Application of Fuzzy Self-adapting Kalman Filter in the Control System of an Eradicating Stump Robot

摘要

In this paper the structure and function of an eradicating stump robot is introduced. In order to eradicate efficiently a tree stump, RBF neural network based on fuzzy self-adapting Kalman filter is applied to control the manipulator motion. By programming with MATLAB and solidifying the program into a chip, the data obtained from the CCD and the sensors on line is processed so as to control the operation of eradicating stump automatically. The test shows that the automatic control system of neural network is effective and the stump eradicated by the robot is about 120 stump whose diameter is over 0.5m per day, the efficiency of which is 25-30 times than that of a eradicating by hand.