Human-robot cooperation strategy for interactive robot soccer by fuzzy Q-learning

This paper presents a learning cooperation strategy based on fuzzy Q-learning in the interactive robot soccer game. The interactive robot soccer game bas been developed to let humans join in the game dynamically and entertain them more. Accordingly, cooperation strategy between humans and autonomous robots is very important for making the game more realistic. Autonomous robots move to their destination depending on the current positions of other robots and the ball. These destinations based on situation will be learned with the fuzzy Q-learning method through playing the game with human operators. In order to evaluate the usefulness of the proposed strategy for the cooperation between humans and robots, the simulation with a modeled human operator and the game with real human operators have been carried out.