基于遗传算法的机器人自定位

为了解决中型组比赛环境下的足球机器人自定位、绑架和跟踪问题,提出一种基于遗传算法的机器人连续自定位方法.首先,从全景图像中提取出场上黑线与机器人辐射线的交点;然后,把该交点与环境地图对应黑线间距离之和的最小值做为适应度函数;最后,以机器人中心坐标做为个体,进行选择、交叉和变异操作,收敛到机器人的自定位坐标.另外,针对绑架和连续定位,在遗传算法全局自定位基础上利用梯度优化算法局部修正主位姿,提高了自定位精度和算法的鲁棒性.仿真结果和场地环境机器人自定位试验说明了该定位方法的有效性.

GA-based self-localization of robot soccer

In order to solve kidnapping and tracking of Robocup un der the match environment of middle-size Robocup soccer team,a continuous self-positioning method of robot based on genetic algorithm(GA) was put forward.F irst the intersection was taken between the white line on the field and the radi um of robot from the panoramic image.Second the minimum value of the sum of the distance between the intersection and the corresponding white line on the envir onmental map was taken as fitness function.Third,with the c...