The workpiece frames relative to each robot base frame should be known in advance for the proper operation of twin-robot nondestructive testing system. However, when two robots are separated from the workpieces, the t...The workpiece frames relative to each robot base frame should be known in advance for the proper operation of twin-robot nondestructive testing system. However, when two robots are separated from the workpieces, the twin robots cannot reach the same point to complete the process of workpiece frame positioning. Thus, a new method is proposed to solve the problem of coincidence between workpiece frames. Transformation between two robot base frames is initiated by measuring the coordinate values of three non-collinear calibration points. The relationship between the workpiece frame and that of the slave robot base frame is then determined according to the known transformation of two robot base frames, as well as the relationship between the workpiece frame and that of the master robot base frame. Only one robot is required to actually measure the coordinate values of the calibration points on the workpiece. This requirement is beneficial when one of the robots cannot reach and measure the calibration points. The coordinate values of the calibration points are derived by driving the robot hand to the points and recording the values of top center point（TCP） coordinates. The translation and rotation matrices relate either the two robot base frames or the workpiece and master robot. The coordinated are solved using the measured values of the calibration points according to the Cartesian transformation principle. An optimal method is developed based on exponential mapping of Lie algebra to ensure that the rotation matrix is orthogonal. Experimental results show that this method involves fewer steps, offers significant advantages in terms of operation and time-saving. A method used to synchronize workpiece frames in twin-robot system automatically is presented.展开更多
Models for the design of assembly processes are considered. Various models for the voice control of an industrial robot are considered: a logical model, semantic networks, a frame model and Petri nets. It is shown tha...Models for the design of assembly processes are considered. Various models for the voice control of an industrial robot are considered: a logical model, semantic networks, a frame model and Petri nets. It is shown that this set of models allows describing the process of designing the technological process for an industrial robot. The logical model of the technological process allows you to define logical relationships. A model based on semantic networks describes the relationship between assembly units in a detail. This allows you to determine the order and method of registration, as well as the mutual orientation of assembly units in the product. The frame model provides the ability to streamline the execution of the build process. A model based on Petri nets allows one to describe the type and sequence of technological transitions. Based on the proposed models, a method of voice control for an industrial robot is developed. The basic principles of voice control for an industrial robot are considered.展开更多
为了实现火龙果采收自动化作业,提出一种基于改进U-Net的火龙果图像分割和姿态估计方法。首先,在U-Net模型的跳跃连接(编码器与解码器部分特征图进行的连接操作)中引入通道和空间注意力机制模块(Concurrent spatial and channel squeeze...为了实现火龙果采收自动化作业,提出一种基于改进U-Net的火龙果图像分割和姿态估计方法。首先,在U-Net模型的跳跃连接(编码器与解码器部分特征图进行的连接操作)中引入通道和空间注意力机制模块(Concurrent spatial and channel squeeze and channel excitation,SCSE),同时将SCSE模块集成到残差模块(Double residual block,DRB)中,在增强网络提取有效特征能力的同时提高网络的收敛速度,得到一种基于注意力残差U-Net的火龙果图像分割网络。通过该网络分割出果实及其附生枝条的掩膜图像,利用图像处理技术和相机成像模型拟合出果实及其附生枝条的轮廓、果实质心、果实最小外接矩形框和三维边界框,进而结合果实及其附生枝条的位置关系进行火龙果三维姿态估计,并在火龙果种植园中获得一个测试集,以评价该算法的性能,最后在自然果园环境下进行实地采摘试验。试验结果表明,火龙果果实图像分割平均交并比(mIoU)和平均像素准确率(mPA)分别达到86.69%和93.89%,三维姿态估计平均误差为8.8°,火龙果采摘机器人在果园环境下的采摘成功率为86.7%,平均采摘时间为22.3 s。满足火龙果机械化作业要求。展开更多
基金Supported by International S&T Cooperation Program of China(Grant No.2012DFA70260)High-end CNC Machine and Basic Manufacturing Equipment of Chinese Key National Science and Technology(Grant No.2011ZX04014-081)
文摘The workpiece frames relative to each robot base frame should be known in advance for the proper operation of twin-robot nondestructive testing system. However, when two robots are separated from the workpieces, the twin robots cannot reach the same point to complete the process of workpiece frame positioning. Thus, a new method is proposed to solve the problem of coincidence between workpiece frames. Transformation between two robot base frames is initiated by measuring the coordinate values of three non-collinear calibration points. The relationship between the workpiece frame and that of the slave robot base frame is then determined according to the known transformation of two robot base frames, as well as the relationship between the workpiece frame and that of the master robot base frame. Only one robot is required to actually measure the coordinate values of the calibration points on the workpiece. This requirement is beneficial when one of the robots cannot reach and measure the calibration points. The coordinate values of the calibration points are derived by driving the robot hand to the points and recording the values of top center point（TCP） coordinates. The translation and rotation matrices relate either the two robot base frames or the workpiece and master robot. The coordinated are solved using the measured values of the calibration points according to the Cartesian transformation principle. An optimal method is developed based on exponential mapping of Lie algebra to ensure that the rotation matrix is orthogonal. Experimental results show that this method involves fewer steps, offers significant advantages in terms of operation and time-saving. A method used to synchronize workpiece frames in twin-robot system automatically is presented.
文摘Models for the design of assembly processes are considered. Various models for the voice control of an industrial robot are considered: a logical model, semantic networks, a frame model and Petri nets. It is shown that this set of models allows describing the process of designing the technological process for an industrial robot. The logical model of the technological process allows you to define logical relationships. A model based on semantic networks describes the relationship between assembly units in a detail. This allows you to determine the order and method of registration, as well as the mutual orientation of assembly units in the product. The frame model provides the ability to streamline the execution of the build process. A model based on Petri nets allows one to describe the type and sequence of technological transitions. Based on the proposed models, a method of voice control for an industrial robot is developed. The basic principles of voice control for an industrial robot are considered.
