[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-955":3,"related-955":96},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":21,"tags":23,"primary_topic":30,"secondary_topics":36,"classification":43,"search_phrases":90,"slug":93,"view_count":94,"doi":8,"paper":8,"created_at":95},955,"重庆梁平：水稻收割实现「无人化」 「渝东粮仓」智能农机成新帮手","https:\u002F\u002Fwww.farmer.com.cn\u002F2026\u002F08\u002F25\u002F991026753.html","秋收时节，重庆市梁平区运用无人驾驶收割机收割水稻。农技人员通过北斗定位和5G技术，设定参数自主规划最优路线，无人驾驶收割机便可在农田中精准完成水稻收割，既降低劳动强度，让收割更加精准、更加智能，又提高了生产效率。近年来在「渝东粮仓」梁平区，无人旋耕机、无人插秧机、无人植保机、无人驾驶收割机等新型智能化设备纷纷亮相，成为农业生产的好帮手，提高了农业现代化技术装备水平和农业综合生产能力，助力乡村全面振兴。",null,"秋收时节，重庆市梁平区运用无人驾驶收割机收割水稻。农技人员通过北斗定位和5G技术，设定参数自主规划最优路线，无人驾驶收割机便可在农田中精准完成水稻收割，既降低劳动强度，让收割更加精准、更加智能，又提高了生产效率。\n\n近年来，在“渝东粮仓”重庆市梁平区，无人旋耕机、无人插秧机、无人植保机、无人驾驶收割机等新型智能化设备纷纷亮相田间地头，成为农业生产的好帮手，提高了农业机械化水平和农业综合生产能力，助力乡村全面振兴。","中国农网 2026-08-25","2026-08-25T07:36:11Z","报道",10,false,53,{"impact":17,"substance":17,"depth":13,"authority":13,"freshness":18,"relevant":19,"comment":20},12,9,1,"地方农业智能化应用报道，有具体案例但缺乏深度分析，信源为行业媒体，时效性好。",[22],{"name":10,"url":6},[24,25,26,27,28,29],"智能农机","北斗","重庆梁平","无人收割机","5G","渝东粮仓",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"A1","rice","水稻","\u002Ftopic\u002Ffield-crops\u002Frice","A",[37],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},"F5","machinery","农机装备与机械化","\u002Ftopic\u002Finputs-equipment\u002Fmachinery","F",{"status":44,"locked":14,"version":45,"method":46,"evidence":47},"classified","2026-10-22.2","rules",{"candidates":48,"agricultural_evidence":50},[49,56,61,68,74,80,85],{"code":38,"score":17,"supported":50,"title":51,"abstract":53,"tags":55},true,[52],"农机",[54],"收割机",[24],{"code":31,"score":57,"supported":50,"title":58,"abstract":59,"tags":60},11,[33],[33],[],{"code":62,"score":63,"supported":50,"title":64,"abstract":65,"tags":67},"F4",3,[],[66],"植保",[],{"code":69,"score":63,"supported":50,"title":70,"abstract":71,"tags":73},"J2",[],[72],"农业现代化",[],{"code":75,"score":63,"supported":50,"title":76,"abstract":77,"tags":79},"J4",[],[78],"秋收",[],{"code":81,"score":19,"supported":14,"title":82,"abstract":83,"tags":84},"F6",[],[],[27],{"code":86,"score":19,"supported":14,"title":87,"abstract":88,"tags":89},"I5",[],[],[28],[91,92],"无人收割机 智能农机 渝东粮仓 重庆梁平","无人收割机 智能农机","无人收割机智能农机渝东粮仓重庆梁平-955",2,"2026-08-26T00:09:29.784138Z",{"total":97,"page":19,"page_size":97,"items":98},6,[99,163,243,293,354,410],{"id":100,"title":101,"url":102,"summary":103,"summary_zh":8,"content":104,"source_name":105,"source_url":8,"published_at":106,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":107,"score_detail":108,"sources":113,"tags":115,"primary_topic":119,"secondary_topics":120,"classification":126,"search_phrases":158,"slug":161,"view_count":19,"doi":8,"paper":8,"created_at":162},3948,"\"外媒看中国\"活动走进黑龙江 看中国农业\"智\"变——稻田一眼望不到边，无人收割机震撼外媒记者","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7691148215814472238","9月28日至30日，来自美国、白俄罗斯、哈萨克斯坦、古巴、新加坡、越南等国的记者走进中国粮食产量第一大省——黑龙江，深入秋收现场、农机企业和粮食加工车间。