Surveying the Application of Iterative Learning Strategy in Uncalibrated Vision-Based Robot Manipulators Control.

This article presents an iterative learning scheme for studying the problem of vision guided robot trajectory tracking. Traditionally visual sensing and manipulation are combined in an open-loop fashion, ‘looking’ then ‘moving’. The accuracy of the operation depends directly on the correctness of the visual sensor, manipulator and robot controller. An alternative to increasing the accuracy of these subsystems is to use a visual-feedback control loop, which will increase the overall accuracy of the system, a principle concern in any application. In this paper, the problem visual servoing is studied with a more general point of view under one aspect. It will consist of proposing an uncalibrated visual servoing, which can deal with unknown environment without using a-prior knowledge based on iterative learning method. To show the practical applicability of the proposed method it has been applied to PUMA560 manipulators using a simulation model to confirm that the method can work properly.