Scholarlink

<p>With the rapid advancement of drone technology, drones have emerged as transformative tools in various fields, including agriculture, military operations, marine remote sensing, environmental monitoring, disaster response, and logistics. A key challenge in these applications is the issue of three-dimensional path planning for drones, which has become increasingly significant. This paper proposes a Dynamic Centroid Reverse Learning and Multi-Strategy Improved Northern Goshawk Optimization (DLC-NGO) for global optimization and UAV path planning in complex environments with multiple threats. The proposed algorithm enhances global exploration capabilities, improves population quality, accelerates convergence speed, and boosts optimization performance. To evaluate the effectiveness of the proposed algorithm, comprehensive tests were conducted using the CEC2017 benchmark functions, with performance comparisons against nine advanced algorithms. The results demonstrate that DLC-NGO outperforms other algorithms in numerical optimization tasks, achieving the best performance in&#xa0;20 out of 30 functions (66.7%)&#xa0;of the CEC2017 test set, which highlights its superior optimization capability. The algorithm was also applied to solve the Traveling Salesman Problem (TSP), where it outperformed NGO and its variants by more than 3.60%. Additionally, DLC-NGO was tested in eight diverse UAV path planning scenarios of varying complexity. Compared to traditional and improved swarm intelligence path planning algorithms, DLC-NGO demonstrated superior robustness and optimization capabilities, yielding faster, shorter, safer, and collision-free flight paths. These findings confirm DLC-NGO’s outstanding performance in numerical optimization and UAV path planning, underscoring its broad potential for real-world applications.</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

DLC-NGO: an enhanced northern goshawk optimization for 3D UAV path planning in complex environments with multiple threats

  • 期刊论文

  • 发表日期：

    2025年9月3日

查看全文
  • Shuai Huang,
  • Youfa Fu,
  • Dan Liu,
  • Jiadui Chen,
  • Ling He,
  • Jie Zhang

摘要

With the rapid advancement of drone technology, drones have emerged as transformative tools in various fields, including agriculture, military operations, marine remote sensing, environmental monitoring, disaster response, and logistics. A key challenge in these applications is the issue of three-dimensional path planning for drones, which has become increasingly significant. This paper proposes a Dynamic Centroid Reverse Learning and Multi-Strategy Improved Northern Goshawk Optimization (DLC-NGO) for global optimization and UAV path planning in complex environments with multiple threats. The proposed algorithm enhances global exploration capabilities, improves population quality, accelerates convergence speed, and boosts optimization performance. To evaluate the effectiveness of the proposed algorithm, comprehensive tests were conducted using the CEC2017 benchmark functions, with performance comparisons against nine advanced algorithms. The results demonstrate that DLC-NGO outperforms other algorithms in numerical optimization tasks, achieving the best performance in 20 out of 30 functions (66.7%) of the CEC2017 test set, which highlights its superior optimization capability. The algorithm was also applied to solve the Traveling Salesman Problem (TSP), where it outperformed NGO and its variants by more than 3.60%. Additionally, DLC-NGO was tested in eight diverse UAV path planning scenarios of varying complexity. Compared to traditional and improved swarm intelligence path planning algorithms, DLC-NGO demonstrated superior robustness and optimization capabilities, yielding faster, shorter, safer, and collision-free flight paths. These findings confirm DLC-NGO’s outstanding performance in numerical optimization and UAV path planning, underscoring its broad potential for real-world applications.