本論文為建構基於機器人作業系統(Robot Operating System, ROS)的足球機器人策略系統，其規則為符合FIRA (Federation of International Robot-soccer Association) 的RoboSot組別比賽而設計。現在的機器人軟體在設計上日益複雜，在機器人的開發人員中不一定有資訊相關領域之人材。因此本論文提出在ROS上架構足球機器人策略系統，以利用ROS中可幫助機器人系統開發之工具，如actionlib套件、SMACH套件及tf套件等。ROS的系統架構為分散式架構，以點對點網路將所有的處理序連接在一起交換資訊。這個架構使得系統可以容易的做到平行處理以及方便在開發上做分工。本論文提出的足球機器人策略系統包含了世界模型套件、策略套件及軌跡規劃套件。在策略套件的部分則採用了動態角色分配的技術，使比賽中可以動態的切換機器人之任務角色。在世界模型套的部分使用了tf套件管理各個物件之坐標。在軌跡規劃套件則採用了多種機器人路徑規畫及速度規劃。最後我們在Gazebo模擬器上建構了一個3D的機器人足球場地模擬環境，以驗證提出的足球機器人策略系統的可行性。 In this paper, we built a soccer robot strategy system that is based on Robot Operating System (ROS). The soccer robot strategy system is capable with FIRA RoboSot competition rule. Nowadays, the development of a robot software system became more and more complex. Developers of robot software system may not have very well knowledge about computer science field. So this paper proposes a soccer robot software system based on ROS that we can use tools of ROS to help and develop the strategy system, like actionlib package, SMACH package, tf package, etc. The system architecture of ROS is a distributed system. The ROS uses peer-to-peer network to link all processes to exchange data. Due to this kind of architecture, we can parallel process data and divide the work easily. The soccer robot strategy system we proposed is including a world model package, strategy package and trajectory package. About strategy package, we used dynamic role assignment. About world package, we used tf module to manage axes of objects. And the trajectory package is used to path planning and velocity planning. So the robot can change role dynamically in a game. Finally, we built a 3D simulation environment in Gazebo simulator to verify the soccer robot strategy system.
