| Summary: | 碩士 === 國立成功大學 === 電機工程學系碩博士班 === 98 === This thesis mainly confers the development of simulator for humanoid robot soccer competition and its strategies. The simulator is developed for AndroSot in FIRA and kid-sized humanoid soccer in RoboCup. Due to the robot soccer game presents a dynamic and complex environment, it provides a challenging platform for multi-agent research. Furthermore, if there were some problems occurred in the robot actions and image processing algorithm, it is very difficult to run or test strategy systems. In order to solve these issues, a humanoid robot soccer competition’s strategy simulation system is proposed, which provides developer to test the feasibility and advancement of the game strategy. In this simulator, strategies which compiled to DLL files may be explicitly loaded at run-time. And the simulation mode is selectable (AndroSot or RoboCup) for its strategies. In AndroSot, the soccer robots are manipulated to perform the tasks of obstacle avoidance, collaboration, and competition for victory. In order to achieve the goal, a fuzzy logic based strategy is implemented for AndroSot. To lead the robot toward the target while detouring obstacle simultaneously, a potential field algorithm of obstacle avoidance is proposed. In RoboCup, the control strategy of attacking, defending, and collaborating are also described. The localization method of the strategy is realized via the Monte Carlo Localization (MCL) and the robot’s position is recorded and represented as a position probability grid map. Finally, the simulation and experiment results demonstrate the validity and robustness of the simulator and strategy systems.
|
|---|
