In this study, an improved Grey Wolf Optimization (GWO) algorithm was designed to optimize the deployment of multiple interference unmanned aerial vehicles (UAVs). First, a scenario model was constructed based on an electromagnetic wave propagation model. Second, using multi-UAV multi-target interference as the task objective, an interference effectiveness evaluation function was built by introducing a low-coverage-efficiency reduction factor based on the global interference-to- noise ratio. An improved GWO algorithm with a reverse learning strategy was employed to solve the task optimization problem, and simulation experiments on interference UAV deployment tasks under different task pressures were conducted. The results show that, compared with the traditional GWO, the proposed algorithm exhibits a superior adaptability under different task pressures represented by the ratio of drones to targets: in high task pressure scenarios, the convergence speed of deployment schemes generated by the improved GWO algorithm has increased by 7.71%; under moderate and low task pressures, the stability of interference efficiency in the generated schemes has improved by nearly 30%; and the interference efficiency across different task pressures remains largely consistent. This demonstrates that the capability of improved GWO algorithm to accommodate interference UAV deployments across diverse task pressure scenarios, excelling particularly in high-pressure environments.
With the advent of unmanned aerial vehicle (UAV) swarm technology, countering UAV swarms has emerged as a pressing challenge requiring immediate attention. Employing UAV swarms with high efficiency-to-cost ratios to counter, disrupt, and intercept enemy UAV swarms has been proven to be a relatively effective countermeasure, prompting extensive research in this field. To comprehensively analyze the progress of intelligent decision-making technology in UAV swarm confrontation, this study initially examined the primary technical challenges faced by intelligent decision-making technology, outlining the establishment and resolution of submodels as the central theme. The study presents three primary models, namely, mathematical programming, game theory, and Markov decision processes, and provides an overview of their current applications and challenges based on relevant theories. Subsequently, the study elaborates on the solution methods for each mathematical model and emphasizes the reinforcement learning-based solving algorithm, highlighting its advantages in the domain of adversarial intelligent decision making. Finally, we summarize the current state and limitations of UAV swarm intelligent decision-making research and offer a perspective on future trends in this field, thereby offering novel avenues for further research.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.