Answers are grounded in this paper and cite their sources.
Reveals improved path optimization for UAV maritime search, suggesting enhanced detection efficacy.
UAV-based maritime search and rescue requires feasible path planning over time-evolving target belief maps, where direct coordinate-based search may generate unreachable grid transitions and population-based optimization can stagnate around local probability peaks. This study proposes a Synergy Strategy Bezier Curve-based Optimization algorithm, termed SSBCO, for UAV-based moving target search. In SSBCO, candidate UAV paths are encoded as reachable motion vectors, ensuring grid feasibility while allowing the optimizer to search for paths with high cumulative detection probability. The probabilistic experience learning strategy uses individual and global historical best information to guide candidate generation toward promising regions. The Q-learning-based adaptive strategy selection mechanism adjusts the search action according to the current search phase, individual rank, and stagnation level. The lens reverse opposition learning strategy generates opposite candidates for inferior individuals to enhance population diversity and reduce the risk of local stagnation. The proposed algorithm was tested in nine drifting-target scenarios and compared with six representative metaheuristic algorithms over 30 independent runs. SSBCO achieved the highest mean cumulative detection probability in all scenarios, improving over the strongest competing mean by 2.7% to 19.3%. Wilcoxon rank-sum tests supported most pairwise gains, and ablation results confirmed the benefit of the complete search-enhancement framework. These results indicate that SSBCO improves UAV path optimization for maritime moving target search by combining feasible motion-vector encoding with adaptive, probability-guided, and diversity-enhancing search mechanisms to target high-probability regions while maintaining path feasibility.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: