基于改进量子头脑风暴算法的UAV三维航迹规划

Three-dimensional path planning for UAV based on improved quantum-behaved brain storming optimization algorithm

针对复杂环境中的无人飞行器航迹规划问题,提出了一种基于改进量子头脑风暴优化(QBSO)算法的UAV三维航迹规划方法.在进化前期,两个种群独立进化,从而提升算法的全局搜索能力.在进化后期,对每个种群中的个体进行排序,每个种群中较优的(排名前50%)个体形成一个新种群,该新种群按照QBSO的进化机制继续进行进化,从而加快算法收敛速度.此外,为进一步提升算法的全局搜索能力,提出了一种改进的待变异个体产生方式.实验结果表明:与基本BSO、QBSO、改进BSO及全局最优BSO算法相比,改进QBSO算法在解决航迹规划问题上具有更高的全局搜索能力、收敛精度和更强的稳定性.

Considering the problem of path planning for unmanned aerial vehicle(UAV)in complex environment,a threedimensional path planning method for UAV based on improved quantum-behaved brain storm optimization(QBSO)algorithm was proposed.In the early stage of the evolution process,two populations evolved independently,thereby improving the global search ability of the algorithm.In the late stage of evolution process,individuals in each population were ranked and those individuals ranked in the top half in each population formed a new population.Then,the new population continued to evolve according to the evolution mechanism of QBSO,which accelerated the convergence speed of the algorithm.In addition,to further improve the global search ability of the algorithm,an improved generation method for individuals to be mutated was proposed.Experimental results show that the path planner based on the improved QBSO algorithm outperforms the BSO,quantum-behaved BSO,improved BSO and global-best BSO algorithms based path planners in terms of explorability,convergence precision and stability.