一种新的路径编码机制在移动机器人路径规划中的应用

针对基于遗传算法的移动机器人路径规划，本文提出了一种新的定长十进制路径 编码机制．首先，将移动机器人所处环境中的障碍物表示成多边形的形式，并对各障碍物顶 点用十进制进行任意编号，然后将移动机器人的路径编码成定长为所有障碍物顶点个数之和 的十进制染色体串．串中，非零位上的十进制值表示路径经过了相应编号的顶点，各顶点在 串中的顺序就是它们在路径中的顺序．此编码方式克服了已有的变长编码机制及定长二进制 编码机制需特殊遗传操作算子和特殊解码的缺陷，使得算法更加简单有效．

THE APPLICATION OF A NOVEL PATH ENCODING MECHANISM IN PATH PLANNING FOR A MOBILE ROBOT

For genetic algorithms based path planning of a mobile robot, a novel fixed-length decimal encoding mechanism for the paths of the mobile robot is proposed in this paper. First of all, the obstacles in the robot environment are described as polygons. Then, the vertexes of all polygons are numbered in decimal. The paths are then encoded into decimal chromosomes of fixed length, which equal the amount of all vertexes. In such a chromosome, each nonzero bit is the decimal number of a vertex the path passes. The order of vertexes in a chromosome is that in a path. Such an encoding mechanism overcomes the shortcomings of variable-length encoding mechanism and other fixed-length binary encoding mechanisms where special decoding and genetic operators are needed, resulting in simplicity and effectiveness of the algorithm.