A Robust Predictor for Image-Based Visual Servoing

The main control problem of visual servoing is to cope with the delay introduced by image acquisition and image processing. This delay is the main reason for limited tracking velocity and acceleration. Predictive algorithms are one solution to handle the delay. A predictor is constructed using BP neural network. It is able to estimate the moving target state even if the motion model of the target is unknown. The composite Jacobian is estimated on-line based on changes in image features and joint angles, eliminating the need for a precise analytical model. Target tracking is achieved by adaptive PD control algorithm with uncertain gravity compensation. Robot control is not dependent on the robot and camera configurations. The visual servoing control scheme provides a good steady-state tracking behaviour and keeps good robustness and adaptability at the same time