多策略改进麻雀搜索算法的无人车路径规划
DOI:
CSTR:
作者:
作者单位:

沈阳化工大学机械与动力工程学院

作者简介:

通讯作者:

中图分类号:

基金项目:


Improved Sparrow Search Algorithm for Unmanned Vehicle Path Planning
Author:
Affiliation:

School of Mechanical and Power Engineering, Shenyang University of Chemical Technology

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为解决麻雀搜索算法应用于无人车路径规划中存在寻优精度不足、寻优效率低和易陷入局部最优的问题,提出一种多策略改进麻雀搜索算法。通过引入二次复合混沌映射对初期种群进行初始化操作,丰富种群多样性;在发现者的位置更新方式中融入基于Logistic函数的自适应惯性权重机制,以平衡算法的全局搜索与局部搜索能力;通过引入非线性扰动因子的正余弦算法对追随者位置更新进行改进,增强算法寻优速度和寻优精度,提升跳出局部最优的能力。实验结果表明:改进麻雀搜索算法在寻优精度和和寻优效率方面均实现显著的优化效果,验证其在无人车路径规划中的有效性。

    Abstract:

    To address the issues of insufficient optimization precision, low optimization efficiency, and susceptibility to local optima when the Sparrow Search Algorithm (SSA) is applied to unmanned vehicle path planning, a multi-strategy improved SSA is proposed. The initial population is initialized using a quadratic composite chaotic mapping to enhance population diversity. An adaptive inertia weight mechanism based on the Logistic function is incorporated into the position update of the discoverers to balance the global and local search capabilities of the algorithm. The position update of the followers is improved by introducing a nonlinear perturbation factor in the Sine Cosine Algorithm, which enhances the optimization speed and precision and improves the ability to escape local optima. Experimental results demonstrate that the improved SSA achieves significant optimization in both precision and efficiency, validating its effectiveness in unmanned vehicle path planning.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-12-11
  • 最后修改日期:2025-01-17
  • 录用日期:2024-12-16
  • 在线发布日期:
  • 出版日期:
文章二维码