Expansion of the Workspace of Eye-in-hand Industrial Robots for Robust Hybrid Vision/force Control

In this paper, a novel approach to workspace expansion for eye-in-hand industrial robots is presented to address the problem of the camera's field-of-view (FOV) limitation in hybrid vision/force control. During the interaction with the workpiece, the camera and the workpiece are at a short distance from each other. Thus, the FOV is very small, which restricts the robot's workspace. To handle this issue, instead of using only a feature object in conventional image-based visual servoing (IBVS), an array of objects is provided on the workpiece in a way that at least one object is entirely in the FOV. However, the conventional IBVS cannot be employed for hybrid vision/force control of such tasks. Thus, for this purpose, using a fuzzy inference system (FIS) and orthogonality principle, a novel hierarchical sliding surface is devised, and the continuous integral sliding mode controller (CISMC) is adopted, which leads to a robust and precise control method to fulfill the mentioned task. The stability of the proposed method is also proved. Experimental tests are conducted using an industrial robot on a workpiece whose results reveal the feasibility and effectiveness of the proposed approach. The results are also compared with traditional methods and show that the workspace expansion and control performance have been improved to a great extent.