arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.12502cs.MA
收藏

构建大规模无人机防御的小组策略

Building Large-Scale Drone Defenses from Small-Team Strategies

Adelaide University(阿德莱德大学);Saab Australia Pty Ltd(萨博澳大利亚有限公司)

Grant Douglas, Stephen Franklin, Claudia Szabo, Mingyu Guo

AI总结:

本文提出通过整合小规模防御策略模块化组件,构建大规模无人机防御策略,实现高效扩展和有效合作行为发现。

摘要:

针对大规模对抗无人机群的防御需要能够有效扩展的协调方法,超越传统的多智能体优化。在本文中,我们提出通过将已在小规模防御团队中证明有效的策略作为模块化组件整合到更大规模的团队中,来实现扩展。动态规划(DP)分解将这些组件组装成大规模团队,以多项式时间实现高效构建可扩展的防御,而无需彻底评估。由于在孤立状态下强大的单元在组合时可能不再强大,我们跨多个小团队候选者进行采样。我们的框架在评估大规模团队结果和优化模块化组件池之间迭代,从而收敛到越来越有效的策略。实验表明,这种分组方法能够扩展到显著更大的场景,同时保持有效性,并揭示出指导优化发现合作行为的特征。

英文摘要:

Defending against large adversarial drone swarms requires coordination methods that scale effectively beyond conventional multi-agent optimisation. In this paper, we propose to scale strategies proven effective in small defender teams by integrating them as modular components of larger forces using our proposed framework. A dynamic programming (DP) decomposition assembles these components into large teams in polynomial time, enabling efficient construction of scalable defenses without exhaustive evaluation. Because a unit that is strong in isolation may not remain strong when combined, we sample across multiple small-team candidates. Our framework iterates between evaluating large-team outcomes and refining the pool of modular components, allowing convergence on increasingly effective strategies. Experiments demonstrate that this partitioning approach scales to substantially larger scenarios while preserving effectiveness and revealing cooperative behaviours that direct optimisation cannot reliably discover.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