休眠期树木修剪是劳动密集型但对维持现代高产果园至关重要的工作。本文针对现代平面树形训练系统（V型棚架苹果、UFO樱桃）的修剪任务，提出端到端管线学习闭环视觉运动控制器。控制器完全使用仿真和合成生成数据进行训练，以零样本方式部署到真实果园。管线包括平面果园树网格的合成生成、基于物理的果园仿真器构建、通过运动规划自动收集成功修剪轨迹，以及结合离线演示与在线仿真推出相结合的新型混合强化学习算法。控制器使用腕部相机的光流输入，避免完整三维重建需求，连续引导切割器穿越杂乱分支环境到指定切割点并在真实果园38次物理试验中展示零样本仿真到真实迁移。在V-Trellis苹果上达到49.9%成功率，UFO樱桃上46.0%。","arXiv (Abhinav Jain, Cindy Grimm, Stefan Lee)","2026-09-20T00:00:00Z",80,{"impact":17,"substance":18,"depth":17,"authority":78,"freshness":20,"relevant":21,"comment":79},13,"仿真到真实零样本迁移的果园修剪机器人研究，方法新颖、数据扎实，对智慧果园机械化有参考价值。",[81],{"name":74,"url":72},[26,83,27,84,85],"农业人工智能","强化学习","果园管理",[87,88],"V-Trellis 苹果 机器人修剪","UFO 樱桃 零样本迁移","V-Trellis苹果机器人修剪-3253",{"doi":9,"openalex_id":9,"authors":91,"venue":9,"cited_by_count":35,"oa_url":9,"card":92,"direction":96,"ingested_from":98},[],{"tldr":93,"method":94,"finding":95,"direction":96,"opportunity":97},"提出端到端视觉运动控制器，用仿真合成数据训练，零样本迁移到真实果园完成修剪。","合成数据生成、物理仿真器、运动规划收集轨迹、混合强化学习、腕部相机光流。","真实果园38次试验零样本迁移成功，苹果49.9%、樱桃46.0%成功率。","农业人工智能与决策模型","可探索多季节、多树种泛化及真实数据微调，提升复杂冠层下的鲁棒性。","agent","2026-09-23T00:04:33.854148Z",{"id":101,"title":102,"url":103,"summary":104,"summary_zh":9,"content":9,"source_name":105,"source_url":9,"published_at":106,"category":12,"cover_url":9,"hotness":13,"is_selected":107,"score":108,"score_detail":109,"sources":115,"tags":117,"search_phrases":120,"slug":123,"view_count":35,"doi":9,"paper":124,"created_at":131},3252,"具身智能农业机器人关键技术与发展趋势——上海大学苗中华等\"感知-决策-模拟-进化-诊断\"五位一体研究框架","http:\u002F\u002Fwww.qikanzj.com\u002Fhek\u002Fnyjxxb\u002Fmulu\u002F455891.html","智慧农业(中英文)期刊发表上海大学苗中华、朱子煜、张伟、薛振锋、孙腾、张异凡、谢涛、何创新、李楠，山东农业大学苑进，北京市农林科学院赵春江，上海交通大学刘成良团队论文：全球农业智能化转型背景下，传统农业机器人面临非结构化环境、作业对象不确定性及控制参数时变等技术瓶颈，导致农业机器人实用效果差，产业化落地困难。具身智能作为实现通用人工智能的关键路径，为突破上述瓶颈提供了新范式。本文系统阐述具身智能理论驱动的农业机器人技术体系与发展路径，创新性构建\"感知-决策-模拟-进化-诊断\"五位一体研究框架。具身感知聚焦开放环境场景理解、作业目标主动感知及多模态融合感知；具身决策涵盖端到端导航、大模型驱动的机械臂操作及多机协同算法；具身模拟着力于高保真场景重建、生成及虚实迁移技术；具身进化整合无监督学习、强化学习及模仿学习机制；具身诊断构建作业状态监测与质量评估体系。","智慧农业(中英文)·上海大学","2026-09-22T00:00:00Z",true,91,{"impact":110,"substance":111,"depth":112,"authority":113,"freshness":13,"relevant":21,"comment":114},24,23,19,15,"核心期刊论文，提出具身智能驱动的农业机器人五位一体框架，方法体系新颖、团队权威，对智慧农业技术路线有较强参考价值。",[116],{"name":105,"url":103},[26,83,27,118,119],"具身智能","多模态感知",[121,122],"上海大学 苗中华 农业机器人","具身智能 农业机器人 