智慧农业 中英文 农业机器人

The ground-surface portions of plant roots (GSPR) and stems play a crucial role in precision agriculture. Accurate detection of the GSPR enables precise target localization for intelligent irrigation systems, thereby facilitating precise irrigation. Furthermore, reliable detection of both the ground-surface portions of plant roots and stems provides essential support for a wide range of agricultural applications, including intelligent weeding, agricultural robot navigation, crop growth monitoring, and plant phenotyping. However, agricultural environments are characterized by significant illumination variations, complex backgrounds, severe occlusions, and the high morphological similarity between roots and soils, all of which make robust detection particularly challenging. In addition, publicly available datasets for the detection of GSPR and stems remain limited. Consequently, research on object detection of the GSPR and stems is still in its early stages. A comprehensive review of detection techniques for the GSPR and stems is still lacking. This paper presents a systematic review of recent advances in the detection of ground-surface portions of plant roots GSPR and stems. It covers GSPR and stems datasets, the application of sensing technologies, the development of detection algorithms, and existing practical application scenarios. In addition, this review evaluates dataset complexity and algorithmic robustness, and discusses the current challenges and future research directions. Overall, this review aims to systematically summarize recent advances in GSPR and stem detection, analyze mainstream sensing technologies and detection algorithms, and provide a comprehensive reference for future research and practical applications in precision agriculture.

A five-keypoint geometric perception method for integrated graded robotic harvesting of ridge-cultivated strawberries。Computers and Electronics in Agriculture

研究非结构化农田的视觉感知、深度学习导航线识别与多传感器融合定位，结合模型预测路径跟踪与导航-作业协同控制，田间试验验证其精度与鲁棒性。

围绕非结构化农田与复杂场景，综述农业机器人自主感知、导航、作业与集群协同的关键技术进展与落地挑战，指出轻量化、智能化与多机协同是重点方向。

浙江省农业科学院农业装备研究所研发组培种苗定植机器人,借视觉与力反馈实现丝兰、马铃薯苗自动定植,位姿识别精度超95%,单株5—7秒、效率为人工3—4倍、损伤率低于5%。

农民日报报道进博会多项农业前沿成果落地：AI辅助育种、数智化养猪平台、农田智能机器人、果品无损智检，AI正从良种培育到采收分级嵌入现代农业全链条。

Year-round utilization of agricultural robotic platforms requires adaptable systems capable of performing multiple operations with interchangeable end-effectors. Although mechanical tool-changing mechanisms are well established, software interoperability, communication, and adaptive perception remain challenges. This narrative review examines software architectures, communication protocols, and edge intelligence technologies relevant to modular agricultural end-effectors. Publications identified through Scopus and Web of Science, complemented by citation exploration, are synthesized across five areas: hardware abstraction and middleware integration, deterministic fieldbuses, distributed network communication, edge computing and artificial intelligence (AI) deployment, and visual servoing. The literature highlights the need to separate task coordination from actuator control and to select communication protocols according to timing and bandwidth requirements. Edge computing, model optimization, and modular perception services can support AI deployment on resource-constrained robotic platforms. However, existing approaches primarily address individual integration challenges rather than complete software reconfiguration following tool exchange. Based on these findings, this review proposes the Modular Agricultural End-Effector Software Architecture (MAESA), a conceptual reference framework integrating automated tool identification, hardware abstraction, communication, perception, and control. Its theoretical contribution lies in unifying previously fragmented integration approaches, while its practical significance is providing design guidance for autonomous tool exchange and year-round agricultural operations.

“我们想让至少80%的农业流程实现自动化，希望和中国机器人领域的供应商进行联合研发。” “我们用人工智能提升印制电路板（PCB）的检测效率，全球50%以上的PCB产自中国。” “我们...

芦笋田垄间，机器人往来穿梭，采收、转运、分拣环环相扣。近日，由农业农村部南京农业机械化研究所农业机器人创新团队研制的芦笋智能采收机器人、多足转运机器人、芦笋智能分拣机器人集中亮相，在田间...

