基于模糊神经网络再励学习控制器设计及其在倒车模型中的应用  

Design of the controller based on reinforcement learning and its application on truck backer-upper

作　　者：陈涌[1] 陈涛[2] 马勇 

机构地区：[1]华能国际山东分公司,济南250002 [2]山东大学后勤集团,济南250100 [3]河南新飞电器集团公司,河南453002

出　　处：《电机与控制学报》2003年第3期264-266,共3页Electric Machines and Control

摘　　要：考虑到神经网络学习算法的特点,给出了一种基于再励学习的自组织模糊CPN。它结合了模糊自组织CPN和再励算法的优点,在控制过程中在线调整网络结构以及对网络参数学习,学习效率高,控制结构简单。可以不要求受控对象的学习模型,实现在线控制,应用在倒车模型中仿真结果展示了所设计系统的良好控制性能。Several learning algorithms of neural networks are studied and a reinforcement learning based on fuzzy self-organizing CPN controller for uncertain system is presented. The structure and parameters of the control system are tuning on-line and the learning algorithm is fast learning speed. Simulation results with the control system applied to the truck backer-upper model show the good performance of the proposed system.

关 键 词：再励学习控制器 设计 模糊神经网络 倒车模型 

分 类 号：TP273.22[自动化与计算机技术—检测技术与自动化装置]