五位一体","上海大学苗中华农业机器人-3252",{"doi":9,"openalex_id":9,"authors":125,"venue":9,"cited_by_count":35,"oa_url":9,"card":126,"direction":96,"ingested_from":98},[],{"tldr":127,"method":128,"finding":129,"direction":96,"opportunity":130},"系统阐述具身智能驱动的农业机器人技术体系，提出五位一体研究框架。","构建'感知-决策-模拟-进化-诊断'五位一体框架，综述关键技术。","具身智能可突破非结构化环境等瓶颈，为农业机器人提供新范式。","可探索具身智能在农业非结构化场景的落地验证与虚实迁移效率提升。","2026-09-23T00:04:33.744630Z",{"id":133,"title":134,"url":135,"summary":136,"summary_zh":9,"content":9,"source_name":137,"source_url":9,"published_at":106,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":138,"score_detail":139,"sources":141,"tags":143,"search_phrases":146,"slug":149,"view_count":35,"doi":9,"paper":150,"created_at":157},3251,"农机化研究2026(8)：基于MobileNetV4-DSFPN的芍药田间机器人视觉导航——安徽理工+皖西学院+中科院合肥物质科学研究院 mIoU 94.11% FPS 23.1","http:\u002F\u002Fwww.qikanvip.com\u002Fqkml\u002F166165.html","农机化研究2026年第8期发表安徽理工大学徐善永、程军辉、张俊卿，皖西学院邢雪景，中国科学院合肥物质科学研究院联合论文：精准分割田间可行驶区域并实时提取导航线是实现农业机器人在田间自主作业的关键环节。针对芍药田间背景复杂、现有语义模型计算复杂度高、实时性差等问题，提出轻量化的MobileNetV4-DSFPN语义分割模型，采用改进MobileNetV4作为高效编码器；解码器部分构建基于深度可分离卷积的轻量级特征金字塔网络（DSFPN）。在芍药田间路径数据集上类别平均像素准确率（mPA）和平均交并比（mIoU）分别达到97.16%、94.11%；导航线的平均横向偏差为0.231像素，平均角度偏差为0.842°；车载计算机上平均推理速度达到23.1 FPS。","农机化研究",78,{"impact":113,"substance":18,"depth":17,"authority":78,"freshness":13,"relevant":21,"comment":140},"核心期刊论文，提出轻量化语义分割模型并给出mIoU 94.11%、23.1 FPS等实测数据，方法新颖、结论可靠，对农业机器人视觉导航有实质参考价值。",[142],{"name":137,"url":135},[26,83,27,144,145],"芍药","视觉导航",[147,148],"安徽理工大学 芍药 田间机器人","MobileNetV4 DSFPN 语义分割","安徽理工大学芍药田间机器人-3251",{"doi":9,"openalex_id":9,"authors":151,"venue":9,"cited_by_count":35,"oa_url":9,"card":152,"direction":62,"ingested_from":98},[],{"tldr":153,"method":154,"finding":155,"direction":62,"opportunity":156},"提出轻量MobileNetV4-DSFPN分割芍药田间可行驶区域并提取导航线。","改进MobileNetV4编码器+深度可分离卷积特征金字塔，芍药田间路径数据集。","mIoU达94.11%，横向偏差0.231像素，车载推理23.1 FPS。","可探索轻量分割模型在复杂田间多作物、多光照下的泛化与边缘部署优化。","2026-09-23T00:04:33.588064Z",{"id":159,"title":160,"url":161,"summary":162,"summary_zh":9,"content":9,"source_name":163,"source_url":9,"published_at":106,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":164,"score_detail":165,"sources":167,"tags":169,"search_phrases":172,"slug":175,"view_count":35,"doi":9,"paper":176,"created_at":183},3249,"设施番茄采摘机器人识别定位与采摘方法研究——江苏大学雷志龙等 基于改进YOLO v5-HSV融合算法识别准确率95.01%","http:\u002F\u002Fwww.qikanzj.com\u002Fhek\u002Fnyjxxb\u002Fmulu\u002F455758.html","智慧农业(中英文)期刊发表江苏大学雷志龙、刘畅、王权团队研究：针对设施单果番茄采摘需求，设计一款设施番茄智能采摘平台，主要由升降机构、采摘机构、识别与定位系统等部分组成。平台整体结构由低压一体化伺服滚珠丝杠副升降机构、六轴协作机械臂和力控末端执行器组成。基于改进YOLO v5-HSV融合算法来识别检测，通过对H分量进行图像阈值分割，提高对成熟目标果实识别的准确率，有效排除未成熟番茄和枝叶背景的干扰；通过眼在手外的标定方法，使用ZED双目相机进行定位。