基于视觉—RTK的苹果园植保机器人自主导航研究

doi:10.13733/j.jcam.issn.2095-5553.2025.06.028

摘要/Abstract

摘要：

针对标准化的宽行矮化密植苹果种植模式的特点，设计一种基于视觉—RTK的自主导航植保机器人自主导航系统。导航任务分为2个部分：行间直行阶段应用U—Net语义分割网络提取边缘线拟合出导航线控制行间植保机器人的航向；行头行尾转弯阶段通过预设RTK全局目标点对植保机器人运动轨迹进行控制，发挥组合导航的优势。结果表明，基于RTK全局规划的平均横向偏差为0.1 m，最大偏差为0.3 m；而基于视觉导航的平均横向偏差为0.5 m，最大偏差为0.9 m。植保机器人导航系统基本满足苹果园自动导航任务的要求，具有一定的可行性。

关键词: 植保机器人, 果园导航, 路径规划, 语义分割, 苹果

Abstract:

Aiming at the characteristics of standardized wide‑row dwarfing and densely planted apple planting mode, an autonomous navigation system for plant protection robot based on visual—RTK was designed in this paper. The navigation task was divided into two parts as follows: in the straight line stage, the edge lines extracted by U—Net semantic segmentation network were used to fit the navigation lines for independent navigation between rows. The motion trajectory of plant protection robot was controlled by RTK positioning point in the turning stage of the row head and tail, and the advantages of integrated navigation were exerted respectively. The results showed that the average lateral deviation of the global planning based on RTK was 0.1 m and the maximum deviation was 0.3 m, while the average lateral deviation of the visual navigation was 0.5 m and the maximum deviation was 0.9 m. The plant protection robot navigation system basically met the requirements of the automatic navigation task of the apple orchard and had certain feasibility.

Key words: plant protection robot, orchard navigation, path planning, semantic segmentation, apple

中图分类号:

S24
TP29

黄鹏飞, 薛新宇, 崔龙飞. 基于视觉—RTK的苹果园植保机器人自主导航研究[J]. 中国农机化学报, 2025, 46(6): 187-192.

Huang Pengfei, , Xue Xinyu, Cui Longfei. Research on autonomous navigation of plant protection robot in apple orchard based on Vision—RTK[J]. Journal of Chinese Agricultural Mechanization, 2025, 46(6): 187-192.

参考文献

[ 1 ] 韩树丰, 何勇, 方慧.农机自动导航及无人驾驶车辆的发展综述[J]. 浙江大学学报(农业与生命科学版), 2018, 44(4): 381-391.

[ 2 ] 王宝梁, 索明何, 刘大诚. 基于开放式结构的多功能农业机器人设计[J]. 中国农机化学报, 2019, 40(3): 179-184.

Wang Baoliang, Suo Minghe, Liu Dacheng. Design of a multifunctional agricultural robot [J]. Journal of Chinese Agricultural Mechanization, 2019, 40(3): 179-184.

[ 3 ] 孟志军. 农机信息化智能化应用发展趋势[J]. 农机市场, 2022(3): 25-26.

[ 4 ] 赖汉荣, 张亚伟, 张宾, 等. 玉米除草机器人视觉导航系统设计与试验[J]. 农业工程学报, 2023, 39(1): 18-27.

Lai Hanrong, Zhang Yawei, Zhang Bin, et al. Design and experiment of the visual navigation system for a maize weeding robot [J]. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(1): 18-27.

[ 5 ] 周俊, 胡晨. 密植果园作业机器人行间定位方法[J]. 农业机械学报, 2015, 46(11): 22-28.

[ 6 ] 李会宾, 韩伟, 史云. 果园作业机器人的自主行间导航系统研究[J]. 中国农业信息, 2019, 31(4): 51-64.

[ 7 ] Malavazi F B P, Guyonneau R, Fasquel J B, et al. LiDAR‑only based navigation algorithm for an autonomous agricultural robot [J]. Computers and Electronics in Agriculture, 2018, 154: 71-79.

[ 8 ] Mostafa S, Chen X, Christopher P, et al. Modelling and simulation of a non‑holonomic omnidirectional mobile robot for offline programming and system performance analysis [J]. Simulation Modelling Practice and Theory, 2018, 87: 155-169.

[ 9 ] Shalal N, Low T, Mccarthy C, et al. Orchard mapping and mobile robot localisation using on‑board camera and laser scanner data fusion—Part A: Tree detection[J]. Computers and Electronics in Agriculture, 2015, 119: 254-266.

[10] 韩振浩, 李佳, 苑严伟, 等. 基于U—Net网络的果园视觉导航路径识别方法[J]. 农业机械学报, 2021, 52(1): 30-39.

Han Zhenhao, Li Jia, Yuan Yanwei, et al. Path recognition of orchard visual navigation based on U—Net [J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(1): 30-39.

[11] 肖珂, 夏伟光, 梁聪哲. 复杂背景下果园视觉导航路径提取算法[J]. 农业机械学报, 2023, 54(6): 197-204, 252.

Xiao Ke, Xia Weiguang, Liang Congzhe. Visual navigation path extraction algorithm in orchard under complex background [J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(6): 197-204, 252.

[12] 彭顺正, 坎杂, 李景彬. 矮化密植枣园收获作业视觉导航路径提取[J]. 农业工程学报, 2017, 33(9): 45-52.

