In this paper we describe the design and implementation of an educational methodology based on a robotic platform used for the small size league (SSL) challenge of the RoboCup initiative. The methodology is based on three main aspects of the learning process, namely classical conditioning, reinforcement learning and cognitive learning. This is achieved through the combination of robotic concepts applied to the soccer problem; a highly interesting topic to the students, together with skill oriented modules. We show practical results achieved after applying this methodology in specific courses in an undergraduate electrical engineering program. Our initial results demonstrate that it is possible to attain significantly better results in terms of learnt concepts and motivation when using our robotic soccer based strategy.
Tópico:
Reinforcement Learning in Robotics
Citaciones:
2
Citaciones por año:
Altmétricas:
0
Información de la Fuente:
Fuente2021 20th International Conference on Advanced Robotics (ICAR)