[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-844":3,"related-844":59},{"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":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":53,"slug":56,"view_count":57,"doi":8,"paper":8,"created_at":58},844,"MDPI Computation:从研究到部署——自主农业机械路径规划综述及可部署性评估框架(原标题:From Research to Deployment in Autonomous Agricultural Machinery: A Review of Path-Planning Technologies Against a Deployability Assessment Framework)","https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194","Harper Adams University、河南农业大学、华南农业大学、中国农业大学等多机构联合综述:点对点GNSS导航已到达TRL 9(商业部署超百万台),基于视觉的作物行跟随视作物和季节处于TRL 5-7,全农场自主动态重规划处于TRL 3-5。主要障碍是缺乏标准化评估基准、感知模型在不同季节和作物类型的泛化失败、地形和滑移反馈与全局路径规划解耦。研究揭示开放田GNSS导航已商业化成熟,但真正的全农场农业自主仍未解决,因为现有系统在季节、地形、传感条件和操作转换的鲁棒性仍不足。",null,"Logical Operator Operator\n\nSearch Text\n\nSearch Type\n\n_add\\_circle\\_outline_\n\n_remove\\_circle\\_outline_\n\n[![Image 1: computation-logo](https:\u002F\u002Fpub.mdpi-res.com\u002Fimg\u002Fjournals\u002Fcomputation-logo.png?6af9c3b6fcf9f52d)](https:\u002F\u002Fwww.mdpi.com\u002Fjournal\u002Fcomputation)\n\n## Article Menu\n\nFont Type:\n\n_Arial_ _Georgia_ _Verdana_\n\nFont Size:\n\nAa Aa Aa\n\nLine Spacing:\n\n__ __ __\n\nColumn Width:\n\n__ __ __\n\nBackground:\n\nOpen Access Review\n\nby \nSam Wane\n\n 1[![Image 2: ORCID](https:\u002F\u002Fpub.mdpi-res.com\u002Fimg\u002Fdesign\u002Forcid.png?0465bc3812adeb52?1787208668)](https:\u002F\u002Forcid.org\u002F0000-0003-3810-2902), \nRedmond R. Shamshiri\n\n 1,2[](mailto:ramsha@mmmi.sdu.dk)[![Image 3: ORCID](https:\u002F\u002Fpub.mdpi-res.com\u002Fimg\u002Fdesign\u002Forcid.png?0465bc3812adeb52?1787208668)](https:\u002F\u002Forcid.org\u002F0000-0002-5775-9654), \nWei Guo\n\n 3[![Image 4: ORCID](https:\u002F\u002Fpub.mdpi-res.com\u002Fimg\u002Fdesign\u002Forcid.png?0465bc3812adeb52?1787208668)](https:\u002F\u002Forcid.org\u002F0000-0001-8263-0222), \nHaibo Chen\n\n 4 and \nFernando Auat Cheein\n\n 1,*[](mailto:fauat@harper-adams.ac.uk)[![Image 5: ORCID](https:\u002F\u002Fpub.mdpi-res.com\u002Fimg\u002Fdesign\u002Forcid.png?0465bc3812adeb52?1787208668)](https:\u002F\u002Forcid.org\u002F0000-0002-6347-7696)\n\n1\n\nEngineering Department, Harper Adams University, Edgmond, Shropshire, Newport TF10 8NB, UK\n\n2\n\nMaersk Mc-Kinney Møller Institute, University of Southern Denmark (SDU), 5230 Odense, Denmark\n\n3\n\nCollege of Artificial Intelligence, Henan Agricultural University, No. 218 Ping’an Avenue, Zhengdong New District, Zhengzhou 450046, China\n\n4\n\nNational Center for International Collaboration Research on Precision Agricultural Aviation Pesticide Spraying Technology, South China Agricultural University, Guangzhou 510642, China\n\n*\n\nAuthor to whom correspondence should be addressed.\n\nSubmission received: 29 June 2026 \u002F Revised: 31 July 2026 \u002F Accepted: 11 August 2026 \u002F Published: 21 August 2026\n\n## Abstract\n\nGlobal labour shortages in the agricultural sector, combined with diminishing arable land and a growing population, are driving investment in autonomous agricultural machinery. Autonomous systems that can navigate crop environments and perform planting, treatment, and harvesting alongside humans are required, but the gap between published research and commercially deployed systems remains wide across most operational scenarios. Why are agricultural robots still not widely deployed in real farms despite decades of research in autonomous navigation and path planning, and what is preventing full farm autonomy? This paper reviews the principal enabling technologies for autonomous agricultural integration, with a specific focus on path planning as the differentiator between research-stage and deployed systems. Current research in human–robot integration, open-field navigation, row identification and following, crop sensing, and power efficiency is synthesised and evaluated against a deployability criterion. A Deployability Assessment Framework is introduced, comprising structured tables that assign Technology Readiness Levels to twelve path-planning families and benchmark eleven commercial and research platforms against field-validated accuracy data. The analysis shows that point-to-point GNSS navigation has reached TRL 9 with over one million commercial units deployed, vision-based crop row following is at TRL 5–7 depending on crop and season, and whole-farm autonomy with dynamic re-planning is at TRL 3–5. The primary barriers are the absence of standardised evaluation benchmarks, the failure of perception models to generalise across seasons and crop types, and the decoupling of terrain and slip feedback from global path planners. Our review reveals that open-field GNSS navigation is commercially mature, but true whole-farm agricultural autonomy remains unsolved because current systems are not robust enough across seasons, terrain, sensing conditions, and operational transitions.