基于图像矩的视觉伺服控制及应用

Image Moment Based Visual Servo Control and Its Application

传统的基于图像的视觉伺服控制中,雅可比矩阵的奇异性将影响到控制系统的稳定性和鲁棒性,利用图像矩作为特征可以保证矩阵为满质的,并且由于该雅可比矩阵为上三角型,能够将平移和转动运动部分解耦,因此简化了控制器设计。在视觉控制器的设计中,基于遗传算法优化的最优PD控制策略能够获得比常用的P控制策略更好的综合动态特性。在物体平面和图像平面平行时,通过微轴孔的精密对准试验验证了上述基于图像矩的视觉伺服控制的有效性。

The conventional image based visual servo control would lead to image singularities that might cause control instabilities, and this problem can be solved by introducing the image moments as features in visual servo control. Where the Jacobian matrix is full rank and upper triangular, thus it has the maximal decoupled structure and simplifies the controller design. Then, PD based visual controller is presented to improve the performance of the visual servo control system instead of the commonly used P controller. Genetic algorithm based PD parameters tuning method is applied to get the optimal parameters. The method proposed is used to align the micro peg and hole, and the experiment results show that the object can reach its desired position faster and more smoothly with PD visual controller.