A Physically Hybrid Strategy-Based Improved Snow Ablation Optimizer for UAV Trajectory Planning

Abstract

Aiming to address the issues of poor optimization-seeking ability and easily falling into local optimization of the Snow Ablation Optimizer (SAO), a Physically Hybrid strategy-based Improved Snow Ablation Optimizer (PHISAO) is proposed. In this paper, a snow blowing strategy was introduced during the initialization phase of the population to improve population diversity. Secondly, the dual-population iterative strategy of SAO has been replaced by a multi-population iterative strategy, which is supplemented with a position update formula for the water evaporation phase. Additionally, Cauchy mutation perturbation has been introduced in the snow melting phase. This set of improvements better balances the exploration and exploitation phases of the algorithm, enhancing its ability to pursue excellence. Finally, a fluid activation strategy is added to activate the potential of the algorithm when its update iterations enter stagnation, helping the algorithm to escape from the local optimum. Comparison experiments between PHISAO and six metaheuristics were conducted on the CEC (Congress on Evolutionary Computation)-2017 and CEC-2022 benchmark suites. The experimental results demonstrate that the PHISAO algorithm exhibits excellent performance and robustness. In addition, the PHISAO is applied into the unmanned aerial vehicle trajectory planning problem together with particle swarm optimization, beluga whale optimization, sand cat swarm optimization, and SAO. The simulation results show that the proposed PHISAO can plan the optimal trajectory in all two different maps. The proposed PHISAO objective function values were reduced by an average of 29.49% (map 1), and 18.34% (map 2) compared to SAO.