\n\n## 1. Introduction\n\nIn the West, farm ownership has become progressively consolidated under fewer, larger operators [[1](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B1-computation-14-00194)], while globally a structural agricultural labour shortage persists due to rural-to-urban migration, the unreliability of seasonal workforces, and the perceived hardship of farm work. These pressures create a direct demand for automation that can extend productive capacity without proportionally increasing headcount. Larger field sizes, tighter weather windows, and the agronomic requirement for precise, timely operations further accelerate this demand.\n\nThe complexity of the agricultural environment—unstructured terrain, seasonal change, unpredictable obstacles, variable soil conditions, and the co-presence of humans—explains the persistently low uptake of truly autonomous navigation for harvesting and crop treatment [[2](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B2-computation-14-00194)]. Reviews of navigation technology across plantation, livestock, and aquatic production confirm that no single platform or sensing modality covers all application types [[2](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B2-computation-14-00194)].\n\nPath planning is the technological linchpin connecting a high-level farm management instruction (“spray field B”) to the low-level motor commands that safely execute it. It determines how efficiently a machine covers a field, how reliably it follows crop rows, how it handles headlands and obstacles, and, ultimately, whether a system is suitable for commercial deployment. Despite hundreds of published path-planning algorithms, the gap between laboratory demonstrations and commercially viable, field-deployed systems remains wide [[3](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B3-computation-14-00194),[4](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B4-computation-14-00194)]. This review argues that deployability—the measurable readiness of a complete system for autonomous field operation under realistic conditions—is the correct lens through which to evaluate progress in agricultural robotics.\n\nThis paper makes three specific contributions: (1) a critical review of enabling technologies—HRI, open-field navigation, row following, crop identification, and power management—evaluated against their contribution to deployability; (2) a Deployability Assessment Framework comprising structured tables that assign TRL values to twelve path-planning families and benchmark eleven commercial and research platforms against field-validated accuracy data; and (3) an identification of four technical gaps—standardised benchmarks, seasonal perception generalisation, terrain-integrated planning, and regulatory pathways—that currently block the transition from TRL 6–7 to TRL 9 for row following systems.\n\nThe review is organised as follows. [Section 2](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#sec2-computation-14-00194) covers the principal technology areas ([Section 2.2](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#sec2dot2-computation-14-00194), [Section 2.3](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#sec2dot3-computation-14-00194), [Section 2.4](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#sec2dot4-computation-14-00194), [Section 2.5](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#sec2dot5-computation-14-00194) and [Section 2.6](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#sec2dot6-computation-14-00194)). [Section 3](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#sec3-computation-14-00194) presents the deployability analysis and tables. [Section 4](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#sec4-computation-14-00194) identifies outstanding technical and regulatory challenges, and [Section 5](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#sec5-computation-14-00194) provides conclusions.\n\n## 2. Analysis of Current Problems and State of Solutions\n\n### 2.1. Review Methodology\n\nThis review was developed through a targeted literature search with a goal of approximately 100 journal papers focused on path planning and its derivatives in agricultural settings. Scopus and Web of Science were the primary bibliographic databases. A total of 88 papers were investigated once duplicates were removed, with the remaining references referring to company websites or ISO specifications. Grey literature, vendor white papers and blogs were read for orientation but were not cited. Some of the figures were generated or enhanced with the aid of AI. Selection criteria: journal articles in English, published from 2019 to 2026, in Agricultural Sciences, Engineering, and Computer Science. Articles exclusively on teleoperation or without relevance to in-field path execution were excluded; earlier foundational studies were also included where the field cites them by convention. The search string combined the following:\n\n(title:(\"farming\" OR \"precision agriculture\") AND abstract:(\"robot\" OR \"automated\")) AND keywords:(\"crop row following\" OR \"path planning\" OR \"autonomous navigation\" OR \"human-robot interaction\")\n\nThe four main resulting pillars of deployability: human–robot interface (HRI), navigation and autonomous movement, crop identification and handling, and power efficiency and environmental impact—are illustrated in [Figure 1](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#fig_body_display_computation-14-00194-f001) and structure the review.