基于神经网络的强化学习在避障中的应用

Neural network-based reinforcement learning applied to obstacle avoidance

为了提高移动机器人的自学习能力,在基于行为控制结构的基础上设计了智能控制结构,该结构引入了强化学习模块。神经网络具有很好的泛化能力,该文提出了基于神经网络的强化Q学习算法,克服了表格式Q学习算法只能应用到离散的状态中并需要大量存储空间的不足,最后结合智能控制结构应用到移动机器人的避障中。实验结果表明,该方法能够使移动机器人通过自学习实现自主避障。

An intelligent control architecture with reinforcement learning was designed based on a behavior-based architecture to improve the learning ability of mobile robots.Normal tabular Q-learning can only be applied to discrete states and requires a large memory.Since neural networks have good generalization,a Q-learning system was developed based on a neural network for obstacle avoidance of mobile robots.Experiments show that the mobile robot can then learn to avoid obstacles.