3台无人驾驶收割机在稻田里收割水稻，稻粒入仓，稻秆粉碎后抛洒还田；媒体团在北大荒智慧农业农机中心观摩，佳木斯骥驰拖拉机制造有限公司的产品出口俄罗斯、非洲等地。本次活动是国新办已先后组织的第五场\"外媒看中国\"系列主题采访活动。","## “外媒看中国”活动走进黑龙江 看中国农业“智”变\n\n2026-09-30 10:23·[中国新闻网](https:\u002F\u002Fwww.toutiao.com\u002Fc\u002Fuser\u002Ftoken\u002FMS4wLjABAAAAvOdgu_VhRab2uUfrYPedveCA9KSEdd4AfYLyl9vkh2s\u002F?source=tuwen_detail)\n\n中新网佳木斯9月30日电 (记者 王妮娜)“稻田一眼望不到边，看不到人，只有无人驾驶收割机在自动收割水稻，很震撼。”29日，新加坡《海峡时报》记者游润恬在富锦市万亩水稻科技示范园的稻田边说。\n\n这是“外媒看中国”系列主题采访活动的第五场。9月28日至30日，来自美国、白俄罗斯、哈萨克斯坦、古巴、新加坡、越南等国的记者走进中国粮食产量第一大省——黑龙江，深入秋收现场、农机企业和粮食加工车间，采访粮食生产和农业现代化。\n\n![Image 1](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-axegupay5k\u002F1a884f5ca7e54ce5a0d94b780ad63c5f~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1791546991&x-signature=Dk7CYAqybcg0oajeQMHjYU364Zk%3D)\n古巴拉丁美洲通讯社记者迭斯在佳木斯骥驰拖拉机制造有限公司用手机拍摄农机。王妮娜 摄\n\n28日举行的中外记者见面会介绍了黑龙江农业规模、智能农业发展等情况。随后，媒体团到哈尔滨、佳木斯等地，实地走访富锦市万亩水稻科技示范园、北大荒智慧农业农机中心等多个机构和企业，观摩粮食深加工、农机制造、寒地水稻种植和智能农业，感受黑土地智慧农业成果。\n\n![Image 2](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-tjoges91tu\u002Fb9a9d73cf0a802c81d4dca9051ba9d6a~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1791546991&x-signature=tP2wGGXZIYqnwLzg%2BuRVPz%2BuSaI%3D)\n媒体团在黑龙江惠达科技股份有限公司了解智能农业机械。王妮娜 摄\n\n29日，媒体团来到富锦市万亩水稻科技示范园。该示范园地处世界三大黑土带之一的中国三江平原。3台无人驾驶收割机在稻田里收割水稻，稻粒入仓，稻秆粉碎后抛洒还田。该示范园内的水田现代农机专业合作社跳出传统“小农”模式，实现全程机械化、集约化、智能化、数字化作业，令媒体团赞叹。\n\n“小时候读过中国古诗‘谁知盘中餐，粒粒皆辛苦’，这一路走下来，看到中国用科技让农业智能化。”游润恬感叹，智能农业让种地变得很轻松、很酷。\n\n![Image 3](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-tjoges91tu\u002Fc25a753320b430649fb2e6e97c76a111~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1791546991&x-signature=iutx3ph%2BbIGHgP%2BhG%2B44y%2BWYWr8%3D)\n在北大荒智慧农业农机中心，无人驾驶收割机在收割水稻。王妮娜 摄\n\n佳木斯骥驰拖拉机制造有限公司是一家智能农机研发和生产企业，产品出口俄罗斯、非洲等地。在该公司，古巴拉丁美洲通讯社记者迭斯爬进3米高的大马力拖拉机驾驶室，拍下许多视频。她说：“我把这些照片和视频带回古巴，我们当地人会对这些先进农机很感兴趣。”她还说，古巴当地农民还在用牲畜耕作，引入先进农机还需要配套条件和有专业知识的农民。\n\n今年4月起，国务院新闻办公室已先后组织五场“外媒看中国”系列主题采访活动，介绍有关地方贯彻落实“十五五”规划的生动实践。本次黑龙江之行旨在让多国媒体记者实地感受中国农业发展。(完)","今日头条·中国新闻网·2026年09月30日","2026-09-30T02:23:00Z",64,{"impact":109,"substance":110,"depth":111,"authority":111,"freshness":97,"relevant":19,"comment":112},18,14,13,"央媒组织的多国外媒实地采访，以无人驾驶收割机等场景展现黑龙江智慧农业与农机装备进展，有画面感和对外传播价值，但属综合报道、信息增量有限。",[114],{"name":105,"url":102},[116,24,117,72,118],"智慧农业","黑龙江","无人驾驶农机",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[121,122],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"code":81,"slug":123,"name":124,"path":125,"parent_code":42},"agricultural-robots","机器人与无人农场","\u002Ftopic\u002Finputs-equipment\u002Fagricultural-robots",{"status":44,"locked":14