• 《中国科学引文数据库(CSCD)》来源期刊
  • 中国科技期刊引证报告(核心版)期刊
  • 《中文核心期刊要目总览》核心期刊
  • RCCSE中国核心学术期刊

基于改进粒子群算法的高地隙无人喷雾机对不规则凸田块的全覆盖作业路径规划

刘国海, 万亚连, 沈跃, 刘慧, 何思伟, 张亚飞

刘国海, 万亚连, 沈跃, 等. 基于改进粒子群算法的高地隙无人喷雾机对不规则凸田块的全覆盖作业路径规划[J]. 华南农业大学学报, 2025, 46(3): 390-398. DOI: 10.7671/j.issn.1001-411X.202409017
引用本文: 刘国海, 万亚连, 沈跃, 等. 基于改进粒子群算法的高地隙无人喷雾机对不规则凸田块的全覆盖作业路径规划[J]. 华南农业大学学报, 2025, 46(3): 390-398. DOI: 10.7671/j.issn.1001-411X.202409017
LIU Guohai, WAN Yalian, SHEN Yue, et al. Complete coverage path planning of irregular convex field for the high clearance unmanned sprayer based on improved particle swarm optimizer algorithm[J]. Journal of South China Agricultural University, 2025, 46(3): 390-398. DOI: 10.7671/j.issn.1001-411X.202409017
Citation: LIU Guohai, WAN Yalian, SHEN Yue, et al. Complete coverage path planning of irregular convex field for the high clearance unmanned sprayer based on improved particle swarm optimizer algorithm[J]. Journal of South China Agricultural University, 2025, 46(3): 390-398. DOI: 10.7671/j.issn.1001-411X.202409017

基于改进粒子群算法的高地隙无人喷雾机对不规则凸田块的全覆盖作业路径规划

基金项目: 

国家自然科学基金(52377054)

详细信息
    作者简介:

    刘国海,主要从事智能农机装备研究,E-mail: ghailiu@ujs.edu.cn

  • 中图分类号: S232

Complete coverage path planning of irregular convex field for the high clearance unmanned sprayer based on improved particle swarm optimizer algorithm

  • 摘要:
    目的 

    满足高地隙无人喷雾机自主导航全覆盖作业的应用需求并优化农机作业效率。

    方法 

    提出了一种针对不规则凸田块的全覆盖遍历路径规划算法。首先,通过获取农田区域的边界数据,得到不规则凸田块的边界轮廓模型;其次,在传统U型转弯方式的基础上,引入作业行与田块边界的夹角,对作业行间的衔接路径原理进行详细阐述;由经过不规则凸区域中心点的直线进行平行线偏移,生成随机方向角的全覆盖作业行后,通过改进的粒子群优化(Particle swarm optimizer,PSO)算法对作业行方向角进行最优化,规划出遍历田块的全覆盖作业路径;最后,将算法在4块典型实际田块中进行仿真测试。

    结果 

    与传统路径规划算法相比,改进PSO算法在1~4个田块的总遍历距离分别减少9.01、23.25、8.71和14.32 m,转弯次数减少率分别下降11.1%、61.5%、16.7%和5.3%,额外覆盖比分别减少0.20、0.96、0.45和1.96个百分点,有效减少了无人农机的能量消耗、提高了作业效率。

    结论 

    在作业区域被完全覆盖的前提下,本算法能规划出无人农机行驶路程较短、覆盖率较高和转弯次数较少的作业路径,可为无人农机的路径规划技术的发展提供理论支撑。

    Abstract:
    Objective 

    In order to meet the application requirements of autonomous navigation full-coverage operation of high clearance unmanned sprayers and optimize the efficiency of agricultural machine operation.

