基于自适应升温模拟退火算法的农业机器人全区域覆盖策略

王伟; 张彦斐; 宫金良; 兰玉彬

doi:10.7671/j.issn.1001-411X.202104022

基于自适应升温模拟退火算法的农业机器人全区域覆盖策略

王伟^1,,
张彦斐²,
宫金良^1, ,,
兰玉彬^{2, 3}

1.
山东理工大学机械工程学院，山东淄博 255000
2.
山东理工大学农业工程与食品科学学院，山东淄博 255000
3.
华南农业大学电子工程学院/人工智能学院，广东广州 510642

基金项目: 国家自然科学基金(61303006)；山东省重点研发计划(重大科技创新工程)(2020CXGC010804)；山东省引进顶尖人才“一事一议”专项经费资助项目(鲁政办字[2018]27号)；山东省重点研发计划(2019GNC106127)；淄博市生态无人农场研究院项目(2019ZBXC200)

详细信息

作者简介:
王伟(1996—)，男，硕士研究生，E-mail: wangw_0229@qq.com

通讯作者:
宫金良(1976—)，男，副教授，博士，E-mail: gjlwing@qq.com

中图分类号: S24;TP242
计量
- 文章访问数: 1518
- HTML全文浏览量: 2
- PDF下载量: 683
出版历程
- 收稿日期: 2021-04-20
- 网络出版日期: 2023-05-17
- 刊出日期: 2021-11-09

Whole area coverage strategy of agricultural robot based on adaptive heating simulated annealing algorithm

1.
School of Mechanical Engineering, Shandong University of Technology, Zibo 255000, China
2.
School of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, China
3.
College of Electronic Engineering/College of Artificial Intelligence, South China Agricultural University, Guangzhou 510642, China

摘要

摘要:
目的
提出一种复杂农田环境下农业机器人全区域覆盖策略，以便合理规划农业机器人的工作遍历路径。

方法
根据农田实际生产环境定义农业机器人复杂工作环境模型，并在此基础上建立一级分区与二级分区的概念。引入遗传算法变异操作的思想，建立基于贪婪机制的模拟退火算法优质可行解生成方法；建立解集多样性的概念，设计基于自适应升温的模拟退火算法改进方法，以此求解分区间的最佳遍历顺序问题。通过A*算法与八邻域搜索法相结合进行农业机器人跨区域衔接路径规划，依此，实现机器人覆盖全区域。

结果
仿真结果表明，改进的模拟退火算法所规划的路径长度分别比传统遗传算法和模拟退火算法减少了14.7%和10.1%，收敛时的迭代次数分别减少9.8%和59.1%；农业机器人全区域覆盖仿真试验中遍历路径重复率为14.86%。高地隙喷药机器人现场遍历试验中，路径重复率为15.83%。

结论
研究结果可为农业机器人在复杂农田环境中全遍历覆盖提供研究思路。
- 农业机器人 /
- 路径规划 /
- 模拟退火算法 /
- A*算法 /
- 路径重复率
Abstract:
Objective
To propose a whole area coverage strategy of agricultural robot in complex farmland environment, and reasonably plan the working traversal path of agricultural robot.

Method
The complex farmland working environment model was defined according to the actual production environment of agricultural robot, and the concepts of first-level partition and second-level partition were established. The idea of genetic algorithm mutation operation was introduced to establish a high-quality feasible solution generation method of simulated annealing algorithm based on greedy mechanism. Based on the establishment of the concept of solution set diversity, an improved method of simulated annealing algorithm based on adaptive heating was designed to solve the problem of the optimal traversal sequence between partitions. The A* algorithm was combined with the eight-neighbor search method to plan the cross-regional connection path of agricultural robot. By this way, the scheme designed in this paper could achieve that the robot covered the whole working area.

Result
The simulation results showed that, compared with the traditional genetic algorithm and simulated annealing algorithm, the path length planned by the improved simulated annealing algorithm was reduced by 14.7% and 10.1% respectively, and the number of iterations during convergence was reduced by 9.8% and 59.1% respectively. The repeating rate of the traversal path of the agricultural robot in the simulation test of whole area coverage was 14.86%. The path repetition rate in the field traversal test of the high ground-clearance spraying robot was 15.83%.

Conclusion
The research results can provide a research idea for the full traversal coverage of agricultural robot in complex farmland environment.
- agricultural robot /
- path planning /
- simulated annealing algorithm /
- A* algorithm /
- path repetition rate

HTML全文

图 1 栅格化农田建模(a)与障碍物膨胀处理(b)

Figure 1. Rasterized farmland modeling (a) and obstacle expansion treatment (b)

下载: 全尺寸图片幻灯片

图 2 栅格分区(a)与栅格分区合并(b)

Figure 2. Grid partition (a) and grid partition merging (b)

下载: 全尺寸图片幻灯片

图 3 模拟退火算法新解生成方法

Figure 3. New solution generation methods of simulated annealing algorithm

下载: 全尺寸图片幻灯片

图 4 3种算法对40个分区的最优遍历路径规划图

Figure 4. The optimal traversal path planning diagram of 40 partitions by three algorithms

下载: 全尺寸图片幻灯片

图 5 遍历路径规划图

Figure 5. Traversal path planning diagram

下载: 全尺寸图片幻灯片

图 6 农业机器人试验现场

1、4和5：障碍物放大图；2：虚拟道路分割线；3：农业机器人

Figure 6. Experimental site of agricultural robot

1, 4 and 5: Obstacle amplification diagrams; 2: Virtual road dividing line; 3: Agricultural robot

