Learning Mobile Robots

Abstract

In this paper, an up-to-date review is presented of different approaches to the vast field of robot learning. The objective of this paper is to make a robust systematization of knowledge in this area, while focusing on a simple proposed model. Various kinds of learning methods are listed, such as neural networks, empiric learning, genetic algorithms or statistical learning, together with their strong and weak points. Furthermore, aspects are analyzed that make learning subject for mobile robots, while focusing on the most suitable methods for the Powerbot Mobile Robot platform. A model based on the way in which an autonomous mobile robot can use the World Wide Web to determine environment parameters is detailed. Research issues are listed in the last section.