搭建的设施番茄采摘机样机平台在现场采摘试验中识别准确率达到95.01%，采摘成功率为87.96%，单果平均采摘时间为14.56s。","智慧农业(中英文)·江苏大学",82,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":13,"relevant":21,"comment":166},"核心期刊论文，方法有改进、数据完整，识别准确率与采摘成功率等指标明确，对设施农业智能装备研发有参考价值。",[168],{"name":163,"url":161},[26,83,170,29,171],"采摘机器人","设施番茄",[173,174],"江苏大学 设施番茄 采摘机器人","YOLO v5 番茄 识别定位","江苏大学设施番茄采摘机器人-3249",{"doi":9,"openalex_id":9,"authors":177,"venue":9,"cited_by_count":35,"oa_url":9,"card":178,"direction":96,"ingested_from":98},[],{"tldr":179,"method":180,"finding":181,"direction":96,"opportunity":182},"设计设施番茄智能采摘平台，融合改进YOLO v5与HSV实现识别定位与采摘。","改进YOLO v5-HSV融合算法、ZED双目相机眼在手外标定、六轴机械臂力控末","识别准确率95.01%，采摘成功率87.96%，单果平均采摘时间14.56秒。","可探索多果簇、遮挡与弱光环境下识别定位鲁棒性，并优化采摘效率与末端力控。","2026-09-23T00:04:33.401768Z",{"id":185,"title":186,"url":187,"summary":188,"summary_zh":189,"content":9,"source_name":190,"source_url":187,"published_at":106,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":191,"score_detail":192,"sources":197,"tags":199,"search_phrases":202,"slug":205,"view_count":35,"doi":206,"paper":207,"created_at":218},3194,"Optimization and Analysis of Agricultural Robot Drive Systems","https:\u002F\u002Fdoi.org\u002F10.54254\u002F2753-8818\u002F2026.37178","This study takes the agricultural robot drive system as the research object and carries out optimization research from two dimensions: mechanical structure and intelligent control. At the mechanical level, redundant degrees of freedom are eliminated through topological analysis of mechanism freedom, a 'short-chain direct-drive' transmission scheme is introduced to reduce mechanical losses, and finite element topology optimization is combined to achieve lightweight design of key components. At the control level, artificial intelligence is introduced to establish a perception system based on convolutional neural networks (CNN) and multi-source information fusion, enabling accurate recognition and prediction of complex terrain. A Back Propagation (BP) neural network Proportion Integration Differentiation (PID) control strategy based on the Dung beetle Optimization (DBO)algorithm is proposed, which effectively addresses the shortcomings of traditional algorithms, such as slow convergence and large overshoot. Meanwhile, model predictive control and an improved soft actor-critic reinforcement learning algorithm are integrated to achieve online adaptive regulation of drive parameters and global optimal control to a considerable extent. The optimized drive system effectively improves the working performance and environmental adaptability of agricultural robots in complex terrain and provides new theoretical and technical ideas for the development of intelligent agricultural machinery.","本研究以农业机器人驱动系统为研究对象，从机械结构与智能控制两个维度开展优化研究。