Scholarlink

Trajectory planning plays a crucial role in UAV flight to improve its efficiency and safety. Particle swarm optimization algorithm (PSO) is a popular trajectory planning method, but it can be plagued by local minima and computational complexity. In this paper, we address these issues by introducing a deep residual learning method to optimize the parameters of PSO to improve trajectory planning for UAVs. The PSO algorithm before and after the improvement is compared using a benchmark test function, which reveals the search advantages of the improved PSO algorithm. Simulation experiments are also conducted in 3D maps for comparison, proving the effectiveness of the improved PSO algorithm trajectory planning.

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 Planning Based on Deep Residual Learning Network Optimization

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Yinghuang Liu,
  • Zhi Lu,
  • Xizhe Tian,
  • Rui Hou

摘要

Trajectory planning plays a crucial role in UAV flight to improve its efficiency and safety. Particle swarm optimization algorithm (PSO) is a popular trajectory planning method, but it can be plagued by local minima and computational complexity. In this paper, we address these issues by introducing a deep residual learning method to optimize the parameters of PSO to improve trajectory planning for UAVs. The PSO algorithm before and after the improvement is compared using a benchmark test function, which reveals the search advantages of the improved PSO algorithm. Simulation experiments are also conducted in 3D maps for comparison, proving the effectiveness of the improved PSO algorithm trajectory planning.