| 275 | 0 | 227 |
| Downloads | Citas | Reads |
The widespread application of drones in complex task scenarios, such as urban inspection, emergency rescue, logistics distribution, and agricultural pest control, imposes higher demands on their autonomous flight and collaborative control technologies, while also introducing various challenges related to perception, decision-making, and onboard computing power. This paper systematically reviews and compares key technological advancements in both fields. In the field of autonomous flight, it covers the traditional perception-planning-control framework, end-to-end methods based on reinforcement learning and imitation learning, as well as differentiable simulation methods that integrate physical models with gradient optimization. In the field of collaborative control, typical multi-drone collaborative control methods, including model-based multi-agent distributed collaborative control theory and data-driven multi-agent reinforcement learning algorithms, are examined. Their fundamental principles, applicable scenarios, and performance characteristics are analyzed. Finally, an innovative multi-drone collaborative control framework is proposed, which combines end-to-end decision-making with physics priors and differentiable simulation techniques. Key challenges related to simulation-to-reality transfer, explainability of collaborative decision-making, and scalability for large-scale swarms are identified, and future development directions are outlined.
[1]闫超，涂良辉，王聿豪，等.无人机在我国民用领域应用综述[J].飞行力学，2022,40(3):1-6.
[2]芦艳春，周开园，张建杰.无人机的发展现状及其在航空应急救援领域的应用综述[J].医疗卫生装备，2023,44(10):108-113.
[3]牛亚晓，张立元，韩文霆，等.基于无人机遥感与植被指数的冬小麦覆盖度提取方法[J].农业机械学报，2018,49(4):212-221.
[4]刘豫，刘佳鑫，贾云飞，等.基于电力巡检的四旋翼无人机控制系统研究[J].测试技术学报，2019,33(4):313-317.
[5]许强，郭晨，董秀军.地质灾害航空遥感技术应用现状及展望[J].测绘学报，2022,51(10):2020-2033.
[6]王耀南，安果维，王传成，等.智能无人系统技术应用与发展趋势[J].中国舰船研究，2022,17(5):9-26.
[7]Idrissi M,Salami M,Annaz F. A Review of quadrotor unmanned aerial vehicles:Applications, architectural design and control algorithms[J]. Journal of Intelligent&Robotic Systems,2022,104:22-55.
[8]Telli K,Kraa O,Himeur Y,et al. A comprehensive review of recent research trends on unmanned aerial vehicles(UAVs)[J]. Systems,2023,11(8):400-448.
[9]张宏宏，甘旭升，毛亿，等.无人机避障算法综述[J].航空兵器，2021,28(5):53-63.
[10]Loianno G,Brunner C,McGrath G,et al. Estimation,control,and planning for aggressive flight with a small quadrotor with a single camera and IMU[J]. IEEE Robotics and Automation Letters,2017,2(2):404-411.
[11]Sonugur G. A review of quadrotor UAV:Control and SLAM methodologies ranging from conventional to innovative approaches[J]. Robotics and Autonomous Systems,2023,161:104342.
[12]Loquercio A, Kaufmann E, Ranftl R, et al. Deep drone racing:From simulation to reality with domain randomization[J]. IEEE Transactions on Robotics,2020,36(1):1-14.
[13]Peng W,Prabhash R,Stavros G,et al. Vision-based navigation of unmanned aerial vehicles in orchards:An imitation learning approach[J]. Computers and Electronics in Agriculture,2025,238:110802.
[14]Belbute-peres F, Smith K, Allen K, et al. End-toend differentiable physics for learning and control[C].The Thirty-Second Annual Conference on Neural Information Processing Systems(NIPS),Montreal,Canada,2018-12-03.
[15]李鹏举，毛鹏军，耿乾，等.无人机集群技术研究现状与趋势[J].航空兵器，2020,27(4):25-32.
[16]Oh K,Park M,Ahn H,A survey of multi-agent formation Control[J]. Automatica,2015,53:424-440.
[17]贾永楠，田似营，李擎.无人机集群研究进展综述[J].航空学报，2020,41(S1):4-14.
[18]Ren W,Beard R. Consensus seeking in multiagent systems under dynamically changing interaction topologies[J]. IEEE Transactions on Automatic Control, 2005,50(5):655-661.
[19]黄红伟，黄天民，吴胜，等.基于事件触发的二阶多智能体领导跟随一致性[J].控制与决策，2016,31(5):835-841.
