| 摘要: |
| 由于单架无人机的性能局限性，无人机集群以其高复杂性、高连续性、高覆盖性和强自主性得到了广泛关注。针对无人机集群中的感知通信一体化（Integrated Sensing And Communication，ISAC）系统，考虑感知与通信的协同应用，构建了基于无人机集群的ISAC一体化系统模型，形成了针对波束、频谱和功率等的最优化分配问题，并提出了基于强化学习的高效求解方法。相比于传统曼克莱斯（Kuhn Munkres，KM）迭代、深度神经网络等方法，随着无人机集群规模以及环境复杂度的提高，所提方法可以在较高复杂度条件下获得更优性能，最终仿真验证了算法的有效性。 |
| 关键词: 强化学习 资源调度 感知通信一体化 无人机集群 智能算法 |
| DOI： |
| 分类号:TN95 |
| 基金项目:国家自然科学基金项目（面上项目，重点项目，重大项目） |
|
| ISAC Intelligent resource allocation method for group UAVs |
|
|
|
|
| Abstract: |
| Due to the performance limitation of single UAV, groups UAVs has been widely concerned for its high complexity, high continuity, high coverage and strong autonomy. Aiming at the integrated sensing and communication (ISAC) system in group UAVs, the ISAC integrated system model based on group UAVs is constructed by considering the collaborative application of sensing and communication. An optimal allocation problem for beam, spectrum and power is formed, and an efficient solution method based on reinforcement learning is proposed. Compared with the traditional Kuhn Munkres (KM) iteration and deep neural network methods, the proposed method can achieve better performance with the increase of the number of UAV and environmental complexity, and simulation results verify the effectiveness of the algorithm. |
| Key words: reinforcement learning resource allocation ISAC group UAVs intelligent algorithm. |