Decoupled image-based visual servoing for robotic manufacturing systems using gain scheduled switch control

Abstract

In this paper, a decoupled image-based visual servoing (IBVS) controller for an eye-in-hand robotic system is presented. This controller can provide fast response system to meet the demand of robotic manufacturing applications. The proposed control algorithm decouples the rotational and translational camera motions and makes three separate stages of control with different gains for each one. A switch scheme for these three stages of control is proposed. The controller is implemented on a Denso robot with a camera installed in an eye-in-hand configuration. Experimental results show the significant enhancement of the control performance in terms of the response time over the traditional IBVS. In addition, the proposed method succeeds in fulfilling some tasks where traditional IBVS fails.