首页分享葡萄园植保机器人路径规划算法

葡萄园植保机器人路径规划算法

来源：花匠小妙招时间：2024-12-17 00:45

摘要: 为提高植保机器人葡萄园作业在垄行识别和路径规划中的准确度和可靠性，该文提出了一种基于支持向量机（support vector machine，SVM）的多支持向量配比权重进行葡萄园垄行识别与农业机器人作业路径规划的算法。该算法利用Kalman滤波器对由激光雷达扫描获取的粗大实况果园数据信息进行预处理，校正数据中的噪声离群点，然后结合SVM，获得垄行环境中的分割超平面和分类边际线，最后根据样本点与分类边际线存在的几何间隔关系判别各点所占相对权重，获取垄线安全预估测位置并进行农业机器人作业导航线的规划拟合。通过对多个实际样本的试验与测试，拟合导航线与实际垄行中心线平均角度偏差为0.72°，相对植保机器人的平均距离偏差为4.22 mm。试验结果表明，该算法能够有效的识别与定位植保机器人所需导航线的位置，拟合的导航线满足葡萄园植保机器人准确作业的要求。

Abstract: To meet the requirements of accuracy and reliability of plant protection robot in ridge identification and route planning, also improve the working conditions of farmers, and achieve an unmanned operation purpose, an algorithm based on multi-support-vector proportioning weight of SVM (support vector machine) to identify the ridge line of vineyards, and the path planning of plant protection robots were proposed. The strategy first uses Kalman filter to pre-process coarse orchard data information obtained by Lidar scanning. According to the principle that Kalman filter complies with Gaussian distribution, the prior point between 2 adjacent points was taken as the prior state, and the latter point was used as the observed point to obtain posteriori state estimation, so as to realize data integration and analysis. With its good system state estimation characteristics, the collected data can be used to judge the trend of the ridge line, so as to correct the noise outliers in the data and improve the readability of the data. Then according to the characteristics of the vineyard branch ridge and the characteristics of ridges line with clearly separable spacing, and corresponding to the situation that the ridge line on both sides can be completely separated, the method was combined with SVM linear classification. With the unique advantages of the classification and due to that SVM can search the unique segmentation hyperplane, the maximum interval and segmentation hyperplane, classification margins in the ridge environment could be gotten. The split hyperplane obtained at this time would be between ridge lines. However, there was a big deviation from the angle of the direction of the ridge line and the horizontal distance. It could not meet the precise operation requirements of plant protection robots. It needed further data processing and analysis. In order to obtain accurate position of the center of ridge line, finally, the relative weights were assigned to the sample points of each ridge based on the geometric interval relationship between the sample points on both sides of the ridge and the corresponding SVM classification marginal line. The classification marginal line was reformed according to the number of sample points and the relative weights. According to the condition of the product of the interval relationship between each sample point and the classification margin, their relative weight must be consistent with the quality value of classification margin. The random sampling consistency iteration method (RANSAC) would avoid the error of cost estimate, and could estimate the parameters of the mathematical model from a group of observed data with outliers, so as to obtain the predicted safety location of the ridge. Although the pre-estimated security location of ridge line was not necessarily consistent with the actual location of the vineyard ridge, navigation line could be obtained indirectly by the security ridge line on both sides and the principle of angle bisector which could meet the requirements of precision operation of plant protection robot. Operation guidance line for plant protection robot could be acquired. After a number of actual samples were tested, the average angular deviation between the fitted navigation line and the actual ridge centerline was 0.72°, and the average distance deviation of the relative plant protection robot was 4.22 mm. Experimental results showed that this algorithm could effectively identify and locate the navigation route needed by the plant protection robot. The fitted navigation line could meet the requirements of accurate operation of the plant protection robot in the vineyard. However, the redundancy of the algorithm was relatively large, and the time required to process data in a single time was about 2.05 s. With the accelerated calculation speed of the processor in the future, the algorithm provided in the article can provide a reference solution for such a problem.

