Performance Investigation and Improvement for the Uncalibrated Hand-Eye Coordination System

The paper studies performance of the uncalibrated hand-eye coordination system, whose image Jacobian matrix is estimated by Neural Network way. Since the training conditions of NN are far from that of the practical working conditions, there are some unmodelled dynamics to be compensated in system controller designing. The discrete model of the system is set up, in accordance with the system dynamics and visual information processing, so that the system´s performance and stability are well investigated, which leads to improved control method. Simulation results validate the effectiveness of the proposed method.