Scholarlink

<p>To effectively address the multi-objective optimization challenges in multi-UAV logistics distribution, such as path length, collision risk, and multiple constraints, and to overcome the inadequacy of the traditional Gray Wolf Optimizer (GWO) in path planning, an Improved Hybrid Strategy Gray Wolf Optimizer (IHS-GWO) is proposed. By enhancing the global search capability of GWO across multiple dimensions, chaotic mapping is introduced to initialize the population, leveraging chaotic sequences to improve the uniformity of the initial population and prevent premature convergence. The ratio of individual path length to the global optimal path length is incorporated to construct an adaptive convergence factor, accommodating differences in path quality. A global best individual guidance term and a weighting strategy are added to break through the limitations of local high-quality individual guidance, efficiently exploring global initial solutions that balance collision risk, path length, and trajectory smoothness. In local planning, the Hill Climbing Algorithm (HC) is integrated to form a deep collaborative mechanism, capturing real-time changes in obstacles, path allocation conflicts, and other constraints. Through local gradient-based optimization, paths are adjusted, simultaneously optimizing smoothness and obstacle avoidance, and enabling rapid replanning in dynamic environments. This fusion mechanism addresses the imbalance in global optimization and the short-sightedness of local decision-making. Experimental results demonstrate that IHS-GWO achieves superior optimization accuracy and stability across various benchmark functions of CEC2017. In multi-UAV scenarios, compared to GWO, IGnT, IGnaa, IGngw, and IGnH algorithms, it significantly optimizes path length, fitness value, and collision frequency. When compared to GA, SA, WOA, NWOA, GOA, ACO, PSO, GEPSO, GWO, IGWO, and NAS-GWO algorithms, the average path ratio is reduced by 15.68%, the average fitness ratio is increased by 29.25%, and the average number of collisions is reduced by more than 4. The cross-modal optimization capability is remarkable. This research holds significant importance for improving the efficiency of multi-UAV logistics transportation, reducing costs, and enhancing environmental adaptability, providing new insights for the application of multi-UAV collaborative distribution.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

UAV Trajectory optimization method based on improved grey wolf optimizer with hybrid strategy

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月12日

查看全文
  • Jian Deng,
  • Honghai Zhang,
  • Yuetan Zhang,
  • Gang Zhong,
  • Mingzhuang Hua

摘要

To effectively address the multi-objective optimization challenges in multi-UAV logistics distribution, such as path length, collision risk, and multiple constraints, and to overcome the inadequacy of the traditional Gray Wolf Optimizer (GWO) in path planning, an Improved Hybrid Strategy Gray Wolf Optimizer (IHS-GWO) is proposed. By enhancing the global search capability of GWO across multiple dimensions, chaotic mapping is introduced to initialize the population, leveraging chaotic sequences to improve the uniformity of the initial population and prevent premature convergence. The ratio of individual path length to the global optimal path length is incorporated to construct an adaptive convergence factor, accommodating differences in path quality. A global best individual guidance term and a weighting strategy are added to break through the limitations of local high-quality individual guidance, efficiently exploring global initial solutions that balance collision risk, path length, and trajectory smoothness. In local planning, the Hill Climbing Algorithm (HC) is integrated to form a deep collaborative mechanism, capturing real-time changes in obstacles, path allocation conflicts, and other constraints. Through local gradient-based optimization, paths are adjusted, simultaneously optimizing smoothness and obstacle avoidance, and enabling rapid replanning in dynamic environments. This fusion mechanism addresses the imbalance in global optimization and the short-sightedness of local decision-making. Experimental results demonstrate that IHS-GWO achieves superior optimization accuracy and stability across various benchmark functions of CEC2017. In multi-UAV scenarios, compared to GWO, IGnT, IGnaa, IGngw, and IGnH algorithms, it significantly optimizes path length, fitness value, and collision frequency. When compared to GA, SA, WOA, NWOA, GOA, ACO, PSO, GEPSO, GWO, IGWO, and NAS-GWO algorithms, the average path ratio is reduced by 15.68%, the average fitness ratio is increased by 29.25%, and the average number of collisions is reduced by more than 4. The cross-modal optimization capability is remarkable. This research holds significant importance for improving the efficiency of multi-UAV logistics transportation, reducing costs, and enhancing environmental adaptability, providing new insights for the application of multi-UAV collaborative distribution.