\n\n**Figure 1.** Summary of key areas: (1) HRI, (2) navigation and autonomous movement, (3) crop identification and handling, (4) power efficiency and environmental impact.\n\n### 2.2. Integration with Humans and Existing Machinery (HRI)\n\nThe transition to field autonomy is constrained by the cost of replacing existing machinery and the time required for farm workers to adopt new operational practices. The scope of this transition across plantation, livestock, and aquatic applications is reviewed in [[2](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B2-computation-14-00194)]. Overall, HRI research accounted for less than 12% of the research papers reviewed, with the majority originating in the USA, Northern Europe, and Japan. Integration of the Robot Operating System (ROS) with legacy farm machinery is demonstrated in [[5](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B5-computation-14-00194)], which presents an effective graphical user interface enabling high-level commands (go to field, follow leader, go to charging station) across a mixed fleet of conventional and robotic vehicles. A modular hardware-software framework using ROS, standardised sensors, and replaceable 3D-printed chassis components has been validated across cotton-crop field trials [[6](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B6-computation-14-00194)].\n\nMachines operating near humans must approach from predictable directions, maintain defined safety distances, and respond to operator gestures. A Human-Aware Module (HAM) applied to soft-fruit picking [[7](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B7-computation-14-00194)] shown in [Figure 2](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#fig_body_display_computation-14-00194-f002), models the human movement envelope using cameras to infer intent through gesture recognition, and legs detected by the LiDAR coverage as shown in (a) blue and pink with the red arrow in (b) demonstrates the leg’s detection and likely movement direction. The new generation of collaborative robots (cobots [[8](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B8-computation-14-00194)]) and sensitive electronic “skin” [[9](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B9-computation-14-00194)] (Airskin [[7](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B7-computation-14-00194)]) are making close-proximity human–robot operation viable on agricultural manipulators. Risk assessment frameworks for autonomous agricultural machinery are becoming standardised practice [[10](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B10-computation-14-00194)], and deep-learning-based human-intention recognition with safety zones is advancing rapidly [[11](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B11-computation-14-00194)]. A comprehensive review of human–robot collaboration (HRC) in agriculture covering 55 studies identifies sensing infrastructure, safety certification, and operator training as the dominant barriers to deployment [[12](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B12-computation-14-00194)].\n\n**Figure 2.** Human-aware navigation module for cooperative fruit-picking (**a**) Detection coverage areas according to the sensor used. (**b**) Inputs and outputs of the camera-based skeleton detector (blue) and the LiDAR-based leg detector (red) [[7](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B7-computation-14-00194)].\n\nFleet coordination extends HRI beyond individual platforms. A decentralised framework for allocating vehicles, implements, and raw materials dynamically across a farm, accounting for soil stability, time horizon, and shared ownership, is proposed in [[13](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B13-computation-14-00194)]. The leader–follower architecture in [[14](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B14-computation-14-00194)] allows a human-driven tractor to lead a swarm of autonomous robots, with the swarm pattern, spacing, and headland-turning logic managed autonomously. Route descriptions using controlled natural language and ISO 8373:2021 vocabulary [[15](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B15-computation-14-00194)] are encoded in the Mission Planner [[16](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B16-computation-14-00194)], enabling routes from the machine shed through gates and across fields to be expressed in a human-readable farm description.\n\nThe analysis of trailer dynamics during headland turning [[17](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B17-computation-14-00194)] addresses a common cause of crop damage and wasted headland in towed implements, providing analytical paths for N-trailer vehicles that prevent corner cutting. Vehicle rollover risk as a function of terrain slope, speed, and turning radius is tabulated in [[18](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B18-computation-14-00194)] and minimised through dynamic path constraints in [[19](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B19-computation-14-00194)].