arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.03304eess.SYcs.SY
收藏

一种基于自适应批评者的神经模糊控制器的设计与实现

Design and implementation of an adaptive critic-based neuro-fuzzy controller on an unmanned bicycle

University of Tehran(德黑兰大学)

Ali Shafiekhani, Mohammad J. Mahjoob, Mehdi Akraminia

AI总结:

本文提出了一种用于无人自行车的自适应批评者神经模糊系统,通过结合批评代理信号与误差反向传播,实现模糊推理规则的在线调整,验证了控制器在暂态响应、模型不确定性和在线学习速度方面的优越性。

摘要:

基于动态规划的模糊批评者学习形成了一种强化学习方法。本文提出了一种用于无人自行车的自适应批评者神经模糊系统。批评代理唯一可用的信息是系统反馈,即控制器在前一状态执行的最后动作。批评代理产生的信号与误差反向传播结合,用于调节自适应控制器的模糊推理规则的结论部分。进行了仿真和实验以评估所提控制器的性能。结果表明,所开发的控制器在暂态响应、对模型不确定性的鲁棒性以及快速在线学习方面表现出优越的性能。

英文摘要:

Fuzzy critic-based learning forms a reinforcement learning method based on dynamic programming. In this paper, an adaptive critic-based neuro-fuzzy system is presented for an unmanned bicycle. The only information available for the critic agent is the system feedback which is interpreted as the last action performed by the controller in the previous state. The signal produced by the critic agent is used along with the error back propagation to tune (online) conclusion parts of the fuzzy inference rules of the adaptive controller. Simulations and experiments are conducted to evaluate the performance of the proposed controller. The results demonstrate superior performance of the developed controller in terms of improved transient response, robustness to model uncertainty and fast online learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