Adaptive Robot Soccer Defence Strategy via Behavioural Trail

Abstract

Robot soccer is a challenging platform for multi-agent research, involving topics such as real-time image processing and control. A team of robots must work together to put the ball in the opponent’s goal while at the same time defending their own goal. A good strategy for the robot defenders can determine who wins the robotic soccer game. Therefore, the goal of this study is to propose a strategy for the defenders using a production rule based on state diagrams. The rule can facilitate easy and rapid comprehension of certain behaviors with respect to two indicators, such as condition and action. The authors determine five key aspects as conditions, including the positions of two defender robots, the position of the goalkeeper and the ball, and coordination between two defender robots and the goalkeeper robot. Each robot has been set its own defence area and specific actions. They conducted three experiments namely simulator testing, real time testing, and ping pong testing to evaluate their proposed defence strategy. The experimental results show that the authors’ proposed strategy versus three state of the art strategies can defeat up to 92% of all types of attack modes. Meanwhile, in the ping pong testing, their proposed strategy can still protect any goal entering from different attacking modes even though only one or two robots are active in the defence area.