Behaviour Learning System for Robot Soccer Using Neural Network
Moeko Tominaga, Yasunori Takemura, Kazuo Ishii · Research Square · 2021
Abstract Technological developments have raised the promise of a human{robot symbiotic society. A soccer game has characteristics similar to those expected in such a society. Soccer is a multiagent game in which the strategy employed depends on each agent's position and actions. This study discusses the results of the development of a learning system that uses a self-organising map to select behaviours depending on the situation. This system can reproduce the action selection algorithm of all players in a certain team, and the robot can instantly select the next cooperative action from the information obtained during the game. In this manner, common sense rules can be shared to learn an action selection algorithm for a set of both human and robot agents as opposed to robots alone.