    Method 

    A complete coverage traversal path planning algorithm for irregular convex fields was proposed. Firstly, an boundary contour model of irregularly convex field was obtained based on the boundary data of farmland area. Secondly, on the basis of the traditional U-turn pattern, the angle between the operation rows and the field boundaries was introduced to elaborate the principles of articulated paths between the operation rows in detail. After generating complete coverage operation rows with random direction angles by parallel line offset from the straight line passing through the center point of the irregular convex region, the direction angles of the operation rows were optimized by the improved particle swarm optimizer (PSO) algorithm, and the field traversal complete coverage working paths were generated. Finally, the algorithm was tested through simulations on four typical real-world fields.

    Result 

    Compared with traditional path planning algorithms, the proposed algorithm reduced the total traversal distance by 9.01, 23.25, 8.71 and 14.32 m in fields 1 to 4, respectively. The reduction rates of the number of turns were 11.1%, 61.5%, 16.7% and 5.3%, while the additional coverage rates decreased by 0.20, 0.96, 0.45 and 1.96 percentage points, respectively. These improvements effectively reduced the energy consumption of unmanned agricultural machinery and enhanced operational efficiency.

    Conclusion 

    Under the premise of complete coverage for the operation area, the proposed algorithm can generate operation paths for unmanned agricultural machinery with shorter travel distances, higher coverage rates and fewer turns. This provides a theoretical support for the development of path planning technology for unmanned agricultural machinery.

  • 图  1   作业行间路径衔接方式

    $ \gamma $为$ \overrightarrow {OM} $与$ \overrightarrow {MN} $的夹角,$ \overrightarrow {OM} $为农机在作业行区域的行驶方向,$ \overrightarrow {MN} $既表示农机在地头转弯区域的行驶方向,也表示地块边界的延伸方向,Pi表示农机行驶在直线和圆弧路径的起点和终点,Oi表示农机转弯时的圆心,l1表示作业行幅宽,R为农机的最小转弯半径。

    Figure  1.   Path connection method between operation rows

    $ \gamma $ is the angle between $ \overrightarrow {OM} $ and $ \overrightarrow {MN} $, $ \overrightarrow {OM} $ is the driving direction of agricultural machinery in the operation row area, $ \overrightarrow {MN} $ not only indicates the driving direction of agricultural machinery in the turn area of the field edge, but also indicates the extension direction of the land boundary, Pi represents the starting point and ending point of the agricultural machinery traveling in a straight line path and an arc path, Oi represents the circle center when the agricultural machinery turns, l1 represents the width of the operation row, and R represents the minimum turning radius of the agricultural machinery.

    图  2   相邻作业行衔接图

    MN为不规则凸田块曲线边界,L1L2为相邻作业行,A1B1为作业行直线与曲线边界的交点,P1P2P3P4为圆弧路径,P2P3为直线路径,O1O2为圆弧路径圆心,α为作业行直线与水平线的夹角,βA1B1直线与水平线的夹角。

    Figure  2.   Graph of connection between adjacent operation rows

    MN is the curve boundary of irregular convex field, L1 and L2 are adjacent operation rows, A1 and B1 are the intersections of straight lines and curve boundaries of operation rows, P1P2 and P3P4 are arc paths, P2P3 are straight paths, O1 and O2 are the circle center of arc paths, α is the angle between straight lines and horizontal lines of operation rows, and β is the angle between straight lines and horizontal lines of A1B1.

    图  3   相邻作业行生成图

    d为无人农机的作业幅宽,θ为作业行垂线与水平线的夹角,∆b为直线截距差值,(x0,y0)为田块中心点坐标,yyy为直线方程。

    Figure  3.   Graph of generation of adjacent operation rows

    d is the working width of the unmanned agricultural machinery, θ is the angle between the vertical line and the horizontal line of the operation row, ∆b is the difference of linear intercept, (x0,y0) is the coordinate of the center point of the field, and y, y and y are linear equations.