[1] 李鑫，曹少波，杨欣，等. 适于机械化作业的葡萄栽培技术规程研究[J]. 中国农机化学报，2017，38(2)：120－123.Li Xin, Cao Shaobo, Yang Xin, et al. Cultivation technical regulations for grape suitable for mechanized operation[J]. Journal of Chinese Agricultural Mechanization, 2017, 38(2): 120－123. (in Chinese with English abstract) [2] 聂森，王丙龙，郝欢欢，等. 基于机器视觉的果园导航中线提取算法研究[J]. 农机化研究，2016,38(12)：86－89.Nie Sen, Wang Binglong, Hao Huanhuan,et al. Navigation line extraction based on machine vision in orchard[J]. Journal of Agricultural Mechanization Research, 2016,38(12): 86－89. (in Chinese with English abstract) [3] 张志斌，潘华稳，李琛，等. 一种基于平均垄间距的视觉导航垄线识别算法[J]. 计算机工程与应用，2011，47(22)：191－194.Zhang Zhibin, Pan Huanwen, Li Chen, et al. Crop rows identification based-row interval for field vision guidance system[J]. Computer Engineering and Applications, 2011, 47(22): 191－194. (in Chinese with English abstract) [4] Torii T, Kitade S, Teshima T, et al. Crop row tracking by an autonomous vehicle using machine vision (part 1):Indoor experiment using a model vehicle[J]. Journal of the Japanese Society of Agricultural Machinery, 2000, 62(5): 37－42. [5] 陈娇，姜国权，杜尚丰，等. 基于垄线平行特征的视觉导航多垄线识别[J]. 农业工程学报，2009，25(12)：107－113.Chen Jiao, Jiang Guoquan, Du Shangfeng, et al. Crop rows detection based on parallel characteristic of crop rows using visual navigation[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2009, 25(12): 107－113. (in Chinese with English abstract) [6] 陈军，蒋浩然，刘沛，等. 果园移动机器人曲线路径导航控制[J]. 农业机械学报，2012，43(4)：179－182,187.Chen Jun, Jiang Haoran, Liu Pei, et al. Navigation control for orchard mobile robot in curve path[J]. Tansactions of the Chinese Society for Agricultural Machinery, 2012, 43(4): 179－182,187. (in Chinese with English abstract) [7] 袁池，陈军，武涛，等. 基于机器视觉的果树行中心线检测算法研究[J]. 农机化研究，2013，35(3)：37－39.Yuan Chi, Chen Jun, Wu Tao, et al. Algorithms of machine vision-based centerline detection of fruit tree rows[J]. Journal of Agricultural Mechanization Research, 2013, 35(3): 37－39. (in Chinese with English abstract) [8] Xue Jinlin, Zhang Lei, Tony E G. Variable field-of-view machine vision based row guidance of an agricultural robot[J]. College of Engineering, 2012, 84: 85－91. [9] 熊斌，张俊雄，曲峰，等. 基于BDS的果园施药机自动导航控制系统[J]. 农业机械学报，2017，48(2)：45－50.Xiong Bin, Zhang Junxiong, Qu Feng, et al. Navigation control system for orchard spraying machine based on Beidou Navigation satellite system[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017, 48(2): 45－50. (in Chinese with English abstract) [10] Zhang Q, Qiu H. A dynamic path search algorithm for tractor automatic navigation[J]. Transactions of the Asae, 2004, 47(2): 639－646. [11] 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.Zhou Jun, Hu Chen. Inter-row localization method for agricultural robot working in close planting orchard[J]. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(11): 22－28. (in Chinese with English abstract) [12] Erkan Kayacan, Erdal Kayacan, Herman Ramon, et al. Distributed nonlinear model predictive control of an autonomous tractor-trailer system[J]. Mechatronics, 2014, 24: 926－933. [13] 罗锡文，张智刚，赵祚喜，等. 东方红X-804拖拉机的DGPS自动导航控制系统[J]. 农业工程学报，2009，25(11)：139－145.Luo Xiwen, Zhang Zhigang, Zhao Zuoxi, et al. Design of DGPS navigation control system for Dongfanghong X-804 tractor[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2009, 25(11): 139－145. (in Chinese with English abstract) [14] 张智刚，罗锡文，李俊岭. 轮式农业机械自动转向控制系统研究[J]. 农业工程学报，2005，21(11)：85－88.Zhang Zhigang, Luo Xiwen, Li Junling. Automatic steering control system of wheeled model farming machinery[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2005, 21(11): 85－88. (in Chinese with English abstract) [15] 陈艳，张漫，马文强，等. 基于GPS和机器视觉的组合导航定位方法[J]. 