Uncalibrated Image-Based Visual Servoing Control based on Image Occlusion using Dual Adaptive Strong Tracking Kalman Filter

Abstract

Focusing on the challenge of visual servoing control subject to feature lost or occlusion, the scenarios of image features being lost or occluded with image features are analyzed. An adaptive strong tracking Kalman filter (ASTKF) is adopted to adjust the image information to improve the accuracy of state vector estimation of lost or occlusion. Another ASTKF is presented to estimate the image Jacobian matrix dynamically in an unstructured environment. Considering the kinematic behavior of visual servoing, combining with the uncertainties of the camera and the manipulator model, proportional-differential and sliding mode control (PD-SMC) method is employed to further enhance the accuracy and robustness of visual tracking. The simulation study is given to show the effectiveness of the proposed scheme.