Mobile robot navigation: Neural q-learning

Abstract

This paper presents the mobile robot navigation technique which utilizes Reinforcement Learning (RL) algorithms and Artificial Neural Network (ANN) to learn in an unknown environment for mobile robot navigation. This process is divided into two stages. In the initial stage, the agent will map the environment through collecting state-action information according to the Q-Learning procedure. Second training process involves Neural Network, which utilizes the state-action information gathered in the earlier phase of training samples. During final application of the controller, Q-Learning would be used as primary navigating tool whereas the trained Neural Network will be employed when approximation is needed. MATLAB simulation was developed to verify and validate the algorithm before real time implementation using Team AmigoBotTM robot. The results obtained from both simulation and real world experiments are discussed.