Teaching neural networks using LEGO handy board robots in an artificial intelligence course

Abstract

In this paper we propose a novel method for teaching neural networks with back propagation in an undergraduate Artificial Intelligence course. We use an agent based approach in the course, as outlined in the textbook Artificial Intelligence A Modern Approach by Stuart Russell and Peter Norvig [7]. The students build a robot agent whose task is to learn path-following behavior with a neural network. Robot agents are constructed from standard LEGO pieces and use the MIT Handy Board as a controller.