虚实坐标智能匹配与自适应三维轨迹规划  

Virtual and Real Coordinate Intelligent Matching and Adaptive Three-dimension Trajectory Planning

作　　者：孟月波[1] 王宙 韩九强[2] 刘光辉[1] 徐胜军[1] MENG Yuebo;WANG Zhou;HAN Jiuqiang;LIU Guanghui;XU Shengjun(School of Information and Control Engineering,Xi’an University of Architecture and Technology,Xi’an 710055,China;School of Automation Science and Engineering,Xi’an Jiaotong University,Xi’an 710049,China)

机构地区：[1]西安建筑科技大学信息与控制工程学院,陕西西安710055 [2]西安交通大学自动化科学与工程学院,陕西西安710049

出　　处：《控制工程》2024年第8期1468-1477,共10页Control Engineering of China

基　　金：陕西省自然科学基础研究面上项目(2020JM-473,2020JM-472);陕西省重点研发计划项目(2021SF-429)。

摘　　要：针对数字孪生增材修复任务中,物件仿真与真实坐标对应困难、三维轨迹误差较大的问题,提出虚实坐标智能匹配与自适应三维轨迹规划方法。采用图像分割方法获取实际场景下物件的分割图像,通过最小外接矩形预估物件真实坐标,仿真端据此执行旋转与平移操作,调整仿真物件的模型位置,实现坐标智能匹配;为最小化虚实坐标误差,设计基于Attention的多尺度残差UNet图像分割模型,利用多尺度残差模块获取物件多尺度特征,通过Attention策略增强网络对位置信息的描述。三维轨迹规划部分,设计融合特征高度的自适应分层算法,减少分层高度偏移,缩减阶梯误差;根据分层结果进行轮廓提取、填充,生成三维轨迹。结果表明,坐标匹配误差小于1mm,三维修复轨迹规划质量较高。For the problem of difficultly matching the simulated coordinates of the object with the real coordinates without difference and the large generation error of three-dimensional trajectory in the digital twin additive repairing task,a method of intelligent matching of virtual and real coordinates and an adaptive three-dimensional trajectory planning is proposed.The image segmentation method is adopted to obtain the segmented image of the additive repairing object in the actual scene.By the minimum circumscribed rectangle estimating the real coordinates of the object,the simulation terminal performs translation and rotation operations accordingly,adjusts the three-dimensional model position of the simulated object,and realizes the intelligent match of coordinate;To minimize the virtual and real coordinate errors,a multi-scale residual UNet image segmentation model based on Attention is designed.The multi-scale residual module is utilized to obtaining the multi-scale features of the object.And through the Attention strategy,the description of location information by network is enhanced,the feature space expression ability is promoted.In the three-dimensional trajectory planning part,an adaptive layering algorithm integrating feature heights is designed to reduce layer height offset and step error.According to the layering results,the contours are extracted and filled and three-dimensional additive repairing tracks are generated.The experimental results show that the matching error of coordinate is less than 1mm,and the three-dimensional repair trajectory planning quality is higher.

关 键 词：增材修复机器人 虚实坐标匹配 三维轨迹规划 图像分割 数字孪生 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]