\n\n### 2.3. Open-Field Navigation\n\nOpen-field navigation—locomotion without crop row constraints—is the most mature segment of agricultural autonomy, covering 27% of the reviewed papers, with a majority of them originating from China and Europe. Summarised in [Figure 3](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#fig_body_display_computation-14-00194-f003), navigation relies on Global Navigation Satellite Systems (GNSS) to derive position and heading, with the pure-pursuit algorithm [[20](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B20-computation-14-00194)] the most widely deployed controller. A comprehensive review of path-planning methods (pure pursuit, Linear Quadratic Regulator (LQR), Fuzzy Logic, Model Predictive Control (MPC)) and motion-control methods (Proportional–Integral–Derivative (PID), neural networks, sliding mode) in an agricultural context is provided in [[21](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B21-computation-14-00194)].\n\n**Figure 3.** Path-planning and motion-control taxonomies for unmanned agricultural tractors [[21](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B21-computation-14-00194)].\n\nThe heading accuracy achievable from two spatially separated GNSS antennas fused with an Inertial Measurement Unit (IMU) is critically assessed in [[22](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B22-computation-14-00194)], which proposes an adaptive Kalman filter that significantly reduces bias on narrow, bumpy terrain. Centimetre-level accuracy using the Quasi-Zenith Satellite System correction signal has been validated in mountainous farmland [[23](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B23-computation-14-00194)]. RTK-GNSS evaluation on dynamic and static platforms against a total station ground truth is described in [[24](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B24-computation-14-00194)].\n\nA complete navigation stack (“FiWare”\u002FSmart Navigation Manager) is developed in [[25](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B25-computation-14-00194),[26](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B26-computation-14-00194)]: a high-level GOTO-GOAL command produces a motion profile, including orientation; Dubins and Spiral controllers manage Ackermann steering; and LiDAR-segmented safety zones trigger real-time path re-planning. The Reeds–Shepp curve [[27](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B27-computation-14-00194)] improves coverage efficiency over irregular field boundaries. Smooth headland turns using Dubins curves and spiral controllers with actuation-rate constraints are formalised in [[28](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B28-computation-14-00194)]. The entry\u002Fexit path planner in [[29](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B29-computation-14-00194)] uses the A* algorithm with vehicle turning-radius constraints and was validated on a 60 kW tractor.\n\nComplete Coverage Path Planning (CCPP) has received substantial recent attention. The work in [[3](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B3-computation-14-00194)] presents a systematic CCPP approach for wheeled robots addressing field entry, irregular boundaries, and headland coverage; Ref. [[30](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B30-computation-14-00194)] extends this to 3D fields with terrain-inclination effects on soil erosion and energy consumption. The review in [[4](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B4-computation-14-00194)] proposes a three-stage methodology: guidance-track generation, traversal sequencing, and smooth drivable path generation. Headland coverage planning with continuous curvature and full tractor-implement geometry constraints is solved in [[31](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B31-computation-14-00194)], the first work to guarantee that field borders are not crossed during manoeuvres.\n\nObstacle avoidance using binarised Google Maps imagery is demonstrated in [[32](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B32-computation-14-00194),[33](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B33-computation-14-00194)]; the minimum-snap algorithm adds vehicle kinematics (minimum curvature, jerk, and snap constraints) to obstacle-circumnavigation planning [[34](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B34-computation-14-00194)]. A hybrid semantic–topological–metric map with a novel switching algorithm [[35](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B35-computation-14-00194)] enables low-energy path planning by incorporating surface type and inclination. Multi-robot cooperative planning, where a UAV and UGV coordinate to locate and service insect traps in olive groves using YOLO-based identification and fiducial-marker landing, represents an emerging frontier [[36](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B36-computation-14-00194)]. It must be mentioned that the use of UAV imagery, proximal sensing, multispectral or hyperspectral data, and AI-based crop monitoring can provide useful information for autonomous robots, such as disease distribution, weed patches, crop growth status, and prescription maps, giving a dual use for real-time UAV imagery.