论文部分内容阅读
为建立一套新型的机器人系统 ,以满足机器人足球比赛的要求 ,设计并实现了清华机器人足球队。在介绍国际机器人足球比赛 (Robo Cup)环境的基础上 ,按照智能程度由低到高的顺序 ,论述了从动作层到决策层的实现方法。包括机器人的整体结构 ,运用多层前馈神经元网络学习个人技术 ,运用优先级方法设计机器人的顶层决策算法来实现多个机器人的合作与对抗。机器人系统完全满足 Robo Cup比赛的要求 ,并在中国 Robo Cup2 0 0 0锦标赛中取得了好成绩。对国内相关领域的研究以及兄弟院校开发机器人足球队具有重要意义
In order to establish a new type of robot system to meet the requirements of robot soccer match, Tsinghua Robot Soccer Team was designed and implemented. Based on the introduction of the environment of Robo Cup, this paper discusses the method from the action level to the decision level according to the order of intelligence level from low to high. Including the overall structure of the robot, multi-layer feedforward neural network learning individual technology, the use of priority methods to design the robot’s top decision algorithm to achieve the cooperation and confrontation of multiple robots. The robot system completely fulfilled the requirements of the Robo Cup and achieved good results in the Robo Cup 20000 Championship in China. It is of great significance for the research in related fields in our country and for the development of the robot soccer team in other universities