HOW INTRODUCING ARTIFICIAL INTELLIGENT BEHAVIOURS IN EDUCATIONAL ROBOTICS

This paper presents a didactical experience using an Artificial Neural Network on a LEGO Mindstorms NXT robot. Artificial Intelligence is an advanced topic with a broad variety of application fields and robotics is one of the most promising both for practical effectiveness and future developments. Robotics particularly attracts pupils but they get even more interested if the robot can show a certain degree of automatic learning. Educational robotics is a new subject where teachers and researchers are involved in providing methodological and practical frameworks to develop robotic-enhanced project-based activities to support in a new way the teaching/learning of scientific and non-scientific disciplines at different levels. The presented experience deals with a simplified version of the Optical Recognition of Characters using standard sensors and firmware on the NXT and the NXC programming language. The user gives a command to the robot on a small stripe of white paper in form of a handwritten sequence of black/empty squares. Each command learnt during a training phase by an Hopfield Neural Network implemented in the robot program, is associated with a simple motion of the robot. This work was made in the framework of European TERECoP (Teacher Education on Robotics-Enhanced Constructivist Pedagogical Methods) project aimed to define a curriculum for teacher training on educational robotics