    图  4   仿真试验场地地形

    Figure  4.   Terrain of test sites for simulation

    图  5   最优作业行方向角全覆盖遍历结果

    Figure  5.   The full-coverage traversal results of optimal direction angle in operation path

    图  6   路径总长度迭代关系图

    Figure  6.   Relationship between total path length and iteration

    表  1   不规则凸田块全覆盖遍历结果

    Table  1   The full coverage traversal results in irregular convex fields

    田块序号
    Field code
    转弯半径(R)/m
    Turning radius
    作业幅宽/m
    Operation width
    总遍历距离/m
    Total traversal distance
    转弯次数
    Number of turns
    额外覆盖比/%
    Additional coverage ratio
    转弯次数减少率/%
    Rate of reduction in
    the number of turns
    传统方法Traditional method 改进方法Improved method 传统方法Traditional method 改进方法Improved method 传统方法Traditional method 改进方法Improved method
    1 0.8 1.8 457.37 448.36 18 16 2.62 0.06 11.1
    2 0.8 1.8 1019.81 996.56 39 15 1.63 0.67 61.5
    3 2.2 5.0 1944.19 1935.48 30 25 0.52 0.07 16.7
    4 2.2 5.0 807.81 793.49 19 18 10.50 8.54 5.3
    下载: 导出CSV
  • [1] 周俊, 何永强. 农业机械导航路径规划研究进展[J]. 农业机械学报, 2021, 52(9): 1-14. doi: 10.6041/j.issn.1000-1298.2021.09.001
    [2] 孟志军, 刘卉, 王华, 等. 农田作业机械路径优化方法[J]. 农业机械学报, 2012, 43(6): 147-152. doi: 10.6041/j.issn.1000-1298.2012.06.027
    [3] 刘洋洋, 茹煜, 刘彬, 等. 直升机航空施药全覆盖航线规划算法[J]. 农业工程学报, 2020, 36(17): 73-80. doi: 10.11975/j.issn.1002-6819.2020.17.009
    [4] 翟卫欣, 王东旭, 陈智博, 等. 无人驾驶农机自主作业路径规划方法[J]. 农业工程学报, 2021, 37(16): 1-7. doi: 10.11975/j.issn.1002-6819.2021.16.001
    [5]

    UTAMIMIA A, REINERS T, ANSARIPOOR A H. Evolutionary neighborhood discovery algorithm for agricultural routing planning in multiple fields[J]. Annals of Operations Research, 2022, 316(2): 955-977. doi: 10.1007/s10479-022-04685-5

    [6]

    SEYYEDHASANI H, DVORAK J S, ROEMMELE E. Routing algorithm selection for field coverage planning based on field shape and fleet size[J]. Computers and Electronics in Agriculture, 2019, 156: 523-529. doi: 10.1016/j.compag.2018.12.002

    [7]

    JIN J, TANG L. Optimal coverage path planning for arable farming on 2D surfaces[J]. Transactions of the ASABE, 2010, 53(1): 283-295. doi: 10.13031/2013.29488

    [8]

    GRAF PLESSEN M. Optimal in-field routing for full and partial field coverage with arbitrary non-convex fields and multiple obstacle areas[J]. Biosystems Engineering, 2019, 186(2): 234-245.

    [9]

    POUR ARAB D, SPISSER M, ESSERT C. Complete coverage path planning for wheeled agricultural robots[J]. Journal of Field Robotics, 2023, 40(6): 1460-1503.

    [10] 罗承铭, 熊陈文, 黄小毛, 等. 四边形田块下油菜联合收获机全覆盖作业路径规划算法[J]. 农业工程学报, 2021, 37(9): 140-148. doi: 10.11975/j.issn.1002-6819.2021.09.016
    [11] 黄小毛, 张垒, 王绍帅, 等. 凸多边形田块下油菜联合直播机组作业路径规划[J]. 农业机械学报, 2022, 53(1): 33-40.
    [12] 陈凯, 解印山, 李彦明, 等. 多约束情形下的农机全覆盖路径规划方法[J]. 农业机械学报, 2022, 53(5): 17-26.
    [13]

    LI Y M, WU T, XIAO Y F, et al. Path planning in continuous adjacent farmlands and robust path-tracking control of a rice-seeding robot in paddy field[J]. Computers and Electronics in Agriculture, 2023, 210: 107900. doi: 10.1016/j.compag.2023.107900