下载: 全尺寸图片幻灯片

表 1 3种算法对不同分区规模的路径规划结果

Table 1 Planning results of three algorithms for different partitioning sizes

算法 Algorithm	分区数量 Partition quantity	路径长度/m Path length	收敛时的迭代次数 Number of iterations at convergence
模拟退火算法 Simulated annealing algorithm	20	294.831 6	60
	30	432.577 6	62
	40	523.952 9	82
传统遗传算法 Traditional genetic algorithm	20	296.114 4	66
	30	426.808 4	143
	40	497.097 1	181
改进模拟退火算法 Improved simulated annealing algorithm	20	292.252 7	22
	30	418.056 9	40
	40	447.120 9	74

下载: 导出CSV

参考文献(20)

[1]	LAN Y B, CHEN S D. Current status and trends of plant protection UAV and its spraying technology in China[J]. International Journal of Precision Agricultural Aviation, 2018, 1(1): 1-9.
[2]	GONG J L, WANG M X, ZHANG Y F, et al. Flow and sound field analysis of agricultural ultrasonic atomizing nozzle[J]. International Journal of Precision Agricultural Aviation, 2019, 2(2): 32-37.
[3]	胡平志, 杨小柳, 李泽滔. 复杂山地环境下的机器人路径规划[J]. 计算机仿真, 2021, 38(3): 286-291. doi: 10.3969/j.issn.1006-9348.2021.03.059
[4]	王红君, 叶荣, 赵辉, 等. 基于改进的烟花-蚁群算法和B样条曲线的农业机器人路径规划[J]. 科学技术与工程, 2021, 21(7): 2730-2736. doi: 10.3969/j.issn.1671-1815.2021.07.025
[5]	杨保海, 任全会, 李海生. 复杂环境下果园机器人路径规划方法研究[J]. 中国农机化学报, 2021, 42(2): 134-138.
[6]	贺利乐, 刘小罗, 黄天柱, 等. 移动机器人全覆盖路径规划算法研究[J]. 机械设计与制造, 2021(3): 280-284. doi: 10.3969/j.issn.1001-3997.2021.03.064
[7]	杨奇峰, 曲道奎, 徐方. 基于障碍物运动预测的移动机器人路径规划[J]. 计算机工程与设计, 2021, 42(1): 182-188.
[8]	LIU J, YANG J, LIU H, et al. An improved ant colony algorithm for robot path planning[J]. Soft Computing, 2017, 21(19): 5829-5839. doi: 10.1007/s00500-016-2161-7
[9]	JIAO Z, MA K, RONG Y, et al. A path planning method using adaptive polymorphic ant colony algorithm for smart wheelchairs[J]. Journal of Computational Science, 2018, 25: 50-57. doi: 10.1016/j.jocs.2018.02.004
[10]	胡诗宇. 清洁机器人的定位与全覆盖路径规划研究[D]. 南京: 东南大学, 2019.
[11]	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. doi: 10.11975/j.issn.1002-6819.2021.2.002
[12]	FAZLOLLAHTABAR H, HASSANLI S. Hybrid cost and time path planning for multiple autonomous guided vehicles[J]. Applied Intelligence, 2018, 48(1): 482-498.
[13]	欧福超. 基于图像处理的QR码图像预处理的研究[D]. 济南: 山东大学, 2014.
[14]	QIAN Q W, WU J F, WANG Z. Optimal path planning for two-wheeled self-balancing vehicle pendulum robot based on quantum-behaved particle swarm optimization algorithm[J]. Personal and Ubiquitous Computing, 2019, 23(3): 393-403.
[15]	王彬溶, 谭代伦, 郑伯川. 基于旅行商问题转化和遗传算法求解汽配件喷涂顺序[J]. 计算机应用, 2021, 41(3): 881-886.
[16]	陶丽华, 马振楠, 史朋涛, 等. 基于TSP问题的动态蚁群遗传算法[J]. 机械设计与制造, 2019(12): 147-149. doi: 10.3969/j.issn.1001-3997.2019.12.037
[17]	蔡延光, 陈厚仁, 戚远航. 混沌烟花算法求解旅行商问题[J]. 计算机科学, 2019, 46(S1): 85-88.
[18]	陈科胜, 鲜思东, 郭鹏. 求解旅行商问题的自适应升温模拟退火算法[J]. 控制理论与应用, 2021, 38(2): 245-254. doi: 10.7641/CTA.2020.00090
[19]	庞峰. 模拟退火算法的原理及算法在优化问题上的应用[D]. 长春: 吉林大学, 2006.
[20]	陈新, 袁宇浩, 饶丹. 一种改进A~*算法在无人船路径规划中的应用[J]. 计算机仿真, 2021, 38(3): 277-281. doi: 10.3969/j.issn.1006-9348.2021.03.057

施引文献(7)

期刊类型引用(3)

1.	杨磊，袁斌，郑锷，叶晨朔，王思行，何贤俊，张潇潇，黄山，胡伟伟，邵敏. 珠江三角洲秋季生物质燃烧对有机气溶胶的贡献. 中国环境科学. 2023(01): 20-28 . 百度学术
2.	黄巧义，于俊红，黄建凤，黄旭，李苹，付弘婷，唐拴虎，刘一锋，徐培智. 广东省主要农作物秸秆养分资源量及替代化肥潜力. 生态环境学报. 2022(02): 297-306 . 百度学术
3.	郭畅，刘剋. 基于MODIS数据京津冀的秸秆焚烧火点监测与分析. 科技风. 2019(31): 125-126 . 百度学术