[20]Xue Z,Zeng J. Formation control numerical simulations of geometric patterns for unmanned autonomous vehicles with swarm dynamical methodologies[C]. 2009 International Conference on Measuring Technology and Mechatronics Automation,Zhangjiajie,China,2009-04-11.
[21]Xue Y,Chen W. Multi-agent deep reinforcement learning for UAVs navigation in unknown complex environment[J]. IEEE Transactions on Intelligent Vehicles,2024,9(1):2290-2303.
[22]符小卫，王辉，徐哲.基于DE-MADDPG的多无人机协同追捕策略[J].航空学报，2022,43(5):530-543.
[23]夏家伟，刘志坤，朱旭芳，等.基于多智能体强化学习的无人艇集群集结方法[J].北京航空航天大学学报，2023,49(12):3365-3376.
[24]Campos C, Elvira R, Rodríguez J, et al. ORBSLAM3:An accurate open-source library for visual,visual-inertial, and multimap SLAM[J]. IEEE Transactions on Robotics,2021,37(6):1874-1890.
[25]Engel J,Koltun V,Cremers D. Direct sparse odometry[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(3):611-625.
[26]Qin T,Li P,Shen S. VINS-Mono:A robust and versatile monocular visual-inertial state estimator[J]. IEEE Transactions on Robotics(T-RO), 2018, 34(4):1004-1020.
[27]Freedom__00.【4K双语字幕】特斯拉Tesla We,Robot发布会|Robotaxi Robovan Optimus[EB/OL]. 2024-10-12[2025-09-07]. https：//www. bilibili. com/video/BV1df2tYFExg/？spm_id_from=333.337.search-card. all.click&vd_source=61fbcdf0b559635774282251aacb69c6.
[28]Hornung A,Wurm K,Bennewitz M,et al. An efficient probabilistic 3D mapping framework based on octrees[J]. Autonomous Robots,2013,34(3):189-206.
[29]小白学视觉.从深度图到点云的构建方式[EB/OL].2020-11-13[2025-06-17]. https：//zhuanlan. zhihu.com/p/291644762.
[30]Newcombe R, Izadi S, Hilliges O, et al. KinectFusion:Real-time dense surface mapping and tracking[C]. IEEE International Symposium on Mixed and Augmented Reality(ISMAR),Basel,Switzerland,2011-10-26.
[31]Zhou B,Gao F,Wang L,et al. Robust and efficient quadrotor trajectory generation for fast autonomous flight[J]. IEEE Robotics and Automation Letters, 2019, 4(4):3529-3536.
[32]Zhou X,Wang Z,Ye H,et al. EGO-planner:An ESDF-free gradient-based local planner for quadrotors[J].IEEE Robotics and Automation Letters,2021,6(2):478-485.
[33]Salih A,Moghavvemi M, Mohamed H,et al. Modelling and PID controller design for a quadrotor unmanned air vehicle[C]. 2010 IEEE International Conference on Automation,Quality and Testing,Robotics(AQTR),Cluj-Napoca,Romania,2010-05-28.
[34]王晓海，孟秀云，李传旭.基于MPC的无人机航迹跟踪控制器设计[J].系统工程与电子技术，2021,43(1):191-198.
[35]Kaufmann E,Bauersfeld L,Loquercio A,et al. Champion-level drone racing using deep reinforcement learning[J]. Nature,2023,620:982-987.
[36]Wang M,Wang Q,Wang Z,et al. Unlocking aerobatic potential of quadcopters:Autonomous freestyle flight generation and execution[J]. Science Robotics,2025,10(101):eadp9905.
[37]Xu Z,Han X,Shen H,et al. NavRL:Learning safe flight in dynamic environments[J]. IEEE Robotics and Automation Letters,2025,10(4):3668-3675.
[38]Li X,Fang J,Du K,et al. UAV obstacle avoidance by human-in-the-loop reinforcement in arbitrary 3D environment[C]. 2023 42nd Chinese Control Conference(CCC),Tianjin,China,2023-07-24.
[39]Joshi B,Kapur D,Kandath H. Sim-to-real deep reinforcement learning based obstacle avoidance for UAVs under measurement uncertainty[C]. 2024 10th International Conference on Automation,Robotics and Applications(ICARA),Athens,Greece,2024-02-22.
[40]Zare M,Kebria P,Khosravi A,et al. A survey of imitation learning:Algorithms,recent developments,and challenges[J]. IEEE Transactions on Cybernetics,2024,54(12):7173-7186.
