PDF (4.3 MB)
Collect
Submit Manuscript
Show Outline
Outline
Abstract
Keywords
Show full outline
Hide outline
Open Access | Just Accepted

DQN-ALNS for UAV Reconnaissance Routing Problem with Target Priority Consideration

Lingjie ZhouZhihao Luo()Jianmai Shi

Laboratory for Big Data and Decision,National University of Defense Technology, Changsha 410073,PR China

 

Show Author Information

Abstract

 In recent years, UAVs have been extensively employed for reconnaissance missions. Our focus is  prioritizing reconnaissance of high-priority targets while minimizing the flight duration when UAV power is  constrained. We introduce a framework called DQN-ALNS, which integrates Deep Q Network (DQN) into the  Adaptive Large Neighborhood Search (ALNS) metaheuristic algorithm to optimize the process through the  current solution’s search state. Specifically, the agent is utilized to select the destroy-repair operators to update  a new solution, thereby iteratively optimizing the UAV reconnaissance routes. Experimental results reveal that  DQN-ALNS achieves superior solutions and faster convergence than other comparison algorithms. The  algorithm leverages the exploratory potential of the current solution and demonstrates robust stability. The final  sensitivity analysis showcases that reconnaissance missions with high priority are better accomplished when  the UAV power is moderate and the target priority is concentrated at smaller values.  

Tsinghua Science and Technology
Cite this article:
Zhou L, Luo Z, Shi J. DQN-ALNS for UAV Reconnaissance Routing Problem with Target Priority Consideration. Tsinghua Science and Technology, 2025, https://doi.org/10.26599/TST.2024.9010219
Metrics & Citations  
Article History
Copyright
Rights and Permissions
Return