An unmanned aerial vehicle path planning algorithm based on particle swarm optimization and backstepping

By combining particle swarm optimization and back learning, the UAV path planning algorithm is improved, solving the problem that traditional algorithms are prone to getting trapped in local optima in complex environments, and achieving efficient and stable path planning.

CN122408758APending Publication Date: 2026-07-17NANTONG UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
NANTONG UNIV
Filing Date
2026-03-03
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Traditional UAV path planning algorithms are prone to getting trapped in local optima in complex and dynamic environments, resulting in low computational efficiency and difficulty in meeting the requirements of real-time performance and robustness.

Method used

Combining particle swarm optimization and back learning, an adaptive mechanism is introduced to adjust the success rate parameter. The particle swarm is initialized using Logistic chaotic mapping, turbulent perturbation is performed using Lévy flight, and back learning is introduced during the iteration process to accelerate convergence.

Benefits of technology

It improves the global exploration capability and efficiency of UAV path planning, avoids premature convergence, and can plan the optimal path in a short time, meeting the requirements of real-time performance and stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122408758A_ABST
    Figure CN122408758A_ABST
Patent Text Reader

Abstract

The application provides a kind of unmanned aerial vehicle path planning algorithm based on particle swarm optimization and reverse learning, belongs to artificial intelligence optimization algorithm and intelligent control technical field.The technical scheme is: including the following steps: step 1, the success rate parameter is introduced into the traditional linear decreasing adaptive mechanism;Step 2, a particle is randomly generated, and the next particle is initialized based on the particle parameters using Logistic chaotic mapping, and so on, the particle swarm is initialized;Step 3, in the process of algorithm optimization, the particles that converge rapidly in a short time are disturbed using Levy flight;Step 4, the algorithm is optimized using reverse learning.The application reduces the operation time of the algorithm and improves the stability of the unmanned aerial vehicle in space operation.
Need to check novelty before this filing date? Find Prior Art