\n\nPath planning in agriculture is often task-dependent. For example, the best path for crop scouting, disease monitoring, selective spraying, weeding, or harvesting may not be the same. [Table 1](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#table_body_display_computation-14-00194-t001) uses information in [[37](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B37-computation-14-00194)] to show the relationship of different agricultural tasks with different navigation requirements, such as coverage efficiency, row following accuracy, target localisation, repeatability, and avoidance of crop damage.\n\n**Table 1.** Agricultural tasks and corresponding navigation requirements.\n\nA recent review of the control systems of agricultural robotics [[38](https:\u002F\u002Fwww.mdpi.com\u002F2079-3197\u002F14\u002F8\u002F194#B38-computation-14-00194)] emphasises that navigation requirements vary significantly across field operations. Tasks such as scouting prioritise coverage efficiency and mapping ","MDPI Computation 14(8):194 2026年8月21日","2026-08-21T00:00:00Z","论文",10,false,83,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,22,20,14,9,1,"综述系统评估了自主农业机械路径规划技术的可部署性，提出评估框架，对智慧农业研究有重要参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"综述","路径规划","自主农机","可部署性评估","MDPI Computation",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"F5","machinery","农机装备与机械化","\u002Ftopic\u002Finputs-equipment\u002Fmachinery","F",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45],{"code":33,"score":46,"supported":47,"title":48,"abstract":51,"tags":52},17,true,[49,50],"农业机械","agricultural machinery",[],[28],[54,55],"可部署性评估 自主农机 路径规划 MDPI Computation","可部署性评估 自主农机","可部署性评估自主农机路径规划MDPIComputation-844",4,"2026-08-22T00:06:00.932761Z",{"total":60,"page":22,"page_size":60,"items":61},6,[62,116,162,228,304,349],{"id":63,"title":64,"url":65,"summary":66,"summary_zh":8,"content":8,"source_name":67,"source_url":8,"published_at":68,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":69,"score_detail":70,"sources":73,"tags":75,"primary_topic":80,"secondary_topics":81,"classification":82,"search_phrases":101,"slug":104,"view_count":57,"doi":8,"paper":105,"created_at":115},3653,"面向智慧农业的自主农业机械——观测、异质性与智能基础设施的集成框架","https:\u002F\u002Fwww.jstage.jst.go.jp\u002Fbrowse\u002Frdj\u002F5\u002F0\u002F_contents\u002F-char\u002Fja","由Hongjin Li、Chunjiang Gao等在Resources Data Journal 2026年第5卷发表的综述文章。面向Agriculture 4.0过渡，针对自主农业机械这一核心议题提出'观测-异质性-基础设施'三位一体的集成框架。系统综述了自主农业机械的技术基础、应用领域、性能优势与采纳约束，并围绕多模态感知、AI驱动决策、自主导航与控制、精准执行、多机协同的耦合展开分析，特别关注环境不确定性、实时决策、互操作性与系统级可扩展性的挑战。研究识别出从孤立任务自动化向数据驱动、适应性、网络化农业自主性的渐进转型，并强调单一组件的改进若无配套计算、通信、机械与制度基础设施支撑，未必带来系统级性能提升。","Resources Data Journal 2026 vol.5 p.576-596 (Hongjin Li, Chunjiang Gao)","2026-09-18T00:00:00Z",74,{"impact":17,"substance":19,"depth":46,"authority":71,"freshness":60,"relevant":22,"comment":72},13,"核心期刊综述提出观测-异质性-基础设施三位一体框架，对自主农机系统级落地有参考价值，但属学术综述、时效一般，适合主题聚合而非每日精选头条。",[74],{"name":67,"url":65},[76,77,78,29,79],"智慧农业","农业人工智能","多模态感知","Agriculture 4.0",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":83},{"candidates":84,"agricultural_evidence":47},[85,90,95],{"code":33,"score":86,"supported":47,"title":87,"abstract":88,"tags":89},11,[49],[49],[],{"code":91,"score":21,"supported":47,"title":92,"abstract":93,"tags":94},"I1",[76],[],[76],{"code":96,"score":97,"supported":14,"title":98,"abstract":99,"tags":100},"I2",2,[],[],[77,78],[102,103],"自主农业机械 集成框架","Resources Data Journal 智慧农业","自主农业机械集成框架-3653",{"doi":8,"openalex_id":8,"authors":106,"venue":8,"cited_by_count":107,"oa_url":8,"card":108,"direction":112,"ingested_from":114},[],0,{"tldr":109,"method":110,"finding":111,"direction":112,"opportunity":113},"综述自主农业机械，提出观测-异质性-基础设施三位一体集成框架。","文献综述，围绕多模态感知、AI决策、自主导航与多机协同分析。","单组件改进若无计算、通信与制度基础设施配套，难带来系统级性能提升。","智慧农业 \u002F 农业物联网","可研究异构农机互操作协议与边缘计算协同，量化基础设施配套对系统级性能的增益。","agent","2026-09-28T00:03:02.555619Z",{"id":117,"title":118,"url":119,"summary":120,"summary_zh":8,"content":8,"source_name":121,"source_url":8,"published_at":68,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":122,"score_detail":123,"sources":126,"tags":128,"primary_topic":130,"secondary_topics":131,"classification":132,"search_phrases":150,"slug":153,"view_count":97,"doi":8,"paper":154,"created_at":161},3120,"Autonomous Agricultural Machinery for Smart Agriculture: An Integrated Framework of Observation, Heterogeneity, and Intelligent Infrastructure（智慧农业自主农机：观测、异质性与智能基础设施一体化框架）","https:\u002F\u002Fwww.jstage.jst.go.jp\u002Farticle\u002Frdj\u002F5\u002F0\u002F5_576\u002F_article\u002F-char\u002Fen","Hongjin Li & Chunjiang Gao 在 Journal of Agricultural Information 5: 576-596 发表综述文章（J-STAGE 平台 2026-09-18 上线）：针对农业 4.0 时代自主农机核心问题——如何在复杂动态田间条件下将异构环境信息转化为可靠自适应可扩展的机器自主性，系统综述自主农机的技术基础、应用领域、性能优势与采用约束，并构建围绕\"观测、异质性、基础设施\"的一体化框架。研究不再按机器类型分类技术，而是考察多模态感知、AI 决策、自主导航控制、精准执行、多机协同之间的耦合关系，特别关注环境不确定性、实时决策、互操作性和系统级可扩展性的挑战。