[41]Arora S, Doshi P. A Survey of inverse reinforcement learning:Challenges,methods and progress[J]. Artificial Intelligence,2021,297:103500.
[42]Loquercio A,Kaufmann E,Ranftl R,et al. Learning high-speed flight in the wild[J]. Science Robotics,2021,6(59):eabg5810.
[43]Kawaharazuka K,Oh J,Yamada J,et al. Vision-language-action models for robotics:A review towards real-world applications[J]. IEEE Access, 2025, 13:162467-162504.
[44]麻玥瑄，齐家悦，朱威禹.大模型赋能无人机博弈对抗研究[J].空天技术，2025(3):79-96.
[45]Serpiva V,Lykov A,Myshlyaev A,et al. RaceVLA:VLA-based racing drone navigation with human-like behaviour[J]. arXiv preprint. 2025,arXiv:2503. 02572.
[46]Wang X,Yang D,Liao Y,et al. UAV-flow colosseo:A real-world benchmark for flying-on-a-word UAV imitation learning[J]. arXiv preprint. 2025,arXiv:2505.15725.
[47]Song Z,He Z,Li X,et al. Synthetic datasets for autonomous driving:A survey[J]. IEEE Transactions on Intelligent Vehicles,2024,9(1):1847-1864.
[48]Shah S,Dey D,Lovett C,et al. AirSim:High-fidelity visual and physical simulation for autonomous vehicles[J]. arXiv preprint,arXiv:1705. 05065.
[49]Dosovitskiy A, Ros G, Codevilla F, et al. CARLA:An open urban driving simulator[J]. arXiv preprint,arXiv:1711. 03938.
[50]Savva M,Kadian A,Maksymets O,et al. Habitat:A platform for embodied AI research[C]. 2019 IEEE/CVF International Conference on Computer Vision(ICCV),Seoul,Korea(South),2019-10-27.
[51]Mu Y,Chen T,Chen Z,et al. RoboTwin:Dual-arm robot benchmark with generative digital twins[C]. 2025IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), Honolulu, HI, USA, 2025-10-19.
[52]Jiang Z, Xie Y, Lin K, et al. DexMimicGen:Automated data generation for bimanual dexterous manipulation[J]. arXiv preprint,2024,arXiv:2410. 24185.
[53]Wang S,Zhang J,Li M,et al. TrackVLA:Embodied visual tracking in the wild[J]. arXiv preprint, 2025,arXiv:2505. 23189.
[54]Zhang J,Huang J,Jin S,et al. Vision-language models for vision tasks:A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(8):5625-5644.
[55]Lu J,Zhang X,Shen H,et al. You only plan once:A learning-based one-stage planner with guidance learning[J]. IEEE Robotics and Automation Letters, 2024, 9(7):6083-6090.
[56]Bern J M,Schnider Y,Banzet P,et al. Soft robot control with a learned differentiable model[C]. 2020 3rd IEEE International Conference on Soft Robotics(RoboSoft),New Haven,CT,USA,2020-05-15.
[57]Schwarke C,Klemm V,Bagajo J,et al. Learning deployable locomotion control via differentiable simulation[J]. arXiv preprint,2025,arXiv:2404. 02887.
[58]Heeg J, Song Y, Scaramuzza D. Learning quadrotor control from visual features using differentiable simulation[C]. IEEE International Conference on Robotics and Automation(ICRA),Atlanta,GA,USA,2025-05-19.
[59]Zhang Y,Hu Y,Song Y,et al. Learning vision-based agile flight via differentiable physics[J]. Nature Machine Intelligence,2025,7:954-966.
[60]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),Detroit,Michigan,USA,2025-05-19.
[61]Brunke L,Greeff M,Hall A,et al. Safe learning in robotics:From learning-based control to safe reinforcement learning[J]. Annual Review of Control,Robotics,and Autonomous Systems,2022,5:411-444.
[62]Pinto L,Davidson J,Sukthankar R,et al. Robust adversarial reinforcement learning[C]. Proceedings of the34th International Conference on Machine Learning(ICML),Sydney,NSW,Australia,2017-08-06.
[63]苟进展，梁天骄，陶呈纲，等.基于一致性理论的无人机编队控制与集结方法[J].北京航空航天大学学报，2024,50(5):1646-1654.
[64]Dong X, Hua Y, Zhou Y, et al. Theory and experiment on formation-containment control of multiple multirotor unmanned serial vehicle systems[J]. IEEE Transactions on Automation Science and Engineering, 2019,16(1):229-240.