Peng Shunzheng, Kan Za, Li Jingbin. Extraction of visual navigation directrix for harvesting operation in short‑stalked and close‑planting jujube orchard [J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 33(9): 45-52.

[13] Jiang A, Noguchi R, Ahamed T. Tree trunk recognition in orchard autonomous operations under different light conditions using a thermal camera and Faster R—CNN [J]. Sensors， 2022, 22(5): 2065.

[14] 沈文龙, 薛金林, 汪东明, 等. 农业车辆视觉导航控制系统[J]. 中国农机化学报, 2016, 37(6): 251-254.

Shen Wenlong, Xue Jinlin, Wang Dongming, et al. Visual navigation control system of agricultural vehicles [J]. Journal of Chinese Agricultural Mechanization, 2016, 37(6): 251-254.

[15] Li S, Zhang M, Ji Y, et al. Agricultural machinery GNSS/IMU‑integrated navigation based on fuzzy adaptive finite impulse response Kalman filtering algorithm [J]. Computers and Electronics in Agriculture, 2021, 191: 106524.

[16] 郭祥雨, 薛新宇. 基于机器视觉的水稻制种田导航线提取方法[J]. 中国农机化学报, 2021, 42(5): 197-201.

Guo Xiangyu, Xue Xinyu. Extraction of navigation lines for rice seed farming based on machine vision [J]. Journal of Chinese Agricultural Mechanization, 2021, 42(5): 197-201.

[17] 姚杰, 张春雨, 彭勇, 等. 基于计算机视觉的小麦收获边缘导航线提取方法[J]. 中国农机化学报, 2024, 45(2): 215-220.

Yao Jie, Zhang Chunyu, Peng Yong, et al. Extraction method of wheat harvesting edge navigation line based on computer vision [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(2): 215-220.

[18] Cao Chao, Trautman P, Iba S. Dynamic channel: A planning framework for crowd navigation [J]. 2019 International Conference on Robotics and Automation, 2019: 5551-5557.

[19] Du Y, Saha S S, Sandha S S, et al. Neural‑kalman GNSS/INS navigation for precision agriculture [J].2023 IEEE International Conference on Robotics and Automation, 2023: 9622-9629.

[1]	刘士琪, 闫九祥, 李倩, 温以民, 刘强. 基于A*与DWA算法融合的割草机器人路径规划[J]. 中国农机化学报, 2025, 46(6): 142-149.
[2]	裴文杰, 刘拥民, 胡魁, 石婷婷, . 面向复杂背景的CFFA—ResNet苹果叶片病害识别模型构建[J]. 中国农机化学报, 2025, 46(6): 169-175.
[3]	王封疆, 王梦飞, 周杰. 基于群智能的农机视觉导航关键算法研究及应用[J]. 中国农机化学报, 2025, 46(5): 92-99.
[4]	项新建, 肖家乐, 汤卉, 胡海斌, 张颖超, 袁天顺. 基于改进BiSeNetV2的甜菜与杂草识别方法研究[J]. 中国农机化学报, 2025, 46(4): 101-107.
[5]	周俊昌, 曾维, 彭鹏, 庞记成, 刘军军, 杨熙临. 苹果叶片病害检测的轻量化YOLOv5研究与实现[J]. 中国农机化学报, 2025, 46(4): 126-132.
[6]	马黎, 崔雅博. 植保无人机群协同作业的路径规划与控制方法[J]. 中国农机化学报, 2025, 46(4): 139-145.
[7]	傅泓龙, 胡裕兵, 谢立敏, 蔡云, 方兵, . 番茄温室机器人的多传感器融合建图与导航研究[J]. 中国农机化学报, 2025, 46(4): 171-178.
[8]	冯昊栋, 郑航, 张毅, 薛向磊, 童俊华, 俞国红, . 垄作模式设施植保机器人设计与导航系统试验[J]. 中国农机化学报, 2025, 46(3): 71-78.
[9]	任晶晶, 张小勇, 贾伟宽. 基于多粒度特征感知的FoveaBox绿色苹果抗遮挡检测模型[J]. 中国农机化学报, 2025, 46(3): 182-187.
[10]	沈中华, 程虎强, , 夏爱强, 李涵. 基于RGE—UNet模型的甘蔗蔗梢识别研究[J]. 中国农机化学报, 2025, 46(3): 188-194.
[11]	刘树腾, 李建平, 张阔, 李绍波, 谢金燕, 张詝. 果筐搬运夹持装置结构参数优化与试验[J]. 中国农机化学报, 2025, 46(2): 56-63.
[12]	谷瑞, 顾家乐, 宋翠玲, 钱春花. 基于坐标注意力的多尺度轻量级苹果叶片病害识别模[J]. 中国农机化学报, 2025, 46(2): 173-180.
[13]	曾德斌, 陆万荣, 郑良芳, 施明登, 陈文绪, . 基于U2—DSCNet植物叶片分割方法研究[J]. 中国农机化学报, 2025, 46(2): 253-258.
[14]	段小勇, 何超, 刘学渊. 基于改进DeepLabV3+的非结构化道路可行驶区域检测[J]. 中国农机化学报, 2025, 46(2): 271-278.
[15]	赵宁磊, 程曼, 袁洪波, 王媛, 蔡振江. 羊舍自主巡检机器人设计与试验[J]. 中国农机化学报, 2025, 46(1): 78-84.