Intellectual method of guiding mobile robot navigation using reinforcement learning algorithm

One of the interesting parts in mobile robot is to navigate independently. It is a difficult task, which requiring a complete showing of the environment and intelligent algorithm. This paper presents an Intellectual navigation method for an autonomous mobile robot which requires only a learning signal such as a feedback indicating the quantity of the applied action. The Q-learning algorithm of reinforcement learning is used for the mobile robot navigation by discrete states and actions in the environment. The Markov decision process is used to improve the performance of the robot navigation. The effectiveness of this optimization method is verified by simulation.