SIA OpenIR  > 信息服务与智能控制技术研究室
基于视觉伺服的联合收割机群协同导航从机定位方法
其他题名Slave positioning method for cooperative navigation of combine harvester group based on visual servo
白晓平; 胡静涛; 王卓
作者部门信息服务与智能控制技术研究室
关键词农业机械 控制 导航 收割机群 机群定位 视觉伺服 对靶控制
发表期刊农业工程学报
ISSN1002-6819
2016
卷号32期号:24页码:59-68
收录类别EI ; CSCD
EI收录号20170103218589
CSCD记录号CSCD:5888607
产权排序1
资助机构国家高技术研究发展计划(863 计划)资助项目(2013AA040403) ; 辽宁省科技攻关计划资助项目(2015104005)
摘要针对收割机群协同导航从机实际定位需求,在分析主机与从机间相对位置关系的基础上,提出了一种采用视觉系统求解靶标投影矩形区域形心坐标,并以此作为导引信息,引导相对位姿测量装置测量从机相对主机位姿,实现从机精确定位的方法。重点对从机定位方法中需解决的运动靶标跟踪和对靶控制2个关键问题进行了研究,提出了一种基于双重波门的运动靶标跟踪方法和一种基于变尺度变论域模糊控制的对靶控制方法。试验结果表明,该文所提定位方法基本不受收割机前进速度的影响,不同速度最大偏差的标准差为0.003 5 m,平均偏差的标准差为0.002 3 m。
其他摘要With the improvement of the farm mechanization level, the more corporate’ style farming emerges. For example, more than one harvester collaborated with each other completes the task of harvesting operations. The new corporate style farming creates several new challenges for the agricultural machinery navigation, and the group navigation is the trend of agricultural machinery navigation technology. Group positioning and collaborative navigation control are the 2 critical technical problems to be resolved. In order to solve the slave positioning problem, a slave positioning method based on visual servo was proposed. Firstly, the combine group based on mater-slave structure was introduced, and the slave positioning scheme was proposed. In order to fulfill the automatic measurement of the slave position, the relative positioning device was designed. The structure and measurement process of the positioning device were introduced in detail. The positioning device was composed of laser ranging sensor, PTZ (Pan Tilt Zoom) controller and monocular camera. The monocular camera was used to guide the laser ranging sensor to aim at the target. The laser ranging sensor was used to measure the distance between the master and the slave. The laser ranging sensor guaranteed high precision of the measurement data. The position measurement process could be divided into 2 steps. The first step was to measure the relative position posture between the master and the slave. According to the deviation between the target’s center and the image center, the system adjusted the platform’s direction to change the posture of the camera, so that the 2 centers in the target and the image could coincide approximately. After aiming at the target, the laser sensor was triggered to measure the distance between the master and the slave. The second step was to calculate the slave positon. A global localization model was built up to show the relative location relationship between the master and the slave, and the slave’s coordinate under global coordinate system could be calculated. Secondly, in order to solve the 2 key problems in the process of the position measurement, 2 methods were proposed. A method of automatic identification for motion target based on dual windows was proposed to reduce the visual feedback delay. This target identify method filtered out most of the identified area by setting dual windows, and searched the target point only in a small area of the image. A variable-scale variable-universe fuzzy control method was proposed to improve the target control accuracy. This method introduced the contraction-expansion factor to improve the granularity of fuzzy rules without increasing the number of control rules, and introduced the variable scale factor to improve the adaptability to the change in the distance between the master and the slave. Finally, in order to verify the effectiveness of the proposed model and method in this paper, the slave positioning experiments were carried out. When the slave ran at the speed of 0.8, 1.0 and 1.2 m/s, the average positioning error was 0.127 9, 0.128 6 and 0.132 1 m respectively. The experimental results show that the slave positioning accuracy is independent of the forward speed, and can meet the slave positioning requirement.
语种中文
引用统计
被引频次:1[CSCD]   [CSCD记录]
文献类型期刊论文
条目标识符http://ir.sia.cn/handle/173321/19749
专题信息服务与智能控制技术研究室
通讯作者胡静涛
作者单位1.中国科学院沈阳自动化研究所
2.中国科学院网络化控制系统重点实验室
推荐引用方式
GB/T 7714
白晓平,胡静涛,王卓. 基于视觉伺服的联合收割机群协同导航从机定位方法[J]. 农业工程学报,2016,32(24):59-68.
APA 白晓平,胡静涛,&王卓.(2016).基于视觉伺服的联合收割机群协同导航从机定位方法.农业工程学报,32(24),59-68.
MLA 白晓平,et al."基于视觉伺服的联合收割机群协同导航从机定位方法".农业工程学报 32.24(2016):59-68.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
基于视觉伺服的联合收割机群协同导航从机定(1578KB)期刊论文作者接受稿开放获取ODC PDDL浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[白晓平]的文章
[胡静涛]的文章
[王卓]的文章
百度学术
百度学术中相似的文章
[白晓平]的文章
[胡静涛]的文章
[王卓]的文章
必应学术
必应学术中相似的文章
[白晓平]的文章
[胡静涛]的文章
[王卓]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 基于视觉伺服的联合收割机群协同导航从机定位方法.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。