A Hybrid Neural-PID Control Scheme for Adaptive Visual Tracking

This paper addresses a hybrid neural-PID control scheme to nonlinear system for real-time robotic visual tracking of a moving object. By using the motion rules of the CCD camera and the object, the equations of observation and state-space are given. Then, the system can be represented as an MIMO ARMAX model and an efficient estimation model. The adaptive optimal predictor can process on-line estimation of the 3D related parameters between the camera and the object. The control scheme adopts the hybrid neural-PID controller that can adjust the PID controller parameters. The paper concludes with the simulation results and the computer simulation shows that the proposed method is effective to visual tracking of combining vision and control.