,"version":45,"method":46,"evidence":127},{"candidates":128,"agricultural_evidence":50},[129,134,139,144,150,154],{"code":38,"score":130,"supported":50,"title":131,"abstract":132,"tags":133},15,[54],[52,54],[24],{"code":31,"score":110,"supported":50,"title":135,"abstract":137,"tags":138},[136],"稻田",[33,136],[],{"code":81,"score":140,"supported":50,"title":141,"abstract":142,"tags":143},8,[27],[],[],{"code":145,"score":146,"supported":50,"title":147,"abstract":148,"tags":149},"I1",4,[],[116],[116],{"code":75,"score":63,"supported":50,"title":151,"abstract":152,"tags":153},[],[78],[],{"code":69,"score":19,"supported":14,"title":155,"abstract":156,"tags":157},[],[],[72],[159,160],"黑龙江 富锦 无人驾驶收割机","北大荒 智慧农业农机中心","黑龙江富锦无人驾驶收割机-3948","2026-10-02T11:53:12.391575Z",{"id":164,"title":165,"url":166,"summary":167,"summary_zh":168,"content":8,"source_name":169,"source_url":166,"published_at":170,"category":171,"cover_url":8,"hotness":13,"is_selected":14,"score":172,"score_detail":173,"sources":176,"tags":178,"primary_topic":183,"secondary_topics":184,"classification":186,"search_phrases":203,"slug":206,"view_count":19,"doi":207,"paper":208,"created_at":242},3974,"A real-time estimation method for wheeled agricultural machinery slip parameters in paddy fields based on the prediction-residual approach","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112478","A real-time estimation method for wheeled agricultural machinery slip parameters in paddy fields based on the prediction-residual approach。Computers and Electronics in Agriculture","基于预测残差法的水稻田轮式农业机械滑转参数实时估计方法。Computers and Electronics in Agriculture","Computers and Electronics in Agriculture","2026-10-01T00:00:00Z","论文",69,{"impact":17,"substance":109,"depth":174,"authority":110,"freshness":18,"relevant":19,"comment":175},16,"提出基于预测残差的水田轮式农机滑移参数实时估计方法，方法新颖且面向实际作业场景，但属细分技术论文，产业影响有限。",[177],{"name":169,"url":166},[116,179,180,181,182],"精准农业","农业机械","水稻生产","导航定位",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[185],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":187},{"candidates":188,"agricultural_evidence":50},[189,194,199],{"code":31,"score":109,"supported":50,"title":190,"abstract":192,"tags":193},[191],"paddy",[33,136,191],[181],{"code":38,"score":130,"supported":50,"title":195,"abstract":197,"tags":198},[196],"agricultural machinery",[180,196],[180],{"code":145,"score":94,"supported":14,"title":200,"abstract":201,"tags":202},[],[],[116,179],[204,205],"水田 农业机械 滑移率 实时估计","预测残差 滑转参数 估计","水田农业机械滑移率实时估计-3974","10.1016\u002Fj.compag.2026.112478",{"doi":207,"openalex_id":209,"authors":210,"venue":169,"cited_by_count":234,"oa_url":8,"card":235,"direction":239,"ingested_from":241},"W7215087308",[211,214,217,219,221,223,226,228,231],{"name":212,"orcid":213},"Dawen