基于混合樽海鞘差分进化算法的航迹规划方法

A path planning method based on hybrid salp swarm-differential evolution algorithm

针对目前利用差分进化算法进行三维航迹规划时存在的早熟收敛、搜索停滞等问题,提出了一种基于混合樽海鞘差分进化算法的航迹规划方法。该算法根据种群多样性大小自适应地将种群划分为多个子种群,利用樽海鞘算法的个体更新策略可使不同子种群间进行充分的信息交流,避免算法在早期陷入局部最优,并在子种群内部利用自适应交叉算子进行差分进化以保证算法收敛。将算法应用于无人机的三维航迹规划,同时进行仿真试验,并与传统的差分进化算法进行比较,验证了该算法的有效性。

Aiming at the problems of premature convergence, search stagnation and so on existing in the three-dimensional path planning currently using differential evolution algorithms, a path planning method based on the hybrid salp swarm-differential evolution algorithm was proposed. The algorithm adaptively divided the population into multiple sub-populations according to the population diversity and utilized the individual updating strategy of the salp swarm algorithm to make full information exchange between different sub-populations, avoiding the algorithm falling into a local optimal in the early stage, and the differential evolution algorithm of adaptive crossover operator was performed within the sub-populations to ensure the convergence of the algorithm. In this paper, the algorithm is applied to the three-dimensional path planning of UAVs, and simulation experiments are performed, and compared with the traditional differential evolution algorithm to verify the effectiveness of the algorithm.