[65]Li J,Liu J,Huang S,et al. Leader-follower formation of light-weight UAVs with novel active disturbance rejection control[J]. Applied Mathematical Modelling,2023,117:577-591.
[66]王振威，刘凯，郭健，等.一种基于领导-跟随策略的多无人机-多无人艇编队协同机制[J].航空学报，2023,44(S2):453-468.
[67]Pan Z,Zhang C,Xia Y,et al. An improved artificial potential field method for path planning and formation control of the multi-UAV systems[J]. IEEE Transactions on Circuits and Systems II:Express Briefs,2022,69(3):1129-1133.
[68]Zhang T,Donga D,Du Z. Swarm control based on artificial potential field method with predicted state and input threshold[J]. Engineering Applications of Artificial Intelligence,2023,125:106567.
[69]Vargas S,Becerra H,Hayet J. MPC-based distributed formation control of multiple quadcopters with obstacle avoidance and connectivity maintenance[J]. Control Engineering Practice,2022,121:105054.
[70]Lowe R, Wu Y, Tamar A, et al. Multi-agent actorcritic for mixed cooperative-competitive environments[C]. 31st Annual Conference on Neural Information Processing Systems(NIPS), Long Beach, CA, USA,2017-12-04.
[71]Lillicrap T,Hunt J,Pritzel A,et al. Continuous control with deep reinforcement learning[J]. arXiv preprint,2015,arXiv:1509.02971.
[72]Yu C,Velu A,Vinitsky E,et al. The surprising effectiveness of PPO in cooperative multi-agent games[C].36th Conference on Neural Information Processing Systems(NeurIPS), New Orleans, LA, USA, 2022-11-28.
[73]Schulman J,Wolski F,Dhariwal P. Proximal policy optimization algorithms[J]. arXiv preprint,2017,arXiv:1707. 06347.
[74]Huang Z,Yang Z,Krupani R,et al. Collision avoidance and navigation for a quadrotor swarm using end-toend deep reinforcement learning[C]. IEEE International Conference on Robotics and Automation(ICRA),Yokohama,Japan,2024-05-13.
[75]Xue Y,Chen W. Multi-agent deep reinforcement learning for UAVs navigation in unknown complex environment[J]. IEEE Transactions on Intelligent Vehicles,2024,9(1):2290-2303.
[76]Batra S, Huang Z, Petrenko A, et al. Decentralized control of quadrotor swarms with end-to-end deep reinforcement learning[C]. Proceedings of the 5th Conference on Robot Learning(CoRL), London, UK,2021-11-08.
[77]Zhang R, Zhang X, Dou L, et al. Game of drones:Multi-UAV pursuit-evasion game with online motion planning by deep reinforcement learning[J]. IEEE Transactions on Neural Networks and Learning Systems,2023,34(10):7900-7909.
[78]Peng Z,Wu G,Luo B. Multi-UAV cooperative pursuit strategy with limited visual field in urban airspace:A multi agent reinforcement learning approach[J]. IEEE Journal of Automatica Sinica,12(7):1350-1367.
[79]Hou Y,Zhao J,Zhang R,et al. UAV swarm cooperative target search:A multi-agent reinforcement learning approach[J]. IEEE Transactions on Intelligent Vehicles,2024,9(1):568-578.
[80]王涛，谢添乐，唐勇，等.认知模型驱动的无人机集群混合智能协同决策方法研究[J].无人系统技术，2025,8(3):109-121.
[81]Wu X,Yan Q,Wang J,et al. Dynamic task allocation for UAV swarm in maritime rescue scenarios based on PG-MAPPO[J]. IEEE Internet of Things Journal,2025,12(18):38073-38087.
[82]Dhuheir M,Erbad A,Hamdaoui B,et al. Multi-agent meta reinforcement learning for reliable and low-latency distributed inference in resource-constrained UAV swarms[J]. IEEE Access,2025,13:103045-103059.
Basic Information:
DOI：10.16338/j.issn.2097-0714.20250105
China Classification Code:V279;V249.1
Citation Information:
[1]Yuan Mingyu,Pan Chao,Tan Xiaowen ,et al.A review of research on autonomous flight and coordination control of unmanned aerial vehicles[J].AEROSPACE TECHNOLOGY,2026,No.470(02):34-52+85.DOI:10.16338/j.issn.2097-0714.20250105.
2026-04-15
2026-04-15