    [14]

    HAN Y, SHAO M, WU Y, et al. An improved complete coverage path planning method for intelligent agricultural machinery based on backtracking method[J]. Information, 2022, 13(7): 313. doi: 10.3390/info13070313

    [15] 李胜伶, 李金广, 赵立军, 等. 基于改进鲸鱼优化算法的丘陵山区田块全覆盖作业路径规划[J]. 农业工程学报, 2024, 40(17): 61-70.
    [16]

    CHAKRABORTY S, ELANGOVAN D, GOVINDARAJAN P L, et al. A comprehensive review of path planning for agricultural ground robots[J]. Sustainability, 2022, 14(15): 9156.

    [17] 商高高, 刘刚, 韩江义, 等. 园艺电动拖拉机作业全覆盖路径规划算法研究[J]. 农机化研究, 2022, 44(9): 35-40.
    [18] 宫金良, 王伟, 张彦斐, 等. 基于农田环境的农业机器人群协同作业策略[J]. 农业工程学报, 2021, 37(2): 11-19.
    [19]

    SEYEDHASANI H, DVORAK J S. Using the vehicle routing problem to reduce field completion times with multiple machines[J]. Computers and Electronics in Agriculture, 2017, 134: 142-150. doi: 10.1016/j.compag.2016.11.010

    [20] 夏娜, 束强, 赵青, 等. 基于维诺图和二分图的水面移动基站路径规划方法[J]. 自动化学报, 2016, 42(8): 1185-1197.
    [21] 景亮, 张亚飞, 沈跃, 等. 四轮独立驱动高地隙无人喷雾机轨迹跟踪自适应控制[J]. 农业机械学报, 2021, 52(12): 408-416. doi: 10.6041/j.issn.1000-1298.2021.12.043
    [22] 周龙港, 刘婷, 卢劲竹. 基于Floyd和改进遗传算法的丘陵地区农田遍历路径规划[J]. 智慧农业(中英文), 2023, 5(4): 45-57.
    [23] 贺磊盈, 杨太玮, 武传宇, 等. 基于贪心遗传算法的穴盘苗补栽路径优化[J]. 农业机械学报, 2017, 48(5): 36-43. doi: 10.6041/j.issn.1000-1298.2017.05.004
    [24] 金宝龙, 夏长高, 韩江义. 多机协同作业全覆盖路径规划[J]. 农机化研究, 2024, 46(12): 28-33. doi: 10.3969/j.issn.1003-188X.2024.12.006
    [25] 谢金燕, 刘丽星, 杨欣, 等. 基于改进粒子群算法的果园割草机作业路径规划[J]. 中国农业大学学报, 2023, 28(11): 182-191.
    [26] 王殿君. 基于改进A*算法的室内移动机器人路径规划[J]. 清华大学学报(自然科学版), 2012, 52(8): 1085-1089.
    [27] 褚宏悦, 易军凯. 无人机安全路径规划的混沌粒子群优化研究[J]. 控制工程, 2024, 31(6): 1027-1034.
    [28]

    RATNAWEERA A, HALGAMUGE S K, WATSON H C. Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients[J]. IEEE Transactions on Evolutionary Computation, 2004, 8(3): 240-255. doi: 10.1109/TEVC.2004.826071

    [29]

    MICHEL T, PHILIPPE S, HELENE F, et al. Path planning for complete with agricultural machines[J]. Springer Tracts in Advanced Robotics, 2006, 24: 549-558.

图(6)  /  表(1)
计量
  • 文章访问数:  94
  • HTML全文浏览量:  11
  • PDF下载量:  34
  • 被引次数: 0
出版历程
  • 收稿日期:  2024-09-12
  • 网络出版日期:  2025-03-12
  • 发布日期:  2025-02-27
  • 刊出日期:  2025-05-09

目录

    /

    返回文章
    返回