Feng","https:\u002F\u002Forcid.org\u002F0000-0002-1307-8902",{"name":215,"orcid":216},"Boyang Wang","https:\u002F\u002Forcid.org\u002F0000-0003-3613-8792",{"name":218,"orcid":8},"Jing He",{"name":220,"orcid":8},"Yuqi Chen",{"name":222,"orcid":8},"Zhongxian Man",{"name":224,"orcid":225},"Jie He","https:\u002F\u002Forcid.org\u002F0000-0003-2134-0998",{"name":227,"orcid":8},"Zhaodi Liu",{"name":229,"orcid":230},"Gaolong Chen","https:\u002F\u002Forcid.org\u002F0000-0002-7415-0867",{"name":232,"orcid":233},"Lian Hu","https:\u002F\u002Forcid.org\u002F0000-0002-4875-7868",0,{"tldr":236,"method":237,"finding":238,"direction":239,"opportunity":240},"提出基于预测-残差法的轮式农机水田滑移参数实时估计方法。","预测-残差法，结合农机运动学模型与实时传感数据估计滑移参数。","该方法能在水田复杂环境下实时准确估计农机滑移参数。","智慧农业 \u002F 农业物联网","可探索多源传感融合与深度学习提升水田滑移估计鲁棒性，并迁移至其他松软地面农机。","openalex","2026-10-02T23:30:02.471920Z",{"id":244,"title":245,"url":246,"summary":247,"summary_zh":8,"content":8,"source_name":248,"source_url":246,"published_at":249,"category":171,"cover_url":8,"hotness":13,"is_selected":14,"score":250,"score_detail":251,"sources":253,"tags":255,"primary_topic":260,"secondary_topics":261,"classification":263,"search_phrases":278,"slug":281,"view_count":94,"doi":282,"paper":283,"created_at":292},3879,"Utilization and Effects of Farm Management Data and Smart Agricultural Machinery on Labor Time in Large-Scale Paddy Farming","https:\u002F\u002Fdoi.org\u002F10.3173\u002Fair.35.123","Utilization and Effects of Farm Management Data and Smart Agricultural Machinery on Labor Time in Large-Scale Paddy Farming。Agricultural Information Research","Agricultural Information Research","2026-09-30T00:00:00Z",68,{"impact":17,"substance":109,"depth":174,"authority":111,"freshness":18,"relevant":19,"comment":252},"核心期刊论文，聚焦大规模水稻种植中农场管理数据与智能农机对劳动时间的影响，方法数据扎实但属细分领域研究，公共影响有限。",[254],{"name":248,"url":246},[116,256,257,258,259],"农业信息化","水稻种植","农机作业","农场管理数据",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[262],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":264},{"candidates":265,"agricultural_evidence":50},[266,270,274],{"code":31,"score":17,"supported":50,"title":267,"abstract":268,"tags":269},[191],[191],[257],{"code":38,"score":57,"supported":50,"title":271,"abstract":272,"tags":273},[196],[196],[],{"code":145,"score":94,"supported":14,"title":275,"abstract":276,"tags":277},[],[],[256,116],[279,280],"Agricultural Information Research 水稻 智能农机","农场管理数据 农业信息化 农机作业 智慧农业","AgriculturalInformationResearch水稻智能农机-3879","10.3173\u002Fair.35.123",{"doi":282,"openalex_id":284,"authors":285,"venue":248,"cited_by_count":234,"oa_url":246,"card":8,"direction":239,"ingested_from":241},"W7214913919",[286,288,290],{"name":287,"orcid":8},"Yukari SHIMIZU",{"name":289,"orcid":8},"Tetsuya