基于黄金分割律选择算子的改进进化编程算法及其在机器人路径规划中的应用

通过分析及结合机器人路径规划的进化编程仿真实验指出,保存最优个体或淘汰最差个体都会引起进化算法早熟现象,并提出如下改进算法按适应度从高(优)到低,依黄金分割律分别取出优秀和最差部分个体(染色体),通过赌轮法,并按适者生存原则从优秀的部分中选择一个体直接进入子代,而按劣者淘汰原则从最差部分中选择一个体从子代中排除.将改进算法运用于机器人路径规划,通过仿真实验检验了算法的有效性.

Improved Evolutionary Programming Based on Golden Section' Operator and Its Application to Path Planning of Robots

It is shown by analysis of evolutionary programming algorithm and experiments of it in the path planning of robots that saving the fittest in every generation of evolutionary programming algorithm may be the source of prematurity convergence. A improving algorithm is put forward: By employing Golden Section we choose some high-fitness chromosomes in a generation, then according to the principle of survive of the fittest, by roulette wheel selection based on fitness, to get one from the chosen chromosomes, which will come into the next generation. On the other hand, according to the principle of eliminating of the bad, that which is chosen in some low-fitness chromosomes in the next generation will be excluded. The improving algorithm has been applied on the path planning of robots, and by emulational experiment the validity of it has been checked out.