基于改进遗传算法的工业机器人视觉动态分拣方法研究  

Research on Visual Dynamic Sorting Method of Industrial Robot Based on Improved Genetic Algorithm

作　　者：梁存仙 焦建静 赵志鹏 孙爱芹[2] 王吉岱[2] LIANG Cunxian;JIAO Jianjing;ZHAO Zhipeng;SUN Aiqin;WANG Jidai(Qingdao Technicians College,Qingdao 266229,China;College of Mechanical and Electronic Engineering,Shandong University of Science and Technology,Qingdao 266590,China)

机构地区：[1]青岛市技师学院,山东青岛266229 [2]山东科技大学机械电子工程学院,山东青岛266590

出　　处：《机械与电子》2025年第3期60-65,73,共7页Machinery & Electronics

基　　金：机械行业职业教育“产科教协同创新”课题(JXHYZX2024075)。

摘　　要：针对工业机器人视觉动态分拣过程存在的漏抓、误抓和精度不高等问题,提出一种基于改进遗传算法的多工件动态分拣方法。在分析工件分拣过程的基础上,确定了相机坐标系、用户坐标系和工具坐标系之间的转换关系。设计了一种图像去重算法,以时间和工件位置为判断依据,经对比去掉重复图像信息。为提高分拣效率,提出了一种基于改进遗传算法的工件动态分拣序列优化方法,利用非均匀变异算子进行邻域变异操作,可提高算法的收敛性和搜索能力,缩短分拣耗时。仿真和实验结果表明:改进遗传算法收敛较快;所述工业机器人视觉动态分拣方法效率较高,具有较好的稳定性和准确性。To overcome the problems of missing grasp,false grasp and low precision in the visual dynamic sorting process of industrial robot,a multi workpiece dynamic sorting method based on genetic algorithm was proposed.Based on the analysis of workpiece sorting process,transformation relationships between camera coordinate system,user coordinate system and tool coordinate system were determined.By using time and position of the workpiece as the judgement basis,an image deduplication algorithm was presented to remove the duplicate image information.At the same time,in order to improve the sorting efficiency,a workpiece dynamic sorting sequence optimization method based on genetic algorithm was proposed.Nonuniform mutation operator was used to perform the neighborhood mutation operation,which could improve the convergence and search ability of the algorithm and shorten the sorting time.Simulation and experimental results show that the improved genetic algorithm converges quickly;the visual dynamic sorting method of the industrial robot has high efficiency,better stability and accuracy.

关 键 词：工业机器人 视觉分拣 图像去重 遗传算法 

分 类 号：TP242.2[自动化与计算机技术—检测技术与自动化装置]