Parallel Mechanisms with Two or Three Degrees of Freedom

Parallel manipulators for the machine tool industry have been studied extensively for various industrial applications. However, limited useful workspace areas, the poor mobility, and design difficulties of more complex parallel manipulators have led to more interest in parallel manipulators with less than six degrees of freedom (DoFs). Several parallel mechanisms with various numbers and types of degrees of freedom are described in this paper, which can be used in parallel kinematics machines, motion simulators, and industrial robots.     

Research on Precision Assembly Robot''''s Joint Torque Control Based on Current Measurement

A set of new current sensing device is used to realize joint torque control based on current measurement in a precision assembly robot's third joint. The output torque's model of the joint's brushless DC motor is founded. Disturbance factors and the compensated effect of the torque's closed loop based on current measurement are analyzed. Related simulations and experiments show that the system has good current tracking and anti-disturbances performance, which improve the force control performance of the robot in assembly.     

Classification of Medical Brain Images

Since brain tumors endanger people‘s living quality and even their lives, the accuracy of classification becomes more important. Conventional classifying techniques are used to deal with thosedatasets with characters and numbers. It is difficult, however, to apply them to datasets that include brain images and medical history (alphanumeric data), especially to guarantee the accuracy.For these datasets, this paper combines the knowledge of medical field and improves the traditional decision tree. The new classification algorithm with the direction of the medical knowledge not only adds the interaction with the doctors, but also enhances the quality of classification. The algorithm has been used on real brain CT images and a precious rule has been gained from the experiments. This oaoer shows that the ahzorithm works well for real CT data.     

基于离散智能的自重构机器人变形策略

在总结自重构机器人系统结构本质特点的基础上，提出了一种描述模型，对几种典型的同构和非同构系统进行统一的描述．探索了自重构机器人的基本变形方法，给出一种建立在全离散的局部智能基础上的变形策略，使机器人通过模块局部之间的交互产生整体自组织的结果，并且能够减低变形算法的计算复杂度．以一个9模块系统的变形过程为例进行了验证．     

面向自主机器人的实时彩色视觉系统

设计开发了一种新型的机器人实时彩色视觉系统，以及基于颜色的实时分割和识别软件系统，采用即插即用型的USB接口数字摄像头，简化了系统的使用和维护，首先把输入的彩色图像从RGB空间转换到YIQ颜色空间，提取出和颜色有关的IQ平面的信息；然后根据目标颜色在IQ平面里分割图像，再对图像进行游程编码，并从游程编码中提取出有效的图像信息；最后通过TCP／IP接口将视觉信息发送给机器人控制系统，为了抑制光强变化的影响，采用了一种阈值学习方法，实验结果表明，整套系统具有很高的实时性和较好的识别效果。     

基于力信息的机器人接触状态下作业的技能学习

为实现机器人接触状态下作业的演示编程，使机器人获得人的基于力信息的作业技能，首先提出了描述接触状态的元素接触形式，用元素接触形式序列建立技能模型，根据不同的接触形式具有的不同腕力分布，利用支持向量机(SVM)对不同的元素接触形式进行辨识，在此基础上机器人获得人在接触状态下的作业技能，实现了演示编程方法中最关键的一步。     

基于小波分析的X线医学图像噪声综合抑制方法

提出了一种基于小波分析理论的医学X线图像噪声的综合抑制方法．将X线图像的试验处理结果与邻域平均、中值滤波去噪处理方法进行对比分析，结果表明该方法不仅能消除噪声提高图像质量，而且有效地保留了影像中丰富的细微影纹和边缘信息．     

基于神经网络的3自由度移动机器人跟踪方法研究

针对具有2个可操舵驱动轮的3自由度移动机器人的轨迹跟踪问题，利用神经网络的任意非线性逼近能力辨识出3自由度移动机器人的逆运动学模型，使系统的3个独立输入控制线性化，将一般非线性系统转化为仿射非线性系统。根据反馈控制理论，设计了跟踪控制器，使系统具有良好的全局稳定性，实现了移动机器人的位置和方位的独立跟踪。最后，通过仿真验证了算法的可行性和有效性。     

现阶段医院HIS系统的HL7改造

以病人基本信息为例,探讨如何在不改变现有HIS的基础上引入HL7,从而与外部相关系统,以及LIS、RIS实现基于HL7的信息交换     

模糊控制在机器人柔顺装配中的应用

提出了一种模糊柔顺的控制方法来控制机器人的装配作业，本方法不需要装配作业的模型参数，省去了大量的计算，并且在控制过程中不需要引入受力信息的变化量，实验证明，这种方法实用性强，实时性好。