识别从孤立任务自动化向数据驱动自适应网络化农业自主性的渐进过渡，强调个体组件改进未必带来系统级性能提升，除非具备兼容的计算、通信、机械和制度基础设施。","J-STAGE \u002F Research Disclosure Journal",78,{"impact":17,"substance":124,"depth":46,"authority":71,"freshness":21,"relevant":22,"comment":125},21,"核心期刊综述，提出观测-异质性-基础设施一体化框架，对智慧农业自主农机研究有参考价值，但属学术综述、产业影响有限。",[127],{"name":121,"url":119},[76,77,78,29,129],"农业4.0",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":133},{"candidates":134,"agricultural_evidence":47},[135,141,146],{"code":33,"score":136,"supported":47,"title":137,"abstract":139,"tags":140},19,[138,50],"农机",[138],[],{"code":91,"score":46,"supported":47,"title":142,"abstract":144,"tags":145},[76,143],"smart agriculture",[],[76],{"code":96,"score":97,"supported":14,"title":147,"abstract":148,"tags":149},[],[],[77,78],[151,152],"自主农机 智慧农业 一体化框架","Hongjin Li Chunjiang Gao 自主农机","自主农机智慧农业一体化框架-3120",{"doi":8,"openalex_id":8,"authors":155,"venue":8,"cited_by_count":107,"oa_url":8,"card":156,"direction":112,"ingested_from":114},[],{"tldr":157,"method":158,"finding":159,"direction":112,"opportunity":160},"综述自主农机技术，提出观测、异质性、基础设施一体化框架。","系统综述多模态感知、AI决策、导航控制与多机协同的耦合关系。","组件改进未必提升系统性能，需兼容的计算、通信、机械与制度基础设施。","可研究异构农机互操作协议与边缘计算架构，填补系统级可扩展性验证空白。","2026-09-22T00:05:38.042546Z",{"id":163,"title":164,"url":165,"summary":166,"summary_zh":167,"content":8,"source_name":168,"source_url":165,"published_at":169,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":170,"score_detail":171,"sources":175,"tags":177,"primary_topic":180,"secondary_topics":181,"classification":182,"search_phrases":199,"slug":202,"view_count":57,"doi":203,"paper":204,"created_at":227},1711,"Path planning for unmanned combined harvester edging operation based on UAV imagery","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112382","Path planning for unmanned combined harvester edging operation based on UAV imagery。Computers and Electronics in Agriculture","基于无人机影像的无人联合收割机边缘作业路径规划。《计算机与电子在农业中的应用》","Computers and Electronics in Agriculture","2026-09-04T00:00:00Z",66,{"impact":172,"substance":17,"depth":173,"authority":172,"freshness":97,"relevant":22,"comment":174},15,16,"论文提出基于无人机影像的联合收割机路径规划方法，属于细分领域进展，但时效性较低。",[176],{"name":168,"url":165},[76,178,77,28,179],"无人机","农机装备",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":183},{"candidates":184,"agricultural_evidence":47},[185,191,195],{"code":33,"score":173,"supported":47,"title":186,"abstract":188,"tags":190},[187],"harvester",[189,187],"收割机",[179,28],{"code":91,"score":22,"supported":14,"title":192,"abstract":193,"tags":194},[],[],[76],{"code":96,"score":22,"supported":14,"title":196,"abstract":197,"tags":198},[],[],[77],[200,201],"农业人工智能 农机装备 智慧农业 路径规划","农业人工智能 农机装备","农业人工智能农机装备智慧农业路径规划-1711","10.1016\u002Fj.compag.2026.112382",{"doi":203,"openalex_id":205,"authors":206,"venue":168,"cited_by_count":107,"oa_url":8,"card":221,"direction":112,"ingested_from":226},"W7208720259",[207,210,212,214,216,218],{"name":208,"orcid":209},"Hongbo Jia","https:\u002F\u002Forcid.org\u002F0000-0001-5426-347X",{"name":211,"orcid":8},"Jun Zhou",{"name":213,"orcid":8},"Jingwei Sun",{"name":215,"orcid":8},"Licun Yuan",{"name":217,"orcid":8},"Yongqiang He",{"name":219,"orcid":220},"Muhammad Aurangzaib","https:\u002F\u002Forcid.org\u002F0000-0002-4445-8801",{"tldr":222,"method":223,"finding":224,"direction":112,"opportunity":225},"基于无人机影像为无人联合收割机规划边缘作业路径。","利用无人机影像生成地图，结合路径规划算法。","实现了无人收割机边缘作业的自动路径规划。","可探索动态障碍物下的实时路径重规划，或结合多机协同作业优化。","openalex","2026-09-05T23:30:02.064293Z",{"id":229,"title":230,"url":231,"summary":232,"summary_zh":8,"content":233,"source_name":234,"source_url":8,"published_at":235,"category":236,"cover_url":8,"hotness":13,"is_selected":14,"score":237,"score_detail":238,"sources":243,"tags":245,"primary_topic":250,"secondary_topics":251,"classification":252,"search_phrases":299,"slug":302,"view_count":107,"doi":8,"paper":8,"created_at":303},5509,"湖北襄阳以「四良」联动书写秋粮丰收 良田良种良技良机齐发力","https:\u002F\u002Fwww.hj.cn\u002Fcontent\u002F2026-10\u002F16\u002Fcontent_20234591.html","宜城市郑集镇金铺村千亩稻田迎来收获，合作社负责人王艳涛把良田、良种、良技、良机融入生产实践：高标准农田把零散地块整合为连片良田并配套灌溉管网，主动对接省农科院把自家田地当试验田试种新品种，按水稻生长阶段精准调控水肥，农机库房配备收割机、插秧机、植保无人机与烘干机。","金秋时节，宜城市郑集镇金铺村的千亩稻田一片金黄。望着颗粒饱满的水稻，宜城市金大地专业合作社负责人王艳涛满脸喜悦。作为襄阳市“三个一千”种粮大户，他多年深耕粮食种植领域，把“良田、良种、良技、良机”融入生产实践，在田野里写下了生动的丰收故事。\n\n良田打底。“想种出好庄稼，第一步得养好地。”王艳涛说，高标准农田建设把零散地块整合成连片良田，还配套完善了灌溉管网。在此基础上，他每年都会对田地进行深翻，让土壤更疏松，减少病虫害发生。\n\n良种当家。王艳涛主动对接省农科院等科研单位，把自家田地当作试验田。“这是省农科院和市农业农村局在我这儿试种的品种。”他指着田间的品种标识牌介绍，今年种得最好的一个品种，亩产预计达1000公斤。他告诉记者，合作社一般选择适配本地气候、抗病性好的品种，好品种种出的稻米，成色、口感、品相更符合市场需求。\n\n良技护航。王艳涛根据水稻不同生长阶段精准调控水肥，遇到拿不准的问题，就请农技专家上门指导。“整个生育期都做精细化田管，加上农技人员上门指导，病虫害防控很到位。”王艳涛说。\n\n良机助力。眼下正是秋粮收获关键期，合作社农机库房里，机器检修声与交谈声交织，一派忙碌景象。王艳涛介绍，合作社配有收割机、拖拉机、插秧机、植保无人机、烘干机等各类农机设备，种地省工、省时、省力。\n\n多年摸爬滚打，王艳涛攒下了一本“种地经”。“种田没有捷径，把土地整好，把种子选对，管理不能偷懒，机器要用好，踏踏实实管好每一亩田，收成就不会辜负付出和努力。”王艳涛朴实的话语，透着种粮人的执着与笃定。","襄阳日报 2026-10-16","2026-10-16T00:00:00Z","报道",39,{"impact":239,"substance":240,"depth":13,"authority":60,"freshness":241,"relevant":22,"comment":242},8,12,3,"地市级典型种粮大户报道，四良联动有实操细节但缺乏新数据与政策增量，时效偏旧，不宜进每日精选。",[244],{"name":234,"url":231},[246,247,179,248,249],"高标准农田","单产提升","良种推广","粮食生产",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":253},{"candidates":254,"agricultural_evidence":47},[255,260,267,272,278,284,289,294],{"code":33,"score":256,"supported":47,"title":257,"abstract":258,"tags":259},7,[],[138,189],[179],{"code":261,"score":60,"supported":47,"title":262,"abstract":263,"tags":266},"A1",[],[264,265],"水稻","稻田",[],{"code":268,"score":57,"supported":47,"title":269,"abstract":270,"tags":271},"H1",[],[246],[246],{"code":273,"score":241,"supported":47,"title":274,"abstract":275,"tags":277},"F4",[],[276],"植保",[],{"code":279,"score":241,"supported":47,"title":280,"abstract":281,"tags":283},"H3",[],[282],"灌溉",[],{"code":285,"score":97,"supported":14,"title":286,"abstract":287,"tags":288},"A8",[],[],[247,249],{"code":290,"score":22,"supported":14,"title":291,"abstract":292,"tags":293},"A",[],[],[249],{"code":295,"score":22,"supported":14,"title":296,"abstract":297,"tags":298},"F1",[],[],[248],[300,301],"襄阳 