Key points are not available for this paper at this time.
Unmanned Aerial Vehicle (UAV) search has been widely applied in critical mission scenarios such as battlefield reconnaissance and disaster response. Due to uncertainties caused by target maneuverability and environmental threats, the development of multi-UAV distributed cooperative search methods to overcome the limitations of single-UAV perception has become imperative. This study addresses the decision optimization problem for multi-UAV cooperative dynamic target search in complex adversarial environments and proposes a systematic decision optimization framework. Firstly, an environmental perception system model is constructed by integrating a multiple distribution hypothesis target motion prediction model with a multi-dimensional search map model, which incorporates target existence probability, environmental uncertainty, and pheromone-inspired coordination signals, and achieves situational updates through dynamic Bayesian inference. Secondly, a distributed model predictive control (DMPC) architecture with motion encoding mechanisms and a lightweight communication protocol is designed to effectively alleviate communication resource dependence. Furthermore, Genetic Programming (GP) algorithm is combined with DMPC to autonomously generate cooperative search strategies that satisfy multiple conditional constraints. Simulation results demonstrate that the proposed method significantly outperforms traditional search methods in terms of dynamic target search timeliness and adaptability to complex environments, particularly exhibiting stronger robustness in adversarial scenarios.
Li et al. (Wed,) studied this question.