A neural-network based autonomous navigation system using mobile robots

Abstract

This paper presents an autonomous navigation system based on neural networks using mobile robots. While this kind of navigation system has many applications, there are two main challenges: the learning capability of the robot, as well as a complex and dynamic navigation environment. The main contribution of this paper is to develop a navigation system with learning capability to adapt to an unknown environment. In particular, the neural network model is specifically designed for our autonomous robot navigation system, and a series of training samples are developed to train the neural network for the robot. In addition, we incorporated sonar sensors with the neural network to solve the problem of autonomous robot navigation. This approach is validated with the simulation and experimental results. It was shown that the robot with the well-trained neural network can navigate out of a specifically designed maze successfully.