Wheeled Mobile Robot Trajectory Tracking Control

In this thesis, trajectory tracking control for AS-R autonomous wheeled mobile robot is considered in theory and application.Firstly, the basic principle of fuzzy control is introduced, and a fuzzy control method of trajectory tracking for AS-R robot is proposed. The proposed method does not depend on the accurate mathematics model, can overcome the effects of the nonlinear, coupling and uncertain factors. Secondly, a kind of neural network based on BP learning algorithm is presented. Then fuzzy inductive inference and self-learning are realized by constructing fuzzy neural network (FNN) that combines fuzzy control and neural network together. FNN uses neural network to realize fuzzy inference, which enable it to have ability of fuzzy inductive inference and ability of tuning the way of inference. Since the construction of FNN has clear meaning, the design and initialization of FNN are also very easy, and a fuzzy Gaussian basis neural network is given. Thirdly, the genetic algorithm is introduced, and the genetic algorithm is used to optimize the FNN's parameters off-line.Finally, software is programmed to implement AS-R autonomous wheeled mobile robot motion control system. Simulation and experiment results validate that the trajectory tracking control laws proposed in this thesis are effective.