摘要
针对RoboCup比赛中足球机器人在动态环境下的进攻速度缓慢、踢球成功率低的问题,采用改进的协方差自适应进化策略(CMA-ES)的算法法设计了一种双足机器人踢球算法。首先,针对CMA-ES算法本身易于陷入局部最优解的缺点,引入了Tent混沌映射和莱维飞行随机数结合的方法,拓展算法的搜索范围,增加种群粒子数,增强算法的全局探索力;利用改进后的CMA-ES算法优化踢球参数,并用逆运动学方法评价参数的可行性;同时采用踢球代价函数确定最佳踢球点的坐标,并引入贝塞尔曲线插值方法进行轨迹优化。最后通过SimRobot仿真实验和NAO机器人实体对比实验,验证了该方法的正确性和有效性。
Aiming at the problems of slow attack speed and low success rate of soccer robot in RoboCup game in dynamic environment,an improved covariance adaptive evolution strategy is adopted.A biped robot kicking algorithm is designed based on the algorithm method of CMA-ES.Firstly,aiming at the disadvantage that CMA-ES algorithm is easy to fall into local optimal solution,the method of combining tent chaotic mapping and Levy flight random number is introduced to expand the search range of the algorithm,increase the number of population particles and enhance the global exploration of the algorithm,the improved CMA-ES algorithm is used to optimize the kicking parameters and the feasibility of parameters is evaluated by inverse kinematics method.At the same time,the coordinates of the best kicking point are determined by kicking cost function,and Bessel curve interpolation method is introduced to optimize the trajectory.Finally,the correctness and effectiveness of this method are verified by simrobot simulation experiment and Nao robot entity comparison experiment.
作者
周鼎宇
梁志伟
ZHOU Dingyu;LIANG Zhiwei(College of Automation and College of Artificial Intelligence,Nanjing University of Posts and Telecommunications,Nanjing 210023)
出处
《计算机与数字工程》
2023年第9期2013-2018,共6页
Computer & Digital Engineering
基金
国家自然科学基金项目(编号:61573100)
南京邮电大学基金项目(编号:NY219123)资助。
