基于模糊神经网络的移动机器人轨迹实时跟踪

Real-Time Trajectory Tracking of Wheel Mobile Robot Based on Fuzzy Neural Networks

分析了目前主要采用的无障碍环境下轮式移动机器人的轨迹实时跟踪运动控制方法和效果;基于模糊逻辑推理思想和神经网络学习能力,构造了一种模糊神经网络控制器,实现对轮式移动机器人的轨迹跟踪控制。通过对神经网络结构的有效设计和参数学习算法研究,实现了轨迹的实时跟踪。计算机仿真的效果与目前研究的几种方法比较,显示了该文设计方法的有效性和优越性。基于加拿大DrRobot公司的WiRobotX80机器人实验平台,完成了移动机器人实时轨迹跟踪的模拟试验。

Analyze and compare main trajectory tracking control ways and effects for the motion control problem of wheeled mobile robots （WMRs） in environments without obstacles. A fuzzy neural network controller is designed to realize the wheel mobile robot＇s trajectory tracking and motion control based on the idea of fuzzy logic reasoning and neural network learning ability. With reference to the structure and parameter learning way of fuzzy neural network controller, they are improved to lead to a solution of real-time trajectory tracking. The computer simulations, which are compared its performance with that of several existing control ways in a number of computer simulation experiments, show that the fuzzy neural network control is effective and superiority. The implementation of this approach on the WiRobotX80, which is made by DrRobot Company in Canada, is finished. WiRobotX80 is a three-wbeel mobile robot, which is described in detail in paper.