Article Details

Title · Authors · Abstract · Keywords · DOI · References

Path Planning Based on HHPSO-GWO

WANG Rongxiu1, YANG Min2

(1.Wuxi Taihu University, Wuxi 214064, China; 2.The 58th Institute of CETC, Wuxi 214000, China)

Section：Artificial Intelligence · Vol. 2026, Issue 5 · Pages：51-55,59 · 2096-4706（2026）05-0051-06 · CLC number：TP301.6 · Document code：A · DOI：10.19850/j.cnki.2096-4706.2026.05.010

Abstract

To address the problems of low computational efficiency, premature convergence or slow late convergence in path planning, a grid map is constructed and a Hierarchical Hybrid Particle Swarm Optimization-Grey Wolf Optimizer (HHPSO-GWO) is proposed. The algorithm divides the population into elite and ordinary particles and implements differentiated learning to dynamically balance search performance. Through simulation comparisons, the optimal path lengths planned by HHPSO-GWO are 16.650 0 and 44.284 3 respectively, which are improved by 30.33% and 16.24% compared with PSO, and by 6.98% and 11.93% compared with GWO. The numbers of convergence iterations are only 12 and 9, which are much fewer than 47 and 52 of the PSO algorithm, and better than 55 and 12 of the GWO algorithm. The results show that the algorithm can improve the convergence speed and effectively shorten the path length, providing a new method for path planning.

Keywords

path planning; HHPSO-GWO; differentiated learning; optimal path

References

  1. [1] Mo Dingjie, Zhao Jie, Linggang, etc Hybrid Particle Swarm Optimization and Improved Grey Wolf Algorithm for Mobile Robot Path Planning [J]. Software Guide, 2025, 24 (7): 54-60
  2. [2] LIANG J Q，ZHOU Z C，LIU X Y. Robot Path Planning Based on Particle Swarm Optimization Improved Grey Wolf Algorithm [J].Software Guide，2022，21（5）：96-100.
  3. [3] Zhang Yuxuan, Zhang Nan A logistics robot motion path planning method based on improved grey wolf algorithm [J]. Computer Measurement and Control, 2024, 32 (9): 276-282
  4. [4] Sun Weixuan, Xiao Yun, Zhang Jinbai, etc A New Gravity Matching Navigation Path Planning Algorithm - Particle Swarm Optimization Grey Wolf Algorithm [J]. Geodesy and Geodynamics, 2025, 45 (9): 922-928936
  5. [5] LI Z，WANG F，WANG R J. An Improved Particle Swarm Optimization Algorithm [J].Computer Measurement & Control，2021，29（10）：217-222.
  6. [6] LIU Z Q，HE L，YUAN L，et al. Path Planning of Mobile Robot Based on TGWO Algorithm [J].Journal of Xi'an Jiaotong University，2022，56（10）：49-60.
  7. [7] HUANG X，LU Y，SHEN L，et al. Multi-Objective Constrained Optimization Problem Solving Based on Particle Swarm Optimization and Gray Wolf Hybrid Algorithm [J].Journal of Chinese Computer Systems，2023，44（2）：288-299.
  8. [8] Song Yu, Gao Gang, Liang Chao, etc UAV path planning based on multi strategy improved grey wolf algorithm [J]. Electronic Measurement Technology, 2025, 48 (1): 84-91
  9. [9] Liu Zhiqiang, He Li, Yuan Liang, etc Path Planning of Mobile Robots Using Improved Grey Wolf Algorithm [J]. Journal of Xi'an Jiaotong University, 2022, 56 (10): 49-60
  10. [10] Wang Tao, Li Zhibin Robot path planning based on grey wolf algorithm under road network constraints [J]. Computer Simulation, 2024, 41 (5): 441-445

About the authors

Wang Rongxiu (1989-), female, Han nationality, from Xinxiang, Henan Province, lecturer, master's student, research direction: computer science.