Ishikawa",{"name":291,"orcid":8},"Satoshi Yoshinaga","2026-10-01T23:30:09.347033Z",{"id":294,"title":295,"url":296,"summary":297,"summary_zh":8,"content":8,"source_name":298,"source_url":8,"published_at":299,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":250,"score_detail":300,"sources":303,"tags":305,"primary_topic":310,"secondary_topics":311,"classification":313,"search_phrases":349,"slug":352,"view_count":63,"doi":8,"paper":8,"created_at":353},3649,"科技支撑水稻全程机械化生产 助力百亩示范样板实现高产——个旧蒙自示范片蒙自点平均亩产1048.0公斤","http:\u002F\u002Fnkytest.yaas.org.cn\u002Fview\u002Ffront.article.articleView\u002F74132\u002F43\u002F1049.html","9月11日，云南省作物学会组织并邀请省内外相关专家组成专家组，对云南省农业科学院粮食作物研究所、国家杂交水稻工程技术研究中心高原育繁示范中心等单位在个旧市大屯街道、蒙自市草坝镇实施的'粒两优8022'百亩示范样板开展现场观摩及测产鉴定。测产结果显示：个旧百亩示范样板平均每亩产量达966.8公斤，蒙自百亩示范样板平均每亩产量达1048.0公斤。该示范样板已逐步实现从传统手工移栽向耕、种、管、收全程机械化生产转型，并配套应用无人机施肥和植保作业。","云南省农业科学院 2026-09-13","2026-09-13T00:00:00Z",{"impact":109,"substance":301,"depth":110,"authority":111,"freshness":63,"relevant":19,"comment":302},20,"省级科研机构主导的水稻全程机械化百亩示范测产，数据具体、信源权威，但时效偏旧且属区域性进展，可作为主题聚合素材而非当日精选。",[304],{"name":298,"url":296},[116,306,307,308,309],"种业振兴","高产示范","无人机植保","水稻机械化",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[312],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":314},{"candidates":315,"agricultural_evidence":50},[316,320,325,329,335,340,345],{"code":31,"score":17,"supported":50,"title":317,"abstract":318,"tags":319},[33],[33],[309],{"code":38,"score":57,"supported":50,"title":321,"abstract":323,"tags":324},[322],"机械化",[322],[],{"code":62,"score":146,"supported":50,"title":326,"abstract":327,"tags":328},[],[66],[308],{"code":330,"score":63,"supported":50,"title":331,"abstract":332,"tags":334},"F3",[],[333],"施肥",[],{"code":336,"score":19,"supported":14,"title":337,"abstract":338,"tags":339},"A8",[],[],[307],{"code":341,"score":19,"supported":14,"title":342,"abstract":343,"tags":344},"F1",[],[],[306],{"code":145,"score":19,"supported":14,"title":346,"abstract":347,"tags":348},[],[],[116],[350,351],"粒两优8022 蒙自 测产","云南农科院 水稻 全程机械化","粒两优8022蒙自测产-3649","2026-09-28T00:03:01.223003Z",{"id":355,"title":356,"url":357,"summary":358,"summary_zh":8,"content":8,"source_name":359,"source_url":8,"published_at":360,"category":12,"cover_url":8,"hotness":361,"is_selected":14,"score":362,"score_detail":363,"sources":366,"tags":371,"primary_topic":374,"secondary_topics":375,"classification":377,"search_phrases":405,"slug":408,"view_count":94,"doi":8,"paper":8,"created_at":409},1957,"云南省农科院粮作所精量播种法助推水稻全程机械化 临沧示范片亩产536.53公斤","http:\u002F\u002Fnkytest.yaas.org.cn:8888\u002Fview\u002Ffront.article.articleView\u002F74124\u002F6\u002F1049.html","云南省农业科学院粮食作物研究所栽培生理研究创新团队9月1日在临沧市双江县沙河乡允俸村实施110亩\"云粳37号\"水稻绿色高效机械化生产技术集成示范样板，现场测产验收结果显示示范片平均亩产达536.53千克，较对照增产40.72千克，增幅8.21%，每亩节约生产成本80元，合计节本增效222.50元\u002F亩。