Path Planning Based on Dynamic Sub-population Pseudo-Parallel Genetic Algorithm

Through analysis of present pseudo-parallel genetic algorithm, propose a new dynamic sub-population pseudo-parallel genetic algorithm. It changes the condition that the magnitude of sub-population is stationary in current information exchange model, the magnitude of sub-population will change with the evolution. This algorithm can not only restrain premature convergence, but also get global values and local values rapidly. Design the adaptive crossover operator according to the generation. The crossover probability will adjust to the evolution, which accelerates the convergence. Through test function, the accuracy and superiority of this algorithm are proved. The simulation shows that the proposed algorithm is reliable and efficient in the path planning of robot soccer.