Robust multi-UAV route optimization via multi-strategy modified ABC
APPLIED SOFT COMPUTING, cilt.203, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 203
- Basım Tarihi: 2026
- Doi Numarası: 10.1016/j.asoc.2026.116159
- Dergi Adı: APPLIED SOFT COMPUTING
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Applied Science & Technology Source, Compendex, INSPEC
- Kocaeli Üniversitesi Adresli: Evet
Özet
Autonomous path planning is a critical component of unmanned aerial vehicle (UAV) navigation, particularly for last-mile delivery applications in smart cities. This paper presents a robust multi-UAV route optimization framework based on a Multi-strategy Modified Artificial Bee Colony (M2ABC) algorithm designed for com plex, low-altitude 3D environments. The proposed M2ABC algorithm integrates an adaptive position update mechanism, noise-induced diversity enhancement, and a globally guided scout phase to overcome premature convergence and improve solution quality in dense obstacle fields. The proposed method ensures collision-free trajectories within constrained 3D operational spaces and achieves superior convergence behavior and path qual ity in cluttered environments. Simulation results demonstrate that the proposed M2ABC algorithm consistently outperforms conventional ABC, IPSO, ABCPSO, and GA in terms of convergence speed, path quality, energy effi ciency, and planning stability. Compared with the conventional ABC algorithm, the proposed approach reduces the average normalized energy consumption by 4.83%, achieves up to 30% energy savings compared with GA, and attains 100% routing success in small-swarm scenarios while maintaining feasible collision-free routes as the swarm size and obstacle density increase. These results demonstrate the effectiveness, robustness, and scalability of the proposed framework for safe multi-UAV navigation in complex 3D environments.