示范片采用机械化流水线精量播种，叠盘暗化催芽48小时，运用无人机多光谱遥感技术同步融合卫星影像、地面墒情及气象站实时数据，反演叶面积指数、冠层含水量及氮素营养诊断参数，动态生成肥料处方图。","云南省农业科学院 2026-09-04","2026-09-04T00:00:00Z",25,70,{"impact":109,"substance":301,"depth":130,"authority":17,"freshness":364,"relevant":19,"comment":365},5,"省级农科院主导的水稻机械化示范片测产数据详实，结合无人机遥感与精准施肥，具有技术推广价值，但时效性稍弱。",[367,368],{"name":359,"url":357},{"name":369,"url":370},"云南省农业科学院","https:\u002F\u002Fwww.nongye31.com\u002Fnews\u002Fdetail\u002F2456.html",[116,33,372,322,373],"云南","遥感技术",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[376],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":378},{"candidates":379,"agricultural_evidence":50},[380,384,388,396,401],{"code":31,"score":17,"supported":50,"title":381,"abstract":382,"tags":383},[33],[33],[33],{"code":38,"score":17,"supported":50,"title":385,"abstract":386,"tags":387},[322],[322],[322],{"code":389,"score":390,"supported":50,"title":391,"abstract":392,"tags":395},"I3",7,[],[393,394],"遥感","无人机多光谱",[373],{"code":330,"score":63,"supported":50,"title":397,"abstract":398,"tags":400},[],[399],"肥料",[],{"code":145,"score":19,"supported":14,"title":402,"abstract":403,"tags":404},[],[],[116],[406,407],"智慧农业 遥感技术 机械化 云南","智慧农业 遥感技术","智慧农业遥感技术机械化云南-1957","2026-09-09T00:03:55.921672Z",{"id":411,"title":412,"url":413,"summary":414,"summary_zh":8,"content":415,"source_name":416,"source_url":8,"published_at":417,"category":171,"cover_url":8,"hotness":13,"is_selected":14,"score":107,"score_detail":418,"sources":420,"tags":422,"primary_topic":427,"secondary_topics":428,"classification":430,"search_phrases":447,"slug":450,"view_count":146,"doi":8,"paper":8,"created_at":451},796,"[预印本]自主农业拖拉机:面向精准稻作的集成杂草检测与LiDAR导航系统(原标题:Autonomous Agricultural Tractor: Integrated Weed Detection and LiDAR Navigation for Precision Paddy Farming)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.19004","稻田定点杂草管理相比传统广域喷药可大幅减少除草剂用量,但现场部署受三大挑战制约:冠层下GNSS退化的稳健作物行导航、稻与形态多样化杂草的实时视觉区分、将稻误识为杂草的不可逆错误代价。本研究提出AgriNav,围绕四个ROS耦合模块构建集成自主拖拉机系统:用于稻检测的WeedDet PyTorch重实现、并行轻量级168万参数CNN-FPN变体(带非对称类加权)、通过硬编码置信门否决保护稻类的逆逻辑判别模块,以及融合GNSS\u002FIMU\u002F轮式里程计的6状态恒定速度转向率扩展卡尔曼滤波。主要系统级贡献是LiDAR-相机融合桥,利用导航LiDAR做ROI约束、世界坐标投影、地面平面滤波和双向置信融合,无额外硬件成本。","[View PDF](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2608.19004)[HTML (experimental)](https:\u002F\u002Farxiv.org\u002Fhtml\u002F2608.19004v1)\n\n> Abstract:Site-specific weed management in paddy farming offers substantial reductions in herbicide use over conventional broadcast spraying, but field deployment has been limited by three persistent challenges: robust crop-row navigation under canopy where GNSS degrades, real-time visual discrimination between rice and morphologically diverse weeds, and the asymmetric