基于最优化模糊逻辑的Robocup中型组动态角色分配

摘要

In the Robocup Mid-size Group competition, teams select the dynamic role assignment will produces system oscillation, time lag and system low sensitivity and others. Improvement of the dynamic role assignment system introduces the introduction of the role of feedback system and using the Frank-Wolfe arithmetic optimization calculate parameter of overshoot, Select key factor most superior influence time which robot gained ball. Role assignment system define degree of membership relations of robot to the role which use the reduced fuzzy control model after determines the weight of each influence factor, robots are assigned role for degree of membership. Simulation and experiment result has indicated the feasibility, the stability and the rapidity of this design.%Robocup中型组机器人足球比赛中,采用动态角色分配系统的队伍在进行角色分配时产生系统振荡、时间滞后和系统反应不灵敏等同题.改进后的动态角色分配系统引入角色跟随反馈系统,选取机器人超调参数利用Frank-Wolfe算法进行最优化计算以及确定影响机器人获取球的时间因素和各影响因子的权值后采用简化的模糊控制模型确定机器人对角色的隶属度关系,机器人则根据隶属度关系进行角色分配.实验和仿真结果表明这种设计的可行性、稳定性和快速性.