杭白菊采摘机器人关键技术研究  

Key techniques of hangzhou white chrysanthemum picking robot

作　　者：樊俊[1] 荀一[1] 鲍官军[1] 吴君亮 杨庆华[1] 

机构地区：[1]浙江工业大学特种装备制造与先进加工技术教育部重点实验室,浙江杭州310032 [2]上海沃施园艺股份有限公司,上海200072

出　　处：《机电工程》2016年第7期909-914,共6页Journal of Mechanical & Electrical Engineering

基　　金：国家科技支撑计划资助项目(2015BAD19B05)

摘　　要：针对杭白菊采摘机械化水平低和人工成本高的问题,研究了杭白菊采摘机器人的本体结构、视觉系统、运动控制系统等方面,设计了一种新型的杭白菊采摘机器人。同时针对杭白菊果实识别的问题,研究了杭白菊的颜色特点和纹理特征,采用了一种基于S分量快速FCM算法的杭白菊果实识别方法,对在顺光和逆光两种不同光照条件下拍摄的杭白菊图像进行了试验。研究结果表明,该方法能够较好地从复杂自然环境中将杭白菊目标快速分割出来,为杭白菊采摘机器人的研制提供了重要参考。Aiming at the problems of the low level of Hangzhou White Chrysanthemum picking mechanization and high labor costs,a walking mechanism,picking arm,an end-effector,vision system and motion control system were researched,a kind of Hangzhou white chrysanthemum picking robot was developed. At the same time,aiming at the problem of fruit identification of Hangzhou White Chrysanthemum,the color feature and texture feature of Hangzhou white chrysanthemum were researched,a new segmentation method for Hangzhou white chrysanthemum that based on the fast FCM algorithm of S component on HSV color space was presented. The Hangzhou white chrysanthemum image in two different light conditions that facing the light and backlight was tested. The results indicate that the proposed method can segment Hangzhou white chrysanthemum quickly and well from the complex natural environment. It can provide some references for the research of agricultural robots.

关 键 词：杭白菊 硬件构成 末端执行器 图像分割 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置] TH122[自动化与计算机技术—控制科学与工程]