农业工程学报，2011，27(3)：126－130.Chen Yan, Zhang Man, Ma Wenqiang, et al. Positioning method of integrated navigation based on GPS and machine vision[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2011, 27(3): 126－130. (in Chinese with English abstract) [16] Freitas G, Zhang J, Hamner B, et al. A Low-Cost, Practical Localization System for Agricultural Vehicles[M]. Intelligent Robotics and Applications. Springer Berlin Heidelberg, 2012:365－375. [17] Vijay S, Thomas F B, Arroyo A A. Development of machine vision and laser radar based autonomous vehicle guidance systems for citrus grove navigation[J]. Computers and Electronics in Agriculture, 2006, 53: 130－143. [18] Mariano Gonzalez-de-Soto, Luis Emmi, Manuel Perez-Ruiz, et al. Autonomous systems for precise spraying-Evaluation of a robotised patch sprayer[J]. Biosystems Engineering, 2016,146:165－182. [19] Oscar C B, Akira M, Kazunobu I N N. Development of an autonomous navigation system using a two-dimensional laser scanner in an orchard application[J]. Biosystems Engineering, 2007, 96(2): 139－149. [20] Jacqueline Libby, George Kantor. Accurate gps-free positioning of utility vehicles for specialty agriculture[J]. ASABE Annual International Meeting, 2010, 15(2): 20－23. [21] 鄢丹青. 空间Kalman滤波与空时Kalman滤波算法[J]. 兰州理工大学学报，2016，42(2)：153－157.Yan Dangqing. Spatial Kalman filtering and spatial-temporal Kalman filtering algorithm[J]. Journal of Lanzhou University of Technology, 2016, 42(2): 153－157. (in Chinese with English abstract) [22] 邓胡滨，张磊，吴颖，等. 基于卡尔曼滤波算法的轨迹估计研究[J]. 传感器与微系统，2012，31(5)：4－7.Deng Hubin, Zhang Lei, Wu Ying, et al. Research on track estimation based on Kalman filtering algorithm[J]. Transducer and Microsystem Technologies, 2012, 31(5): 4－7. (in Chinese with English abstract) [23] 刘桂辛. 改进的自适应卡尔曼滤波算法[J]. 电子设计工程，2016, 24(2)：48－51.Liu Guixin. The improved adaptive Kalman filter algorithm[J]. Electronic Design Engineering, 2016, 24(2): 48－51. (in Chinese with English abstract) [24] 郭明玮，赵宇宙，项俊平，等. 基于支持向量机的目标检测算法综述[J]. 控制与决策，2014, 29(2)：193－200.Guo Mingwei, Zhao Yuzhou, Xiang Junping, et al. Review of object detection methods based on SVM[J]. Control and Decision, 2014, 29(2): 193－200. (in Chinese with English abstract) [25] 帅勇，宋太亮，王建平. 考虑全过程优化的支持向量机预测方法[J]. 系统工程与电子技术，2017，39(4)：931－940.Shuai Yong, Song Tailiang, Wang Jianping. Method on support vector machine prediction considering whole process optimization[J]. System Engineering and Electronics, 2017, 39(4): 931－940. (in Chinese with English abstract) [26] 郭晨晨，朱红康. 一种改进的支持向量机模型研究[J]. 陕西科技大学学报，2017，35(2)：189－194.Guo Chenchen, Zhu Hongkang. Research on improved support vector machine model[J]. Journal of Shanxi University of Science & Technology, 2017, 35(2): 189－194. (in Chinese with English abstract) [27] 苏成利，郑博元，李平. 基于自适应边界向量提取的多尺度v-支持向量机建模[J]. 控制与决策，2015,30(4)：721－726.Su Chengli, Zheng Boyuan, Li Ping. Multiscale v-support vector machine modelong based on adaptive boundary vector extraction[J]. Control and Decision, 2015,30(4): 721－726. (in Chinese with English abstract) [28] Khemchandani R, Sharma S. Robust least squares twin support vector machine for human activity recognition[J]. Applied Soft Computing, 2016, 47: 33－46. [29] 姚家扬，罗志增. 一种基于新型阈值函数小波去噪方法[J].杭州电子科技大学学报，2015, 35(4)：80－83.Yao Jiayang, Luo Zhizeng. Research on wavelet denoising based on a new threshold function[J]. Journal of Hangzhou Dianzi Universit, 2015, 35(4): 80－83. (in Chinese with English abstract) [30] 磨少清，刘正光，张军，等. 基于图像自身信息的图像边缘检测阈值自动设定方法[J]. 光电子·激光，2011, 22(8)：1246－1250.Mo Shaoqing, Liu Zhengguang, Zhang Jun, et al. An unsupervised threshold selection method for edgr detection based on image self-information[J]. Journal of Optoelectronics·Laser, 2011, 22(8): 1246－1250. (in Chinese with English abstract) [31] 袁清珂，张振亚，毕庆. 改进RANSAC算法在直线拟合中的应用[J]. 组合机床与自动化加工技术，2015(1)：123－125.Yuan Qingke, Zhang Zhenya, Bi Qing. Linear fitting application based on the improved RANSAC algorithm[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2015(1): 123－125. (in Chinese with English abstract) [32] 吴剑亮，李艳，高扬，等. 基于改进RANSAC算法的道路直线提取方法[J]. 地理空间信息，2017, 15(5)：42－44. [33] 张永祥，古佩强，穆铁英. 改进的RANSAC基础矩阵估计算法[J]. 小型微型计算机系统，2016，37(9)：2084－2087.Zhang Yongxiang, Gu BeiQiang, Mu TieYing. Improved RASANC algorithm for fundamental matrix estimation[J]. Journal of Chinese Computer Systems, 2016, 37(9): 2084－2087. (in Chinese with English abstract)