A chaotic adaptive dual population co-evolution (CADES) optimization algorithm for unmanned aerial vehicle path planning

CN122431147APending Publication Date: 2026-07-21GUILIN UNIV OF ELECTRONIC TECH +1

View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office: CN · China
Patent Type: Applications(China)
Current Assignee / Owner: GUILIN UNIV OF ELECTRONIC TECH
Filing Date: 2026-05-25
Publication Date: 2026-07-21

AI Technical Summary

Technical Problem

Existing UAV path planning algorithms suffer from insufficient global path exploration, inadequate local path optimization accuracy, susceptibility to local optima, poor path smoothness, and low obstacle avoidance reliability in complex obstacle environments. Existing co-evolutionary algorithms have low information transmission efficiency and struggle to achieve dynamic balance between global and local conditions.

Method used

The CADES optimization algorithm, which employs a chaotic adaptive dual-population co-evolution, is used to achieve global path exploration through the CEO module, local path optimization through the AE module, and dynamic collaboration through the collaborative interaction module. Combined with dynamic elite migration, multi-strategy fusion, and stagnation restart mechanisms, a balance between global and local outcomes is achieved.

Benefits of technology

It improves the accuracy, smoothness, and obstacle avoidance success rate of UAV path planning, adapts to complex obstacle environments, meets the multi-objective optimization needs of UAV path planning, and generates high-quality and reliable paths.

✦ Generated by Eureka AI based on patent content.

Smart Images

Figure CN122431147A_ABST

Patent Text Reader

Abstract

The application relates to the technical field of unmanned aerial vehicle path planning, and discloses a chaotic adaptive dual-population collaborative evolution CADES optimization algorithm for unmanned aerial vehicle path planning, which aims to solve the technical defects of the existing unmanned aerial vehicle path planning algorithm, such as insufficient global path exploration, insufficient local path optimization precision, easy falling into local optimization, poor path smoothness and the like. The algorithm comprises three core units, namely a CEO module, an AE module and a collaborative interaction module. The CEO module realizes global wide exploration of the unmanned aerial vehicle motion space based on chaotic mapping, generates diversified path candidate solutions and ensures coverage of all potential feasible path areas. The AE module realizes fine local path optimization through adaptive Gaussian disturbance and mask crossover guided by the global optimal path, and improves the path smoothness and obstacle avoidance safety. The collaborative interaction module integrates dynamic elite migration and multi-strategy fusion, realizes efficient collaboration and information intercommunication of the two modules, and balances the global path exploration and local path optimization capabilities.

Need to check novelty before this filing date? Find Prior Art