A Multi-Strategy Improved Artemisinin Algorithm For UAV 3-D Path Planning

As the application of drones becomes increasingly widespread, path planning for drones in various complex environments has gradually emerged as a challenge. It involves searching for a path that is both short and safe. Traditional path-planning methods perform well in simple environments, but they f...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International Symposium on Autonomous Systems (Online) s. 1 - 6
Hlavní autori: Hu, Yuhao, Shi, Mengji, Li, Tong, Sun, Xinyu, Li, Meng, Lin, Boxian, Qin, Kaiyu
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 23.05.2025
Predmet:
Accuracy
Autonomous aerial vehicles
Complex environments
Convergence
Drones
Optimization
Particle swarm optimization
Path planning
Radar
Simulation
Swarm intelligence optimization algorithms
Three-dimensional displays
Unmanned aerial vehicles (UAVs)
ISSN:2996-3850
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:As the application of drones becomes increasingly widespread, path planning for drones in various complex environments has gradually emerged as a challenge. It involves searching for a path that is both short and safe. Traditional path-planning methods perform well in simple environments, but they fall short in complex scenarios. A smooth obstacle-avoidance path planning scheme is proposed for UAVs based on a 3D Halton-Cauchy Diffusion Artemisinin Optimization (CDAO) algorithm. The approach enhances initial solution quality through 3D Halton sequence initialization, thereby enhancing convergence accuracy and speed by integrating a Cauchy elite population genetic strategy and a diffusion thinking strategy. The effectiveness of the CDAO algorithm is validated in three environments with varying complexity levels. Comparative experiments demonstrate that CDAO outperforms other swarm intelligence optimization algorithms such as PSO, HLOA, PO, and SCA in adaptability and optimization performance.
ISSN:2996-3850
DOI:10.1109/ICAISISAS64483.2025.11051849