一种面向工业应用的机器人回位方法  

A Robot Homing Method for Industrial Applications

作　　者：侯龙潇 HOU Longxiao(Henan Machinery Design&Research Institute Co.,Ltd.,Zhengzhou 450003,China)

机构地区：[1]河南省机械设计研究院有限公司,河南郑州450003

出　　处：《机械制造与自动化》2024年第4期235-240,286,共7页Machine Building & Automation

摘　　要：针对工业机器人作业过程中非正常停机引起位姿处于未知状态而导致机器人无法从停机位置自动返回初始位置的问题,提出一种工业机器人的回位方法。设计机器人回位路径,结合k-近邻算法、构造回位空间以及空间分类阈值对机器人的位姿信息进行分类化处理;重构机器人特征数据进行决策树模型的训练;使用训练完成的模型决策回位路径后执行机器人回位程序,实现工业机器人自动返回初始位。回位试验实验结果表明:在随机位姿和携带多样工具的状态下机器人回位成功率为93.3%。For the abnormal halt of industrial robots in the working process resulting in their postures in an unknown state and the failure of automatic return to the initial position from the halt position,a homing method for industrial robot is proposed,which includes designing a robot return path,classifying the robot's pose information by combining the k-nearest neighbour algorithm and constructing return space and spatial classification threshold,reconstructing the robot feature data for decision tree model training andexcuting the robot regression program after using the trained model decision return path.Thus theautomatic return of industrial robots to the initial position being realized.The experimental results show that the success rate of robot return is 93.3%in random posture and with various tools.

关 键 词：工业机器人 回位方法 空间构造 路径设计 决策树算法 K-近邻算法 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置] TP391[自动化与计算机技术—控制科学与工程]