Switching Control of Image-Based Visual Servoing With Laser Pointer in Robotic Manufacturing Systems
Switching Control of Image-Based Visual Servoing With Laser Pointer in Robotic Manufacturing Systems
复制标题
DOI：
10.1109/tie.2008.2003217
复制
发表时间：
2009-02
影响因子：
7.7
通讯作者：
W. Xie;Zheng Li;X. Tu;C. Perron
中科院分区：
文献类型：
--
作者：
W. Xie;Zheng Li;X. Tu;C. Perron
在本文中，眼在手机器人系统与激光指示器的开发，以检测，把握，并在机器人制造系统的主体上的平面物体的装配。本文的重点是检测的对象和移动的末端执行器的位置，一个泵可以完美地吸取的对象。基于图像的视觉伺服（IBVS）的切换控制被设计为控制末端执行器相对于静止物体的姿态，使得由相机观察到的平面物体的图像特征会聚到用于进一步组装的目标图像特征。采用一个简单的现成的激光指示器来实现深度估计，以获得图像雅可比矩阵。通过使用激光光斑作为图像特征和分离的自由度的方法，所提出的开关控制算法的旋转和平移运动的相机，以避免传统的IBVS固有的缺点。在机器人装配系统上的实验验证了该方法的有效性。
In this paper, an Eye-in-Hand robotic system with laser pointer is developed to detect, grasp, and assemble a planar object on a main body in robotic manufacturing systems. This paper is focused on detecting the object and moving the end effector to a position where a pump can perfectly suck up the object. A switching control of image-based visual servoing (IBVS) is designed to control the pose of the end effector with respect to the stationary object so that the image features of the planar object observed by the camera converge to the target image features for the further assembly. A simple off-the-shelf laser pointer is adopted to realize the depth estimation for obtaining the image Jacobian matrices. By using a laser spot as an image feature and the separate degree-of-freedom method, the proposed switch-control algorithm decouples the rotational and translational motions of the camera to avoid the inherent drawbacks of traditional IBVS. The experiments on a robotic assembly system are given to verify the effectiveness of the proposed method.