Action selection in robot soccer using case- based reasoning"
Designing coordinated robot behaviors in uncertain, dynamic, real- time, adversarial environments, such as in robot soccer, is very challenging. In this talk I will present a case-based reasoning approach for cooperative action selection, which relies on the storage, retrieval, and adaptation of example cases. I will focus on cases of coordinated attacking passes between robots in the presence of the defending opponent robots. I will introduce a retrieval technique that weights the similarity of a situation in terms of the ball and the robots positional features, as well as in terms of the cost of moving therobots from the current situation to match the similar cases. Case retrieval and reuse are achieved within the distributed team of robots through communication and sharing of own internal states and actions. Finally I will discuss an evaluation of our approach, both in simulation and with real robots, in laboratory scenarios, with two attacking robots versus two defending robots as well as versus a defender and a goalie and I will show that the desired coordinated passing behavior is achieved and also outperforms a reactive action selection approach.