基于融合改进人工鱼群算法的无人机航迹规划  

Drone Trajectory Planning Based on Improved Artificial Fish Swarm Algorithm

作　　者：王璞 刘宏杰 WANG Pu;LIU Hongjie(School of Information Science&Engineering,Kunming 650500,China)

机构地区：[1]云南大学信息学院,昆明650500

出　　处：《火力与指挥控制》2025年第2期93-99,共7页Fire Control & Command Control

摘　　要：针对标准人工鱼群算法(AFSA)在复杂环境下进行航迹规划时,存在航迹求解精度低、难以跳出局部最优等问题,提出一种优化的自适应人工鱼群算法(IAAFSA)。该算法引入鱼群自适应策略,动态调整鱼群的步长和拥挤度因子,以平衡前期探索能力与后期求解精度;引入PSO的社会认知观点,加快算法的收敛速度;在鱼群迭代求解过程中进行精英策略的交叉繁衍,以增强种群的多样性,提高算法在全局搜索中寻到更优解的能力。实验中,使用MATLAB对两个具有不同地形特点的地图进行仿真验证,结果表明IAAFSA在解决三维航迹规划问题时具有更好的收敛速度和寻优精度。In response to the issues of low solution accuracy and difficult to escape from local optimal problems,etc.when applying the standard Artificial Fish Swarm Algorithm(AFSA)for trajectory planning in complex environments,an improved algorithm called the IAAFSA is proposed.Firstly,this algorithm incorporates a self-adaptive strategy for the fish swarm,the step size and crowding factor are dynamically adjusted to balance the early exploration capability with the later solution accuracy.Secondly,it introduces the social cognitive perspective from PSO to accelerate the convergence speed of the algorithm.Finally,during the crossbreeding of the elite strategy during the iterative solving process of fish swarm,the diversity of population is enhanced,thereby the algorithm's ability to find better solutions in global search is improved.In the experiment,MATLAB is used to simulate and validate the algorithm on two maps with different terrain characteristics.The results indicate that IAAFSA demonstrates better convergence speed and optimization accuracy when addressing three-dimensional trajectory planning problems.

关 键 词：无人机 航迹规划 自适应人工鱼群算法 社会认知 精英策略 交叉繁衍 

分 类 号：V279[航空宇航科学与技术—飞行器设计] V249