改进粒子群算法的无人机三维路径规划

打开文本图片集

中图分类号：TP391.4；G434 文献标识码：A 文章编号：1006-8228（2025）12-08-06

Abstract：ToaddressthelimitationoftraditionalParticleSwarmOptimization（PSO）algorithmsinUAV3Dpathplanning：easily getingtrappedinlocaloptima，animprovedPSOalgoritm（ISO）isproposed.First，terrin-awarerandompermutationofHalton sequencesisemployedforiitializationtohanceparticledistributionuiformityandspatialcoverageSecondnonlineardyamic adjustmentofinertiaweightsandlearningfactorsbalancesglobalexplorationandlocalexploitation.Logarithmicspiraltemsand Laplaceperturbationsareintroducedintothevelocityandpositionupdateparts，espectivelytoimprovetheabilitytoscapelocal optima.Finallyaneliteretentionstrategyandapartialinferiorsolutionre-initilizationstrategyarecombinedtooptimize populatiodiversityExperimentsshowthatISOexhibitssuperiorglobalsearchcapabilitiesandstableoptimizationperforancein complex 3D environments，with a 16.35% increase in average fitness and an 82.78% reduction in standard deviation compared to traditional PSO，and thusoutperforming traditional PSO and other typical path planning algorithms.

Keywords：Halton Initialization;LogarithmicSpiral;ElitePreservation;NonlinearAdaptive;LaplacianPerturbation

0引言

随着科技进步和复杂环境探索需求增加，无人机三维路径规划具有灵活、高效等优点，广泛应用于侦察、物流、巡检、救援等领域。（剩余7392字）