在机械层面，通过机构自由度拓扑分析去除冗余自由度，引入“短链直驱”传动方案以降低机械损耗，并结合有限元拓扑优化实现关键零部件的轻量化设计。在控制层面，引入人工智能，建立基于卷积神经网络（CNN）与多源信息融合的感知系统，实现对复杂地形的准确识别与预测；提出基于蜣螂优化（DBO）算法的BP神经网络PID控制策略，有效改善传统算法收敛慢、超调大等不足；同时融合模型预测控制与改进的柔性演员-评论家强化学习算法，实现驱动参数的在线自适应调节及较大程度上的全局最优控制。优化后的驱动系统有效提升了农业机器人在复杂地形下的作业性能与环境适应性，为智能农业机械的发展提供了新的理论与技术思路。","Theoretical and Natural Science",69,{"impact":193,"substance":194,"depth":195,"authority":13,"freshness":13,"relevant":21,"comment":196},12,20,17,"论文提出短链直驱与DBO-BP-PID等控制优化方案，方法新颖但偏理论，产业影响有限。",[198],{"name":190,"url":187},[26,83,27,200,201],"智能农机","驱动系统",[203,204],"农业机器人 驱动系统 优化","DBO BP神经网络 PID控制","农业机器人驱动系统优化-3194","10.54254\u002F2753-8818\u002F2026.37178",{"doi":206,"openalex_id":208,"authors":209,"venue":190,"cited_by_count":35,"oa_url":187,"card":213,"direction":96,"ingested_from":64},"W7213976318",[210],{"name":211,"orcid":212},"Ziyuan Ma","https:\u002F\u002Forcid.org\u002F0000-0002-7931-3258",{"tldr":214,"method":215,"finding":216,"direction":96,"opportunity":217},"从机械结构与智能控制两方面优化农业机器人驱动系统，提升复杂地形适应性与作业性能。","机构自由度拓扑分析、有限元拓扑优化、CNN多源融合感知、DBO-BP-PID与强","优化驱动系统有效提升农业机器人在复杂地形下的作业性能与环境适应性。","可探索轻量化驱动与在线强化学习控制在真实农田多机协同中的泛化性与能耗权衡。","2026-09-22T23:30:39.723894Z",{"id":220,"title":221,"url":222,"summary":223,"summary_zh":9,"content":9,"source_name":224,"source_url":9,"published_at":106,"category":225,"cover_url":9,"hotness":13,"is_selected":14,"score":76,"score_detail":226,"sources":229,"tags":231,"search_phrases":235,"slug":238,"view_count":35,"doi":9,"paper":9,"created_at":239},3095,"从这扇窗,看见中国农业的底气——中国农业科学院第八届农科开放日观察","https:\u002F\u002Fszb.farmer.com.cn\u002Fnmrb\u002Fhtml\u002F2026\u002F20260922\u002F20260922_1\u002Fnmrb_20260922_13411_1_2102145214697279506.html","9-22 农民日报头版刊登对中国农业科学院第八届农科开放日的整版观察。9-19 启幕的开放日汇聚作物科学研究所、南京农业机械化研究所、植物保护研究所、蜜蜂研究所等所级展位：作物所野生稻\u002F地方杂粮种子标本扫码可查每份种质来历；南京农机化所多足转运机器人面向丘陵山地作业、可横移\u002F原地转向、4 条仿生机械腿遇障碍物灵活抬落、稳定背负 100 公斤农资与果品破解山区果品\"种得出、运不下\"难题；植保所无人机模拟操作台前排起小长队，让孩子们上手操控摇杆体验飞防作业；蜜蜂所无刺蜂\u002F熊蜂差异化授粉技术破解人工授粉费时费力、果品品质不稳难题。","农民日报","报道",{"impact":18,"substance":17,"depth":227,"authority":19,"freshness":13,"relevant":21,"comment":228},16,"全国性农科开放日观察，涵盖种质资源、丘陵山地农机、飞防与授粉技术，信息增量与时效性俱佳，值得进入每日精选。",[230],{"name":224,"url":222},[26,27,232,233,234],"种质资源","蜜蜂授粉","植保无人机",[236,237],"中国农科院 农科开放日","南京农机化所 多足转运机器人","中国农科院农科开放日-3095","2026-09-22T00:05:33.364777Z"]