面向无人机集群协同的感知-通信-控制联合优化方法-自主智能无人系统专刊

  • 许驰 ,
  • 李安顺 ,
  • 于海斌
展开
  • 中国科学院沈阳自动化研究所

收稿日期: 2026-06-01

  修回日期: 2026-10-12

  网络出版日期: 2026-10-19

基金资助

国家自然科学基金青年基金B类;辽宁省自然科学基金A类;辽宁省“兴辽英才”青年拔尖人才项目

Joint Optimization of Sensing, Communication, and Control for UAV Swarms Collaboration

  • XU Chi ,
  • LI An-Shun ,
  • YU Hai-Bin
Expand

Received date: 2026-06-01

  Revised date: 2026-10-12

  Online published: 2026-10-19

Supported by

工业无线控制网络技术与系统;工业互联网“通感算控智”协同理论与关键技术;工业智联网理论与技术

摘要

针对无人机集群空地协同过程中的高实时、低功耗调度问题,构建了感知-通信-控制(S2C)联合优化模型,提出了一种融合图卷积网络(GCN)与近端策略优化(PPO)的优化算法。首先,充分考虑无人机集群动态拓扑频繁切换、多约束强耦合等特点,以同时最小化时延和能耗为目标,构建了关于感知频次、通信功率、飞行速度和航向角的联合优化问题,并将其建模为马尔可夫决策过程。其次,利用GCN对时变拓扑与链路特征进行编码,设计基于阈值感知的动态拓扑更新机制,并通过量化拓扑变化幅度触发局部消息传递更新,实现对无人机链路频繁通断与节点动态入网的高效自适应。在此基础上,基于PPO进行集中式多目标联合优化,并设计惩罚函数引导算法优先满足跟踪精度要求,动态权衡时延与能耗。仿真结果表明,所提算法较基线方法降低时延45.5%、降低能耗3.2%,轨迹跟踪误差稳定在30 m以内。

本文引用格式

许驰 , 李安顺 , 于海斌 . 面向无人机集群协同的感知-通信-控制联合优化方法-自主智能无人系统专刊[J]. 航空学报, 0 : 1 -0 . DOI: 10.7527/S1000-6893.2026.33998

Abstract

To satisfy the high-realtime and low-power scheduling requirements for air-ground collaboration of UAV swarm, this paper establishes a joint optimization model for Sensing-Communication-Control (S2C) and proposes an optimization algorithm that combines a Graph Convolutional Network (GCN) with Proximal Policy Optimization (PPO). Fully considering the characteristics of frequent dynamic topology changes and strongly coupled constraints, and aiming at minimizing latency and energy consumption, we first formulate a joint optimization problem with respect to perception frequency, transmit power, flighting speed, and heading angle, and model the problem Markov decision process. Then, GCN is adopted to encode time-varying topology and link features, and a threshold-aware dynamic topology update mechanism is designed. By quantifying topology variations and triggering local message-passing update, we realize high-efficiency adaption to frequent link interruptions and dynamic node access of UAVs. On this basis, PPO is employed for centralized multi-objective collaborative optimization. A penalty-based reward function is designed to prioritize tracking accuracy and dynamically balance latency and energy consumption. Simulation results show that, compared with baseline algorithms, the proposed algorithm reduces latency by 45.5% and energy consumption by 3.2%, and maintains the trajectory tracking error steadily within 30 m.

