Application of normal cloud based adaptive genetic algorithm inUAV path planning
基于正态云自适应遗传算法的无人机航路规划

Sequential genetic algorithm SGA easily gets stuck at a local optimum and has a slow convergent speed. To overcome its shortage, this paper presented NCAGA for UAV path planning. It applied a novel method of encoding based on rectangular plane coordinate system, which simplified the complexity of encoding and achieved a higher planning speed. The improved genetic algorithm combined with the normal X-condition cloud generator to adjust the probability of crossover and mutation adaptively. The stable tendency of normal cloud contributed a higher convergence speed and character of randomness conduced to a lower possibility of premature. Simulation results demonstrate that NCAGA is able to plan path quickly that made UAV avoid the dangerous areas with a higher effectiveness and success rate, so that it has a wide application prospect.