Visual servo control of uncalibrated robot system with dead-zone input

This paper addresses the robust trajectory tracking problem for an eye-in-hand system. It considers not only the uncertainties and disturbances in robot model, but also the unknown dead-zone input. By combing neural network approximation, sliding model control and adaptive technique, the robot can track the desired trajectory well using information proved by a camera. Finally, stability and robustness are proved by Lyapunov method. Computer simulations are presented to confirm the effectiveness of the proposed visual feedback controller.