Inflorescence trimming is essential for producing high-quality table grapes, but it is labor-intensive and demands skilled labor. Automating it is difficult: grape inflorescences have a complex branching structure, are frequently occluded, and are viewed under highly variable illumination, and the cutting tool must be positioned precisely. This study presents perception and motion control methods for a grape inflorescence trimming robot. The methods localize the cutting point on the inflorescence and position the cutting tool at that point, using a dual-range framework. At far range, a detection model identifies the target inflorescence and guides the manipulator to a suitable observation distance; at close range, a segmentation-based method localizes the cutting point on the main stem. This study covers cutting-point localization and tool positioning only. The robot stopped when the scissors reached the cutting point; the stem was not cut, so the trimming result itself was not evaluated. To improve perception robustness, multi-frame detection and real-time illumination augmentation were introduced. Two motion control strategies were developed and compared: sequential trajectory control (STC) and hybrid feedback control (HFC), the latter using real-time visual feedback for continuous motion correction. The system was evaluated in a greenhouse vineyard on 30 preselected inflorescences of the table grape cultivar Shine Muscat grown under a pergola training system. The mobile platform was positioned manually in front of each target. Each inflorescence was processed once by each control strategy, yielding 60 trials in total. Positioning was counted as successful when the main stem was between the scissor blades and within the effective cutting range. STC achieved a positioning success rate of 90.0 %, a mean positional error of 2.1 cm, and a mean operation time of 31.9 s. HFC achieved a positioning success rate of 83.3 %, a smaller mean positional error of 1.4 cm, and a longer mean operation time of 35.4 s. In successful trials, HFC placed the scissors where a cut would keep exactly the two uppermost lateral branches in 52.0 % of cases, compared with 33.3 % for STC. Visual feedback therefore reduced positioning error but did not increase positioning success or shorten operation time. Real-time illumination augmentation raised the target detection rate from 41.6 % to 100.0 % across 125 frames covering cloudy and sunny conditions at multiple locations in the vineyard, and multi-frame aggregation eliminated the 3.0 % single-frame target selection error. Perception took 58.5 % of the total operation time under STC and was the main time bottleneck. These results show that the proposed methods can localize the cutting point and position the cutting tool on a single cultivar in a greenhouse vineyard under natural illumination and occlusion.

研制了约410马力无人履带式农业动力平台，配机电传动及果园作业机具。

Aside from perhaps some chatter or music playing, generally greenhouses can be more muted spaces for growing. However, when you've got robots running them? They're even quieter, as evidenced with a peek inside Hippo Harvest's robotics and machine learning-powered greenhouses in Pescadero, California.…

提出结合RGB-D定位与遗传算法的机器人采收排序方法，优化高密度果园采摘路径。

系统回顾2021—2025年除草机器人感知、定位、决策与执行技术进展，比较机械、激光、视觉喷药等路线，指出多模态融合与低成本落地是未来重点。

研发UWB与视觉融合导航的自主供苗底盘，解决温室移栽运苗劳动强度大问题。

2026年全国粮油和大豆产业博览会11月1日在郑州闭幕，以“发展粮油产业、保障粮食安全”为主题。展会集中展示智能巡检犬、具身智能播种机器人、智能温室管理系统等装备，我国农业科技进步贡献率已超64%，“十五五”规划明确加快发展农业新质生产力。

提出融合时序动态图神经网络语义分割与导航线提取的自主农业机器人框架。

浙江省农科院与农业AI企业麦麦科技签署战略协议，围绕大田与设施农业场景联合研发智能农机及农业机器人，开展概念验证与中试示范，推动科研成果落地。

用全生命周期成本与环境评估，分析小型电池农业机器人用于四种作物生产的可行性。

浙江省农科院农业装备研究所携8款适用农机亮相永康中国丘陵山区农业机械博览会，其中种苗定植机器人实现国产替代、价格仅进口同类设备40%，并涵盖组培清洗线、激光除草、精准投饲等智能装备。