| Summary: | 碩士 === 淡江大學 === 機械與機電工程學系 === 92 === This thesis presents the design of an Action Selection Mechanism (ASM) for soccer robots using artificial immune network (AIN). Each robot executes its own actions provided by the ASM, and group of robots perform a formation task by collaboration. The proposed mechanism is applied to small-size robot soccer game, in which the global coordinates of the soccer robots are known by image processing. The game strategy is designed according to the positions of the ball and robots on the soccer field. Strategy design includes three major procedures. First, according to the situation in the soccer filed, a term formation is decided for the soccer term and a role is selected for each individual robot. Second, each robot executes an action provided by the AIN-based ASM to fulfil its role playing. Finally, the robot action is executed by using a point to point motion controller. The simulation results show that the AIN-based ASM can be applied to a multi-robots system and execute the task of group control successfully. The integrated system is also tested on a RoboCup small-size soccer filed. Experiments of ASM based on AIN algorithms include ball tracking and shooting, and obstacle avoidance. The results show that the proposed ASM provide an applicable algorithm for mobile robots to play soccer game.
|
|---|
