抄録
This paper addresses uncalibrated image-based visual servoing utilizing a fixed camera with estimation of the image Jacobian without knowledge of camera configuration or robot kinematics. The image Jacobian is estimated using the affine model of the end-effector feature. The robot system is controlled using the nonlinear least squares optimization technique for minimizing the image error between the goal position and the position of the end-effector. In order to avoid the obstacle, the composite cost function is proposed. The simulation results show the validity of the proposed method.
