论文部分内容阅读
提出了一种基于反演设计和RBF神经网络自适应的非完整移动机器人轨迹跟踪方法.首先,设计一个虚拟的速度控制律使得输出跟踪误差尽可能小;然后,利用反演技术设计一个基于RBF神经网络的动力学控制器,以确保在机器人系统中存在不确定性和外界扰动的情况下,机器人仍具有良好的跟踪能力.RBF神经网络连接权值在线自适应律由Lyapunov理论导出,保证了控制系统的稳定性.本文提出方法的主要优点是不需要移动机器人动力学的先验知识,而且对外界扰动具有良好的鲁棒性.最后,在两轮非完整移动机器人上的仿真结果证明了本文所提出方法的有效性.
A method of trajectory tracking of nonholonomic mobile robot based on backstepping design and RBF neural network is proposed.Firstly, a virtual velocity control law is designed so that the output tracking error is as small as possible. Then, an RBF Neural network dynamics controller to ensure that the robot still has good tracking ability in the presence of uncertainties and external disturbances in the robot system.The online adaptive law of RBF neural network connection weights is derived from Lyapunov theory and guaranteed Control system’s stability.The main advantage of the proposed method is that it does not need the prior knowledge of mobile robot dynamics and has good robustness to external disturbances.Finally, the simulation results on two rounds of nonholonomic mobile robots demonstrate that The effectiveness of the proposed method in this paper.