基于遗传算法有障碍物的机械手工作空间研究

Manipulator's Working Space Research on Obstacle's Effect Using Genetic Algorithm

机械手工作空间的测定非常复杂,在机械手可伸展的区域如果遇到障碍物将会使测定变得更加复杂;障碍物会影响到整个机械手的工作空间的形状和尺寸,甚至会将机械手的工作空间分成两个或多个独立的区域,以至原来可测量的区域变成不可测量区域;本文针对在机械手工作空间中存在障碍物的情况,将其工作空间进行离散化并利用遗传算法对其工作空间进行估算,通过确定X_(SP),Y_(SP),Z_(SP)在工作空间中的位置来获得机械手工作空间,获得了比以往更加精确的工作空间;将搜索空间离散化为有限个点大幅减少了计算时间,同时遗传算法可以有效的解决搜索空间离散化之后点的位置的确定的优化问题。

The workspace （WS） determination of a Manipulator is a complex problem. Obstacle presence does not only exclude points from the original WS but it affects the whole workspace＇s shape and size to the extent that it sometimes divides the working space in two or more separate regions that cannot be linked by the same Manipulator. This paper presents an approach for the estimation of the manipulator＇s WS in the presence of obstacles. The author scatters the search volume and uses genetic algorithms to estimate its workspace. By determining the position of every WSP in the working space, this paper obtains a more accurate result than ever before. The search volume is discretized into finite points and significant reduced the computational time, genetic algorithm can efficient solve the problem of identifying the discretized points＇ position in the search volume.