Some Intelligent Control For Robot With Uncertainties

The robot, as the"plant to be controlled", is a multi-input/multi-output, highly coupled, nonlinear mechanical system. As a result of inaccurate measurement and modeling, coupled with changes in load, as well as the impact of external disturbances, in fact, the robot can not be accurate and complete mathematical model. The problem of uncertainty robot stabilization for nonlinear systems,three methods are introduced to control the robot.The problem of uncertainty robot stabilization for nonlinear systems with parameter uncertainties and unknown outside interference is considered. A robust controller, which use non-linear thinking and the state feedback control based on T-S model fuzzy control theory, is designed to achieve the effective attenuation of the system, and guaranteed the system has a good performance asymptotic stability.The sliding mode control has quick response and takes on invariability to system parameter and external disturbance, which can assure the asymptotic stability of system, but being strong fluctuations of control is the shortcoming. The radial basis function neural network(RBFNN) is introduced on base of common sliding mode control, in which the switching function is regarded as the input of RBFNN while the output is switching the absolute value of the gain K, and the object function is set by using the characteristic of sliding mode control. It becomes possible to make the system to eliminate the fluctuations of control and have strong robust by using the learning function of neural network.The sliding mode control demands that the industry value of the uncertainty must be known. However, it is impossible in the practice system. Therefore, the RBF neural network is introduced on base of common sliding mode control. The scheme can achieve tracking effect with high precision and speediness, as well as diminish chattering of control under the condition of existing model error and external disturbance.