面向装配机器人的作业目标视觉识别与定位方法  

Job Target Recognition and Location Method for Assembly Robots

作　　者：宿月文 金守峰[2] 田明锐 SU Yue-wen;JIN Shou-feng;TIAN Ming-rui(School of Mechanical Engineering,Baoji University of Arts and Sciences,Baoji Shaanxi 721007,China;School of Mechanical and Electrical Engineering,Xi′an Polytechnic University,Xi′an 710048,China)

机构地区：[1]宝鸡文理学院机械工程学院,陕西宝鸡721007 [2]西安工程大学机电工程学院,西安710048 [3]长安大学高速公路施工机械陕西省重点实验室,西安710064

出　　处：《组合机床与自动化加工技术》2018年第10期97-101,共5页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：陕西省自然科学基础研究计划项目(2017JM5141);陕西省教育厅专项科研计划项目(17JK0334);西安工程大学博士基金(BS1535);西安工程大学研究生创新基金(CX201713);西安市科技计划项目(201805030YD8CG14(5))

摘　　要：针对装配机器人在作业过程中所面临的工件形状多样性等因素对工件的识别、定位造成的扰动,提出利用BRIEF描述子对SURF算法提取的作业目标特征点进行描述,采用最近邻汉明距离融合PROSAC算法进行两步骤的匹配,去除无效匹配点对,提高识别精度;通过模板图像与作业目标图像的转换关系建立4参数的仿射变换模型,求解装配作业目标的形心坐标,结合装配机器人视觉系统的标定参数得到目标形心的世界坐标。实验结果表明该方法在不考虑几何畸变的情况下,实现了对装配作业目标的快速识别与定位,定位误差不超过1. 0mm。Focusing on the disturbance of the identification and positioning caused by the shape diversity of the workpiece in the process of assembling robot,this paper proposed a description of the job feature points extracted by the SURF algorithm using the BRIEF descriptor,two-step matching is performed using the nearest neighbor Hamming distance PROSAC algorithm to remove the invalid matching point pairs and improve the recognition accuracy.Through the transformation relationship between the template image and the target image,a 4-parameter affine transformation model is established to solve the centroid coordinates of the assembly target,and the calibration coordinates of the assembly robot vision system are obtained.The experimental results show this algorithm can realize the rapid identification and positioning of the assembly target without considering the geometric distortion,and the positioning error does not exceed 1.0mm.

关 键 词：装配机器人 机器视觉 仿射变换 定位 

分 类 号：TH165[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]