PHL: An Adaptive Multi-Objective Hybrid Algorithm for UAV Swarm Path Planning
Soma Hamza Taha, Amin Salih Mohammed · Qalaai Zanist Scientific Journal · 2025
Unmanned Aerial Vehicles (UAVs) are widely used for surveillance, logistics, and disaster response activities. However, real-time navigation, energy-efficient routing, and safe maneuvering in unpredictable environments continue to pose a challenge for swarm-based UAV path planning. This work proposes the Adaptive Multi-Objective Hybrid Metaheuristic Algorithm (PHL), which combines PSO, HHO, and Lévy Flight for better UAV path planning. PHL optimally balances global exploration and local exploitation, enabling adaptive obstacle circumvention and load sharing among multiple agents. As a primary contribution, a dynamic cost function tackling travel time, energy usage, collision probability, and path smoothness is formulated. Comprehensive simulations validate that PHL outperforms other hybrid algorithms in terms of path efficiency, energy consumption, and collision avoidance when working with multiple UAVs. The findings demonstrate that PHL performs best in rapidly changing complex environments, showing promise for swarm-based UAV missions that require scalable solutions. Additional validation demonstrates that PHL outperforms other hybrid metaheuristic algorithms, suggesting minimum path cost energy consumption with advanced obstacle avoidance. Balancing the workload allows for optimal UAV function to be demonstrated. Its claim is reinforced by the strength and real-time precision shown in the navigation of UAV swarms through highly dynamic environments.