cost of misclassifying rice as weed, which is irreversible. \n> \n> This paper presents AgriNav, an integrated autonomous tractor system built around four ROS-coupled modules: a custom PyTorch reimplementation of WeedDet for rice detection, a parallel lightweight 1.68M-parameter CNN-FPN variant with asymmetric class weighting, an inverted-logic discrimination module that protects the rice class through a hardcoded confidence-gate veto, and a 6-state constant-velocity-turn-rate Extended Kalman Filter fusing GNSS, IMU, and wheel odometry with three-level outage bridging. Our primary system-level contribution is a four-mechanism LiDAR-camera fusion bridge that uses the navigation LiDAR for region-of-interest constraint, world-coordinate projection, ground-plane filtering, and bidirectional confidence fusion at zero additional hardware cost. \n> \n> Simulation experiments demonstrate continuous position tracking through a 20-second GNSS outage, crop row detection confidence above 0.9 throughout operation, and rice-detection confidences from 0.32 to 0.95 across paddy, aerial, and post-flood imagery. The LiDAR ROI constraint reduces detection inference region by an estimated 30 to 50 percent.\n\nSubjects:Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)\nCite as:[arXiv:2608.19004](https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.19004) [cs.RO]\n(or [arXiv:2608.19004v1](https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.19004v1) [cs.RO] for this version)\n[https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2608.19004](https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2608.19004)\n\narXiv-issued DOI via DataCite (pending registration)\n\n## Submission history\n\nFrom: Sudip Dhakal [[view email](https:\u002F\u002Farxiv.org\u002Fshow-email\u002Ff6fe364c\u002F2608.19004)] \n\n**[v1]** Wed, 19 Aug 2026 15:04:22 UTC (1,887 KB)","arXiv:2608.19004 2026-08-19 [预印本]","2026-08-19T07:04:00Z",{"impact":17,"substance":109,"depth":174,"authority":13,"freshness":140,"relevant":19,"comment":419},"面向精准稻作的自主拖拉机系统，集成杂草检测与LiDAR导航，技术细节丰富，但属预印本且应用场景特定，影响范围有限。",[421],{"name":416,"url":413},[423,424,425,426,136],"预印本","自主拖拉机","LiDAR导航","杂草检测",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[429],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":431},{"candidates":432,"agricultural_evidence":50},[433,437,442],{"code":31,"score":57,"supported":50,"title":434,"abstract":435,"tags":436},[191],[136],[],{"code":38,"score":140,"supported":50,"title":438,"abstract":440,"tags":441},[439],"tractor",[],[],{"code":62,"score":63,"supported":50,"title":443,"abstract":444,"tags":446},[],[445],"除草",[],[448,449],"自主拖拉机 杂草检测 预印本 LiDAR导航","自主拖拉机 杂草检测","自主拖拉机杂草检测预印本LiDAR导航-796","2026-08-21T00:05:57.744668Z"]