一种基于改进Elman神经网络的机器人行为控制器

Modified Elman Neural Network Controller for Behavior-Based Robot

为了增强移动机器人在动态环境中的学习和适应能力,提出了一种新的基于改进Elman神经网络的具有学习和记忆功能的机器人行为控制器,并且利用遗传算法来优化神经网络的连接权值,提高了机器人行为的准确性和快速型。仿真实验结果显示,本文提出的方法对机器人的学习和适应能力有很大的提高。

It is crucial that a robot should have both learning and evolutionary ability to adapt to dynamic environments. This paper proposes a new robot behavior decision controller using Modified Elman Neural Network （MENN）.The MENN has the advantages of time series prediction capability because of its memory nodes, as well as local recurrent and self-feedback connections, Genetic algorithm is introduced to optimize the connection weight values of MENN in order to achieve better behavior performance. The computer simulation is given to show the validity of the method.