中文摘要：

文章针对双轮移动机器人的路径跟踪问题，提出了基于反演法的运动学控制和滑模动力学控制相结合的控制算法，运动学控制器解决位姿和跟踪速度之间的控制关系，动力学控制器解决机器人的姿态和控制电压之间的控制关系；为了减小传统运动学控制器的跟踪误差、提高路径跟踪控制的特性，采用RBF神经网络对控制器的不确定参数进行在线自适应学习。仿真结果表明，文中提出的基于RBF神经网络自适应算法比传统控制算法具有更优越的跟踪效果。

英文摘要：

This paper presents an algorithm combining the kinematics controller designed by backstepping method and the dynamics controller designed by the sliding mode control for two＇wheeled mobile robot path tracking. The kinematics controller is used to solve the control relationship between the posture and tracking speed, and the dynamics controller is used to solve the control relationship between the attitude and the control voltage of the robot, In order to reduce the tracking error of the traditional kinematics controller and improve the characteristics of path tracking control, the RBF neural network adaptive online learning is used for uncertain parameters of the controller. The simulation results show that the proposed adaptive algorithm based on RBF neural network has better tracking performance than the traditional control algorithm.