Curve Control Points-based Feature Extraction for Visual Servo with rotational pose compensation

The spline curve is commonly used for describing the contour of the target object in the field of image-based visual servo (IBVS). However, this method has the disadvantage of low sensitivity and poor precision when facing the camera's rotational motions. To solve this problem, a visual servo system with rotational pose compensation is presented in this study. The NURBS (Non Uniform Rational B-spline) curve is firstly used to obtain the curve control points by fitting the projected curve of the target contour on the image plane. And then, the control points are employed for constructing the image Jacobian matrix. The rotational compensation controller is designed to compensate the rotational motions of the robot. To verify the feasibility of this method, a set of visual servo tasks are carried out on the Puma560 platform. Experimental results demonstrate that the proposed method has high accuracy and computational efficiency.