A reinforced quantum Aquila Optimizer

A reinforced quantum Aquila Optimizer for multi-threat 3D UAVs path planning in complex environments

This study proposes RLQFAO, a reinforced variant of the Aquila Optimizer, which integrates four synergistic strategies. RLQFAO first employs a good point set-based initialization method to enhance population diversity at the outset. During the evolutionary process, an adaptive strategy selection mechanism dynamically balances global exploration and local exploitation. To further strengthen global search capabilities, a moth–flame search operator augmented with quantum rotation gates is incorporated. In addition, a Q-learning-based neighborhood perturbation model adaptively selects effective disturbance strategies based on real-time feedback from the search process. Together, these components work synergistically to improve convergence stability and overall optimization performance, particularly in high-dimensional and constraint-intensive scenarios.

Main reference: Yang, H., Yu, M., Zhang, J., Xiong, Y., Wang, D., & Xu, J. (2026). A Reinforced Quantum Aquila Optimizer for Multi-Threat 3D UAVs Path Planning in Complex Environments. Applied Mathematical Modelling, 116736.https://doi.org/10.1016/j.apm.2025.116736