基于激光雷达的全生长周期甘蔗地行间自主导航研究  

Research on autonomous navigation between rows of sugarcane in the whole growth cycle based on LIDAR

作　　者：李岩舟[1] 石奕峰 涂伟[2] 覃锋 潘柳颖 何艳洲 Li Yanzhou;Shi Yifeng;Tu Wei;Qin Feng;Pan Liuying;He Yanzhou(School of Mechanical Engineering,Guangxi University,Nanning,530004,China;Guilin Teachers Technical College,Guilin,541199,China)

机构地区：[1]广西大学机械工程学院,南宁市530004 [2]桂林师范高等专科学校,广西桂林541199

出　　处：《中国农机化学报》2022年第3期153-158,177,共7页Journal of Chinese Agricultural Mechanization

基　　金：广西科技重大专项(桂科AA18242011)。

摘　　要：为开发一套适应于丘陵山区甘蔗全生长周期的自主导航系统,将二维激光雷达用作导航传感器,并设计矫正算法来修正地形对雷达横向数据的影响。由于不同生长时期的甘蔗形态差异较大,传统聚类算法聚类参数固定导致实际聚类效果较差,提出一种基于点云数目阈值分辨的自适应聚类算法,利用滤波和甘蔗直线种植特点引入置信区间。定位甘蔗后,采用基于斜率判定的改进最小二乘法来实现少量数据的直线拟合,通过田间试验证明,该方法能够消除地形和甘蔗叶片对雷达点云数据的影响,定位误差都能控制在10 cm以内,实现了甘蔗全生长周期行走路径的拟合。In order to develop an autonomous navigation system suitable for the whole growth cycle of sugarcane in hilly and mountainous terrain,two-dimensional LIDAR was used as a navigation sensor,and a correction algorithm was designed to correct the influence of terrain on the lateral data of the radar.Due to the large differences in the shape of sugarcane in different growth periods,the traditional clustering algorithm had fixed clustering parameters,resulting in poor actual clustering effect.An adaptive clustering algorithm based on point cloud number threshold resolution was proposed.The confidence interval was introduced by using the characteristics of filtering and sugarcane linear planting.After locating the sugarcane,the improved least squares method based on slope determination was used to realize the straight line fitting of a small amount of data.Field experiments confirmed that this method could eliminate the influence of terrain and sugarcane leaves on the radar point cloud data,and the positioning error could be controlled within 10 cm.In this regard,the fitting of the walking path in the whole growth cycle of sugarcane is realized.

关 键 词：丘陵地带 激光雷达 全周期 导航 聚类 最小二乘拟合 

分 类 号：S237[农业科学—农业机械化工程]