宜城 水稻 单产","金大地合作社 王艳涛","襄阳宜城水稻单产-5509","2026-10-22T00:06:58.807971Z",{"id":305,"title":306,"url":307,"summary":308,"summary_zh":8,"content":309,"source_name":310,"source_url":8,"published_at":235,"category":236,"cover_url":8,"hotness":13,"is_selected":14,"score":311,"score_detail":312,"sources":314,"tags":316,"primary_topic":321,"secondary_topics":322,"classification":323,"search_phrases":344,"slug":347,"view_count":107,"doi":8,"paper":8,"created_at":348},5504,"山西因地制宜发展农业新质生产力 智能农机加速下乡","http:\u002F\u002Ftuopin.ce.cn\u002Fnews\u002F202610\u002Ft20261016_3260414.shtml","《山西省智慧农业行动计划（2026—2030年）》细化落地举措，围绕丘陵山地特点推进智慧农业先行先试、智慧农（牧、渔）场建设与技术创新。全省坡耕地1686.66万亩、占耕地总面积29.06%，为此加强丘陵山区智能农机研发引进，开展丘陵山区杂粮农机具研究，组建省级智慧农业产业技术体系。","**阅读提示**\n\n**我省依托科研院所与高校、企业联合攻关，量身研发本土化、适配型智能农机装备。当前，智能技术稳步融入耕种管收储全产业链条，推动农业生产实现精准管控、降本增效。同时，相关部门统筹推行农业社会化服务、落实专项政策补贴、开展定向技能培训等多项举措，打通技术落地堵点，构建智慧农业发展体系，让数字红利惠及广袤田野，书写黄土高原现代农业转型发展新答卷。**\n\n晨光破晓，阳光渐暖。太原市小店区北格镇梁家庄村的智慧农业大棚内，智能设备精准感知田间环境变化，保温卷帘随气温变化平稳升降，全程无需人工操作。\n\n这座由山西优班图科技股份有限公司联合山西农业大学（省农科院）共建的实验基地，是我省设施农业智能化升级的生动缩影，见证着传统农业向智慧农业转变的迭代蜕变。\n\n“大棚卷帘并非一次性全开，而是根据温度变化幅度循序渐进调节。”基地负责人李鹏飞介绍。大棚内各类传感器全天候实时采集温湿度、光照强度、二氧化碳浓度等核心环境数据，通过智能系统自动联动卷帘、通风、灌溉等设备，实现种植环境动态精准调控，彻底颠覆了传统“看天种地”的粗放模式，全面迈入“数据管棚”的智慧农业新阶段。\n\n农业新质生产力，核心是数字技术与农业生产的深度融合。2026年中央一号文件明确提出，要因地制宜发展农业新质生产力，促进人工智能与农业发展相结合，拓展无人机、物联网、机器人等应用场景。对标国家部署，《山西省智慧农业行动计划（2026—2030年）》细化落地举措，加快数字技术与农业深度融合，提升农业智能化水平，提高农业生产效率、资源利用率和农民收入，推动山西现代农业高质量发展。\n\n依托政策牵引、科研攻关、产业赋能，三晋大地各类智能农机、数字装备加速落地，贯穿农业生产全链条，为特色种养提质增效、群众稳定增收注入数字动能。\n\n**立足实际**\n\n**研发适配型智能农机**\n\n我省丘陵山地广、零散坡耕地多。第三次国土调查数据显示，全省坡耕地达1686.66万亩，占耕地总面积29.06%；梯田耕地达1421.68万亩，占耕地总面积24.49%。地块零散、坡度不均、田间道路狭窄，适配小块坡耕地的专用农机短缺，是丘陵山区农业提质增效的主要瓶颈。\n\n靶向破解本土生产难题，我省聚焦农业生产薄弱环节，联动科研机构、涉农企业、专业合作社精准攻关，量身研发适配丘陵山区作业的智能农机装备，补齐山区农业机械化、智能化短板。\n\n8月20日，娄烦县天池店乡南岔村马铃薯新优品标准化种植示范基地内，一垄垄马铃薯长势喜人，智能化种植设备的赋能成效尽显。\n\n“马铃薯长势旺盛，丘陵山区自走式马铃薯种植机发挥了重要作用。”娄烦润和美种植专业合作社负责人尤同义说。这款机具由山西省薯类产业技术体系专家赵旭志、贺孝兵团队研发，可一次性完成开沟、播种、起垄、镇压等一体化作业，通过起垄镇压保墒技术有效提升出苗率，精准解决了丘陵山区小地块大中型农机难进地、小型农机功能单一的行业痛点。\n\n不只马铃薯种植装备，多款适配山区地形的智能农机相继落地推广。针对农业生产各类细分痛点，山西农机科创持续发力、多点突破。\n\n由山西农业大学（省农科院）高粱研究所研究员白文斌团队研发的“大地智牛”全自主覆膜播种机器人，已在阳高、寿阳、襄垣、武乡、永和等多个山区县2000余亩耕地验证使用。该设备集成施肥、覆膜、铺设滴灌带、播种、覆土五道工序，可在6°及以下坡度耕地稳定作业，填补了国内丘陵山区覆膜播种智能农机的空白。设备作业时速稳定，可根据不规则曲线地块自主规划作业路径、动态调整速度，兼顾作业精度与生产效率。\n\n山西沃勃农业发展有限公司与山西农业大学（省农科院）园艺学院等科研部门，聚焦温室果蔬采摘用工紧缺、成本偏高、果实损伤率高的难题，融合多模态视觉与三维定位技术，成功研发履带式自主导航采摘机器人，实现果实精准识别定位、机械臂柔性低损采摘。一台机器人可替代2—3名采摘工，单棚年节约人力成本1.6万元以上。\n\n围绕玉米全生育期绿色除草需求，五台县城园丰农机制造有限公司联合清华大学天津高端装备研究所等单位，集成全地形移动平台、多模态感知组件、智能决策控制器、高精度导航系统、仿生物理除草与松土机构、复合能源系统及物联网作业平台，成功制造覆膜玉米智能除草机器人。该款机器人可自主建立地块与作物行地图，精准识别玉米苗株、杂草、地膜和障碍物，在实现清除田间杂草的同时完成土壤浅松。\n\n太原科技大学和山西农谷现代农业装备科技有限公司等单位，成功研制黄花菜智能采摘机器人。此款采摘机器人依托国际领先的并联机器人技术，可保障高速高精度作业；视觉系统利用高感光相机与多光谱融合增强方法，能快速识别花蕾进行轨迹规划；末端执行器采用了力位混合控制技术，可精准定位采摘点实现无损采摘；控制系统融合激光雷达等多传感器，可实现复杂田块自主导航与动态避障。\n\n一系列本土化、适配型智能农机的研发与落地，精准破解了我省丘陵山地农业生产的诸多短板，为推动山地农业从传统人工劳作向智能高效作业转型提供了全新选择。\n\n**全链赋能**\n\n**贯穿耕管收储全环节**\n\n8月23日，运城市盐湖区龙居镇南花村百忍堂冷库分选车间内，智能分拣设备全速运转，一颗颗红香酥梨经由传送轨道有序输送，通过多维度智能扫描，系统综合比对果体大小、重量、色泽、表皮瑕疵、内部品质等多项参数，依托智能算法自动分级、精准归类，实现标准化分选。\n\n“人工分拣没有统一标准，果品品相、大小参差不齐，很多优质梨果因分拣不规范，卖不上高端市场价。”冷库负责人张蓓坦言。智能分拣设备的投入使用，彻底补齐人工分拣的短板，让优质果品匹配高端价值，有效助力农户增收、产业提质。如今，智能化、数字化技术已全面渗透农业种植、田间管护、采收加工、仓储保鲜全链条，从单一设备示范应用，转向全流程、系统化智慧升级。\n\n田间管护更精细。春季小麦管护关键期，曲沃县曲村镇下坞村麦田里，搭载北斗定位的自由式喷灌机器人灵活作业，180米直径喷射范围实现360°无死角精准供水。相较于传统灌溉模式，设备节水55%左右，作业效率提升85%以上，既省水省力，又保障麦苗均匀受水、长势均衡。小麦灌浆期，临猗县统筹8支专业飞防队伍、119架植保无人机，对全县26.97万亩小麦开展“一喷三防”全覆盖作业，无人机按精准航线低空作业，均匀喷施药剂与叶面肥，筑牢粮食丰产防线。\n\n育苗耕种更高效。山西六新科技有限公司等单位联合研发的数智育苗机器人，搭载双模式自由切换、地块仿形自适应两大核心技术。设备可快速切换条播、撒播作业模式，自动根据苗圃凹凸地表调整播种高度，保证落种均匀；内置定量分料结构，适配大小不同农作物、蔬菜、林木、药材种子，可同步完成播种、覆土、轻度镇压一体化作业，整机机动灵活，适合露天苗圃大范围连续作业。\n\n田间作业更智能。山西恒赫百旺智能科技有限公司研发的丘陵山地无人设备，集成智能感知、精准决策、自主执行功能，可智能生成与坡地、梯田契合的自主飞行航线，实现定高、定速全自主飞行与定量施药作业。\n\n仓储保鲜更安全。太原先元科技有限公司等联合打造的粮食干燥仓储全流程管理系统，以中央集控调度机器人为核心，可智能识别粮食水分，动态调节作业温度、风量，精准完成粮食干燥处理；仓储阶段可24小时自动监测粮情、智能翻粮，全方位保障粮食存储安全。\n\n为持续拓宽智慧农业应用场景，今年7月，省工信厅、省农业农村厅联合发文，聚焦种植、养殖、农产品初加工三大重点领域，启动农业领域机器人典型应用场景遴选工作，以标杆场景引领农机装备创新迭代，推动全省农业机械化、智能化高质量发展。\n\n在北斗导航、智能感知、精准算法等技术支持下，智慧农机已成为三晋大地耕、种、管、收的生力军。\n\n左权县探索建立“县级统筹、农机到户、技术护航、补贴直达”四位一体工作模式，投放300余台配备北斗导航、无人驾驶功能的智能农机，实现耕、种、管、收全链条作业。据该县农业农村局工作人员介绍，智能农机依托导航系统规划作业路径，行距误差控制在2厘米以内，作业深度偏差不超1厘米，可有效杜绝漏耕、重耕问题，种子利用率提升15%以上，农业生产精细化、标准化水平显著提升。\n\n怀仁市依托智慧农机载体，以数据互联互通为支撑，搭建起涵盖耕、种、管、收各环节的智慧农事服务体系，助力当地农业由传统“会种地”向现代“慧种地”迭代升级，大力推行可感知、可控制、可决策的智慧农业发展模式。该市农业机械化发展中心主任郭亮介绍，自2023年起，当地逐步推广农机无人驾驶辅助系统，现有设备保有量约200套，有效降低人工与农资投入成本。\n\n**破解堵点**\n\n**构建长效发展体系**\n\n智能农机、数字装备的广泛应用，为我省农业转型升级、提质增效提供了有力支撑，但高端智能设备造价偏高、小农户购置能力不足等问题，仍然制约着全省智慧农业的规模化普及、全覆盖推广。\n\n“公司研发的履带式智能植保无人机可自主规划路线、24小时不间断作业，性能稳定高效，但价格偏高，目前主要推广于广西、海南等规模化果园种植区，省内仅万荣、临猗等林果大县落地应用。”山西添翼创新科技有限公司总经理闫太平道出行业共性难题。\n\n山西优班图科技股份有限公司等联合研发的智能水肥药一体机同样面临推广困境，设备可根据作物长势精准施肥喷药、节本增效，却因购置成本较高，让众多小农户望而却步。\n\n针对单家独户购置成本高、设备利用率低的痛点，各地立足小农户多、地块碎片化的农业实情，创新探索“智能农机共享+农业生产托管”模式，将高端智能装备转化为社会化服务的“公共农具”，让小农户便捷享受数字农业红利。\n\n社会化服务提质增效，助力普惠共享。临汾市翼城县益农区域农机社会化服务中心，依托全套智能农机装备开展规模化农业托管服务，全程托管土地2万余亩，单环节托管超10万亩，辐射带动周边大量小农户。通过统一智能化作业，实现亩均节本50元以上、增产15%，相关实践成功入选全国农机社会化服务典型案例，为全省智慧农机普惠化推广提供可借鉴的经验。\n\n政策精准托举，打通落地壁垒。