基于Kalman滤波的移动机械臂动态抓取研究  

Dynamic catch for mobile manipulator based on Kalman filter

作　　者：王兆权 吴海彬[1] 叶锦华[1] 许金山 WANG Zhao-quan;WU Hai-bin;YE Jin-hua;XU Jin-shan(School of Mechanical Engineering and Automation,Fuzhou University,Fuzhou 350108,China)

机构地区：[1]福州大学机械工程及自动化学院

出　　处：《机电工程》2019年第8期851-856,共6页Journal of Mechanical & Electrical Engineering

基　　金：国家自然科学基金资助项目(51605093);工信部智能制造综合标准化与新模式应用项目(2018);福建省科技厅产学重大基金专项资助项目(2015H6012)

摘　　要：针对机械臂在交通路锥自动取放系统中的抓取问题,对系统运动过程中路锥位置的预测、机械臂的抓取策略等方面进行了研究。提出了一种基于Kalman滤波与位置伺服的路锥动态抓取方法,建立了路锥的相对运动模型,采用Kalman滤波算法对路锥位置进行了预测,以补偿系统动态抓取的滞后;采用矢量积法构造了机械臂的雅克比矩阵,从而建立了基于路锥位置伺服的运动控制模型;在此基础上,论述了路锥在不同距离时机械臂的两个运动阶段,提出带速度补偿的抓取方法,使得机械臂可以在移动过程中完成对路锥的抓取;通过所搭建的实验平台,对所提方法进行了验证。研究结果表明:该方法能够有效地提高机械臂的路锥跟踪精度,避免了动态抓取时机械臂与路锥间的直接碰撞,使整个抓取过程更加平稳。Aiming at the problem of realizing the dynamic catch application about traffic cones’ automatic extraction& placement system, the prediction of cone position, the catch strategies of manipulator were researched, and traffic cone dynamic catch method which based on Kalman filter and cone’s position servo control was proposed. The relative motion model of cone was established. To compensate for the lag of the system during dynamic catch, the Kalman filter algorithm was adopted in the prediction of cone position. To establish the servo control model which based on cone’s position, the vector product method was used to construct the manipulator’s Jacobian matrix.By this,two moving stages of the manipulator were proposed for the different cone’s distances. Finally,by the method of velocity compensation, traffic cone was caught by manipulator during the mobile process. An experimental platform was built to validate the proposed method. The results indicate that the dynamic catch method can effectively improves the tracking accuracy of the manipulator, and it avoids the direct collision between cones and manipulator,and makes the whole catch process more stable.

关 键 词：交通路锥 移动机械臂 KALMAN滤波 位置伺服 动态抓取 

分 类 号：TP241[自动化与计算机技术—检测技术与自动化装置]