参考文献

[1] 陈林, 缪志强, 王祥科, 等. 自主飞行器技术及其在低空经济中的应用综述[J]. 机器人, 2025, 47(3): 470-496.
CHEN L, MIAO Z Q, WANG X K, et al. A review of autonomous aircraft technology and its applications in low-altitude economy[J]. Robot, 2025, 47(3): 470-496 (in Chinese).
[2] 胡杨林, 张天魁, 李博, 等. 无人机使能的通信感知一体化组网与技术研究综述[J]. 电子与信息学报, 2025, 47(04): 859-875.
HU Y L, ZHANG T K, LI B, et al. Survey on UAV-enabled integrated sensing and communication networking and technologies[J]. Journal of Electronics & Information Technology, 2025, 47(4): 859-875 (in Chinese).
[3] 赵江, 皮明豪, 田栢苓, 等. 面向多目标跟踪的集群无人机自组织共识决策方法[J]. 航空学报, 2025, 46(16): 192-214.
ZHAO J, PI M H, TIAN B L, et al. Self-organized consensus decision-making method for swarm UAVs in multi-target tracking[J]. Chinese Journal of Aeronautics, 2025, 46(16): 192-214 (in Chinese).
[4] 方浩, 赵欣悦, 陈杰, 等. 无人飞行器集群自主控制: 预设性能驱动的安全编队控制[J]. 自动化学报, 2025, 51(5): 931-941.
FANG H, ZHAO X Y, CHEN J, et al. Autonomous control of unmanned aerial vehicle swarms: safety formation control driven by prescribed performance[J]. Acta Automatica Sinica, 2025, 51(5): 931-941 (in Chinese).
[5] 李敏, 包富瑜, 王恒. 无人机使能的无线传感网总能耗优化方法[J]. 自动化学报, 2024, 50(11): 2259-2270.
LI M, BAO F Y, WANG H. Total energy optimization method for UAV-enabled wireless sensor networks[J]. Acta Automatica Sinica, 2024, 50(11): 2259-2270 (in Chinese).
[6] 李伟, 郭艳, 李宁, 等. 智能反射面辅助无人机移动边缘计算任务数据最大化方法[J]. 航空学报, 2023, 44(19): 269-280.
LI W, GUO Y, LI N, et al. Task data maximization method for IRS-assisted UAV mobile edge computing[J]. Chinese Journal of Aeronautics, 2023, 44(19): 269-280 (in Chinese).
[7] 李伟, 郭艳, 何明, 等. 满意度驱动下无人机移动边缘计算服务缓存和资源分配方法[J]. 航空学报, 2024, 45(19): 255-268.
LI W, GUO Y, HE M, et al. Satisfaction-driven service caching and resource allocation for UAV mobile edge computing[J]. Chinese Journal of Aeronautics, 2024, 45(19): 255-268 (in Chinese).
[8] LI K X, LIU J J, GU X, et al. Dynamic decision-making of UAV swarm based on constrained multi-objective optimization under incomplete interference information[J]. Chinese Journal of Aeronautics, 2025, 103846.
[9] DENG J, ZHANG H H, HUA M Z, et al. Key technologies for logistics UAV routing based on a dual-layer MODDPG–NSGA2 architecture[J]. Chinese Journal of Engineering, 2025, 47(12): 2510-2526.
[10] MAVROVOUNIOTIS M, LI C H, YANG S X, et al. A survey of swarm intelligence for dynamic optimization: Algorithms and applications[J]. Swarm and Evolutionary Computation, 2017, 33: 1-17.
[11] MA H P, SHEN S G, YU M, et al. Multi-population techniques in nature inspired optimization algorithms: A comprehensive survey[J]. Swarm and Evolutionary Computation, 2019, 44: 365-387.
[12] ZHAO W, CUI S X, QIU W, et al. A survey on DRL-based UAV communications and networking: DRL fundamentals, applications and implementations[J]. IEEE Communications Surveys & Tutorials, 2026, 28: 3911-3941.
[13] AMODU O A, ALTHUMALI H, HANAPI Z M, et al. A comprehensive survey of deep reinforcement learning in UAV-assisted IoT data collection[J]. Vehicular Communications, 2025, 55: 100949.
[14] MALEKI H, BA?ARAN M, DURAK-ATA L. Energy-efficient offloading decision for beyond-5G multi-access edge computing-enabled UAV swarms[J]. IEEE Transactions on Vehicular Technology, 2026, 75(3): 5239-5243.
[15] LIU C, ZHONG Y, WU R, et al. Deep reinforcement learning based 3D-trajectory design and task offloading in UAV-enabled MEC system[J]. IEEE Transactions on Vehicular Technology, 2025, 74(2): 3185-3195.
[16] PANAHI F H, PANAHI F H. Intelligent UAV-based mobile offloading: a multi-objective optimization approach[J]. IEEE Transactions on Green Communications and Networking, 2025, 9(3): 900-909.