相关部门积极落实农机购置与应用补贴政策，将农用无人机、田间智能监测设备、智能耕作机械等新型装备纳入补贴范围，推行优机优补、精准补贴，大幅降低经营主体购置成本。\n\n今年8月，省农机发展中心在清徐县举办农机购置与应用补贴产品现场演示评价活动。本次活动旨在严格规范补贴产品准入标准，夯实农机购置补贴政策实施基础，推动先进适用农机装备的推广应用。参评产品涵盖农用（植保）无人驾驶航空器、农用北斗辅助驾驶系统、北斗农机作业监测终端、田园管理机及微耕机五大品类148个型号。\n\n“我们研发智能农机的最终目标是让农民成为‘白领’，坐在办公室就能种地。”闫太平说，智能农机的广泛落地、高效应用，离不开高素质专业人才的支撑。\n\n今年7月，省农业农村厅印发了《2026年全省高素质农民培育工作实施方案》。根据方案，培育工作专门面向参与智慧农业项目的新型农业经营主体骨干、青年农民骨干、返乡入乡创业群体等重点人群，紧扣我省智慧农业发展核心需求，重点围绕智慧农业发展理念、物联网、大数据、人工智能等信息技术应用、智能农业装备应用、智慧农（牧、渔）场发展等开展培训，破解智能农机“无人会用、无人善用”的人才短板。\n\n同时，全省各地也在积极探索适应智能农机操作的高素质农民培养新途径。朔州市举办的农机手技能提升培训班专门增设北斗导航辅助驾驶、作业质量监测等智能终端操作课程，帮助农机手适应现代农业发展需求。\n\n交口县组织技术人员将无人机驾驶技术培训直接送到田间地头，围绕农业无人机的核心应用场景，从设备构造、飞行原理、安全规范到植保作业参数设置，进行从理论到实操的全流程教学。乡宁县培育30名持证飞手，组建本土专业技术队伍，可熟练操控植保无人机开展梯田智能化作业。\n\n从单点设备示范突破，到全链条技术赋能，我省逐步探索出一条“科研攻关+政策托举+服务赋能”的智慧农业发展路径。曾经依赖人力、看天吃饭的传统农业，正被数据驱动、智能管控的现代化农业重塑。智能农机不再是大型示范基地的专属配置，而是持续下沉千家万户田块的普惠工具，持续释放农业新质生产力效能，为黄土高原旱作农业现代化、三晋乡村全面振兴注入源源不断的数字动能。\n\n![Image 1](https:\u002F\u002Fnginx-sxrb.app.sxrbw.com\u002Fsxrb\u002Fepaper\u002Fpc\u002Fpic\u002F202610\u002F16\u002F49417_0ab510f3-011f-4e35-afe4-86c9214ec13f_l.jpg)\n\n大棚专用自主水肥药农情监测机器人正在进行喷药作业。本报记者 崔如意摄\n\n![Image 2](https:\u002F\u002Fnginx-sxrb.app.sxrbw.com\u002Fsxrb\u002Fepaper\u002Fpc\u002Fpic\u002F202610\u002F16\u002F49417_2321f7b6-ed58-493b-9175-92dbb5561970_l.jpg)\n\n丘陵山区自走式马铃薯种植机正在作业。本报记者 崔如意摄\n\n**相关链接**\n\n《山西省智慧农业行动计划（2026—2030年）》提出，我省将：\n\n1.推进智慧农业先行先试。开展“人工智能+”行动，打造以新技术集群和大模型为支撑的大田种植、设施农业、规模养殖等应用场景，示范推广智能化农机装备。鼓励各市、县因地制宜打造1—2个种植业、畜牧业、渔业等智慧农业应用场景。鼓励建设智慧农业应用引领区，推进种植方案与物联网智能装备、智能灌溉系统、智能农机设备、智慧管理平台等耦合应用。用好线上线下宣传渠道，总结推广智慧农业发展经验做法。\n\n2.推进智慧农（牧、渔）场建设。实施农（牧、渔）场智慧赋能计划，培育一批不同技术模式的智慧农（牧、渔）场。发挥规模主体带动作用，培育一批智慧农业发展社会化服务主体，集成推广智慧农业新技术、新装备。\n\n3.推进智慧农业技术创新。支持科研院校开展智慧农业技术模式研究、集成与推广，利用农业生产过程的数字化仿真、推演，形成最优种植、养殖管理方案。加快智能农机装备技术攻关，加强丘陵山区智能农机装备研发、引进，开展丘陵山区杂粮农机具研究。推进国家级智慧农业重点实验室建设。组建省级智慧农业产业技术体系，为智慧农业发展提供技术支撑。培育一批智慧农业领域科技领军企业，推进智慧农业技术研发、成果转化和产业化应用。促进应用场景需求和研发服务能力对接，推动新技术新产品应用推广。","中国经济网扶贫频道 2026-10-16",69,{"impact":19,"substance":17,"depth":173,"authority":86,"freshness":57,"relevant":22,"comment":313},"省级智慧农业综合报道，智能农机研发与全链应用案例扎实、信源多元，但时效偏旧，适合作为主题聚合素材而非当日精选。",[315],{"name":310,"url":307},[76,317,318,319,320],"农业机器人","智能农机","丘陵山区","农业社会化服务",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":324},{"candidates":325,"agricultural_evidence":47},[326,330,334,339],{"code":33,"score":240,"supported":47,"title":327,"abstract":328,"tags":329},[138],[138],[318],{"code":91,"score":57,"supported":47,"title":331,"abstract":332,"tags":333},[],[76],[76],{"code":335,"score":22,"supported":14,"title":336,"abstract":337,"tags":338},"F6",[],[],[317],{"code":340,"score":22,"supported":14,"title":341,"abstract":342,"tags":343},"G2",[],[],[320],[345,346],"山西 智能农机 丘陵山区","山西 农业新质生产力 智慧农业","山西智能农机丘陵山区-5504","2026-10-22T00:06:58.505233Z",{"id":350,"title":351,"url":352,"summary":353,"summary_zh":8,"content":354,"source_name":355,"source_url":8,"published_at":356,"category":236,"cover_url":8,"hotness":13,"is_selected":14,"score":357,"score_detail":358,"sources":360,"tags":362,"primary_topic":368,"secondary_topics":373,"classification":375,"search_phrases":387,"slug":390,"view_count":107,"doi":8,"paper":8,"created_at":391},5448,"全国宜机收芝麻全程机械化观摩会在安徽太和举行 省农科院作物所主办","https:\u002F\u002Fwww.aaas.org.cn\u002F4303133\u002F71576873.html","10 月 16 日至 18 日，由安徽省农业科学院作物研究所主办的 2026 年全国宜机收芝麻全程机械化生产技术暨联合机收现场观摩会在太和县举行，国家特色油料产业技术体系首席科学家苗红梅研究员、省农科院副院长张磊出席，150 余人参会。17 日上午与会代表赴双浮镇高寨村、旧县镇张槐村观摩 600 亩宜机收芝麻新品种机械化生产示范，现场展示芝麻机械化联合收割作业。作物所张银萍副研究员介绍芝麻耕种管收全程机械化装备与国家、省主推技术，强调农机农艺融合。","10月16日至18日，由安徽省农业科学院作物研究所主办的“2026年全国宜机收芝麻全程机械化生产技术暨联合机收现场观摩会”在安徽省太和县举行，国家特色油料产业技术体系首席科学家苗红梅研究员、省农科院副院长张磊出席会议。\n\n17日上午，与会代表赴太和县双浮镇高寨村、旧县镇张槐村，观摩600亩宜机收芝麻新品种机械化生产示范情况。示范选用高油酸宜机收芝麻新品种，集成机械精量播种、宽窄行种植、平衡施肥、病虫草害综合防控、联合机械收获等绿色高产机械化生产技术，并现场展示芝麻机械化联合收割作业。苗红梅介绍了芝麻产业发展获得的突破性科技成果，院作物研究所张银萍副研究员介绍了芝麻耕、种、管、收全程机械化生产机械装备以及国家主推技术和省主推技术，并强调了农机农艺融合的重要性，获得与会领导与专家代表们的一致好评。\n\n17日下午，召开“特色油料（芝麻）科技与产业创新融合发展研讨会议”，围绕芝麻产业发展现状与展望、江西黑芝麻宜机收品种选育与应用、芝麻加工新产品开发等作专题报告，主产省农技推广部门、产业技术体系专家和企业代表进行交流发言。张磊在讲话中指出，芝麻是我国重要的特色油料作物，事关油料供给安全和主产区农民增收。安徽是芝麻主产省之一，要聚力推进良种、良机、良法深度融合，加快宜机收品种和全程机械化生产技术推广应用，补齐芝麻生产机械化短板，推动芝麻产业向优质、高产、高效方向转型升级。\n\n本次会议集中展示了宜机收芝麻新品种全程机械化生产技术和联合收获装备的最新进展。示范结果表明，应用宜机收芝麻新品种及绿色高产全程机械化生产技术，有效提升了我国特色油料芝麻全程机械化生产水平，促进了农民节本增收和乡村振兴的快速发展。专家建议加大推广良种、良机、良法的深度融合，保障我国特色油料芝麻产业健康稳定发展。\n\n农业农村部科技发展中心、全国农业技术推广服务中心、农业农村部信息中心、农业农村部农村经济研究中心、农业农村部食物与营养发展研究所、中国农业科学院油料作物研究所，安徽、河南、湖北、江西、河北等主产省农技推广部门，国家特色油料产业技术体系岗站专家，科研院所、种植主体和企业代表等150余人参加会议。","安徽省农业科学院 2026-10-20","2026-10-20T00:00:00Z",75,{"impact":18,"substance":17,"depth":20,"authority":71,"freshness":239,"relevant":22,"comment":359},"全国性芝麻机械化生产观摩会，展示宜机收新品种与联合收获装备进展，产业级技术推广价值明确，值得进入每日精选。",[361],{"name":355,"url":352},[363,364,365,366,367],"农机农艺融合","全程机械化","芝麻","宜机收品种","特色油料",{"code":369,"slug":370,"name":371,"path":372,"parent_code":290},"A4","soybean-oilseeds","大豆与油料","\u002Ftopic\u002Ffield-crops\u002Fsoybean-oilseeds",[374],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":376},{"candidates":377,"agricultural_evidence":47},[378,383],{"code":33,"score":46,"supported":47,"title":379,"abstract":381,"tags":382},[380],"机械化",[138,380],[364,363,366],{"code":369,"score":240,"supported":47,"title":384,"abstract":385,"tags":386},[365],[365],[365],[388,389],"安徽太和 宜机收芝麻 观摩会","安徽省农科院 芝麻 全程机械化","安徽太和宜机收芝麻观摩会-5448","2026-10-21T00:10:02.295488Z"]