Extending Robot Soccer Using NEAT

Robot soccer is an active research area that offers a challenging research domain to investigate a large spectrum of issues relevant to the development of complete autonomous agents. We used a two‐ and three‐agent robotic soccer simulation to study a coevolutionary learning technique: NeuroEvolution of Augmenting Topologies (NEAT). Our aim is to figure out a good fitness function for the robot soccer player that can learn how to carry the ball, avoid the opponent (the defensive and the goalie) and kick it towards the goal. Through experimentation, we achieve two fitness functions that can be used for both the player and the defender robot. By using these fitness functions, NEAT autonomously evolved suitable neural network architectures for the robots to accomplish the task most of the time, proving that the fitness functions has roughly captured the learning process.