[17] RAHMAN A K M A, MRIDUL M C, ROY P, et al. A multi-head attention mechanism assisted MADDPG algorithm for real-time data collection in internet of drones[J]. Vehicular Communications, 2025, 54: 100944.
[18] NAOURI A, NOURI N A, HADABI A, et al. Dynamic and adaptive task offloading for UAV-enabled MEC systems[J]. Future Generation Computer Systems, 2026, 183: 108505.
[19] TAREKEGN G B, et al. Trajectory control and fair communications for multi-UAV networks: a federated multi-agent deep reinforcement learning approach[J]. IEEE Transactions on Wireless Communications, 2025, 24(9): 7598-7611.
[20] GUL Z, OZGUN A S, HINDISTAN C, et al. Reinforcement learning based-driven parameter adaptation for UAV systems[C]//AIAA SCITECH 2026 Forum. Orlando, FL: AIAA, 2026: AIAA 2026-2581.
[21] ZHUANG J, HAN G, XIA Z, et al. Robust policy learning for multi-UAV collision avoidance with causal feature selection[C]//Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS’25). Richland, SC: International Foundation for Autonomous Agents and Multiagent Systems, 2025: 2392-2401.
[22] YE Z, WANG K, CHEN Y, et al. Multi-UAV navigation for partially observable communication coverage by graph reinforcement learning[J]. IEEE Transactions on Mobile Computing, 2023, 22(7): 4056-4069.
[23] LI Y, LI J, WANG J, et al. Multiscale-graph-enhanced reinforcement learning for conflict resolution in dense UAV networks[J]. IEEE Internet of Things Journal, 2025, 12(21): 44290-44303.
[24] TENG M, LI X, ZHANG X, et al. Graph-based spatiotemporal RL framework for sequential task offloading in multi-UAV systems[J]. IEEE Transactions on Mobile Computing, 2026, 25(5): 6306-6319.
[25] XIE W, YANG H, XIONG Z, et al. Resource allocation for UAV-assisted anti-jamming semantic D2D networks: a graph reinforcement learning approach[J]. Computer Networks, 2025, 269: 111463.
[26] WU D, CAO Z, LIN X, et al. A learning-based cooperative navigation approach for multi-UAV systems under communication coverage[J]. IEEE Transactions on Network Science and Engineering, 2025, 12(2): 763-773.
[27] WANG K, LAM C T, NG B K, et al. On the impact of phase errors in phase-dependent amplitudes of near-field RISs[J]. IEEE Transactions on Vehicular Technology, 2025, 3647594.
[28] 肖陶, 唐睿, 张睿智, 等. NOMA使能的水下可见光通信系统中资源分配机制[J]. 信息与控制, 2025, 54(5): 673-685.
XIAO T, TANG R, ZHANG R Z, et al. Resource allocation mechanism in NOMA-enabled underwater visible light communication systems[J]. Information and Control, 2025, 54(5): 673-685 (in Chinese).
[29] XU C, TANG Z X, YU H B, et al. Digital twin-driven collaborative scheduling for heterogeneous task and edge-end resource via multi-agent deep reinforcement learning[J]. IEEE Journal on Selected Areas in Communications, 2023, 41(10): 3056-3069.
[30] XU C, ZHANG P F, YU H B, et al. Dynamic blockchain-empowered trustworthy end-edge collaborative computing via rotating multi-agent DRL[J]. IEEE Transactions on Wireless Communications, 2025, 24(6): 4864-4878.
[31] 陈建国, 姚蔚然, 孙光辉, 等. 融合进化算法和深度强化学习的飞行器制导控制一体化[J]. 自动化学报, 2026, 52(1): 52-64.
CHEN J G, YAO W R, SUN G H, et al. Integration of guidance and control for aircraft based on evolutionary algorithm and deep reinforcement learning[J]. Acta Automatica Sinica, 2026, 52(1): 52-64 (in Chinese).
[32] XU C, ZHANG J Y, YU H B. Control-communication co-optimization for wireless cloud robotic system via multi-agent transfer reinforcement learning[J]. IEEE/CAA Journal of Automatica Sinica, 2026, 13(2): 311-326.
Options
文章导航

/

〈 〉