一种无人机编队控制方法研究与仿真
Research and Simulation of a UAV Formation Control Method
DOI: 10.12677/mos.2024.133242, PDF,    国家自然科学基金支持
作者: 陈泽坤*, 何杏宇：上海理工大学光电信息与计算机工程学院，上海
关键词: 编队控制；避障一致性；避障灵活性；强化学习；Formation Control； Obstacle Avoidance Consistency； Obstacle Avoidance Flexibility； Reinforcement Learning
摘要: 现有的无人机群编队控制研究难以在障碍物环境下兼顾无人机的避障一致性和避障灵活性。为此，本文提出了一种基于强化学习的差异化无人机编队控制方法。该方法允许无人机群中的任一无人机根据其局部环境在编队聚集、编队保持和避障之间改变其编队控制策略，并设计了一个强化学习模型为上述三种控制策略下的无人机计算最优偏移向量。仿真结果表明，该方法可以有效地兼顾无人机群的避障灵活性和一致性，从而提高其飞行效率并保持其网络联通性。
Abstract: In existing formation control researches, it is hardly to reconcile both the obstacle avoidance consistency and obstacle avoidance flexibility of the UAV swarm. In view of this, this paper proposes a reinforcement learning based differentiated formation control method for UAVs. This method allows any UAV within the swarm to adapt its formation control strategy among formation aggregation, formation maintenance, and obstacle avoidance based on its local environment, and a reinforcement learning model is designed to compute the optimal offset vector for each UAV under the three aforementioned formation control strategies. Simulation results demonstrate that the method can effectively balance the maneuverability and consistency of obstacle avoidance for UAV swarms, thereby improving their flight efficiency and maintaining network connectivity.
文章引用：陈泽坤, 何杏宇. 一种无人机编队控制方法研究与仿真[J]. 建模与仿真, 2024, 13(3): 2662-2672. https://doi.org/10.12677/mos.2024.133242

参考文献

[1] Zhang, H. and Hanzo, L. (2020) Federated Learning Assisted Multi-UAV Networks. IEEE Transactions on Vehicular Technology, 69, 14104-14109. [Google Scholar] [CrossRef] 
[2] Wu, Y., Low, K.H. and Lv, C. (2020) Cooperative Path Planning for Heterogeneous Unmanned Vehicles in a Search-and-Track Mission Aiming at an Underwater Target. IEEE Transactions on Vehicular Technology, 69, 6782-6787. [Google Scholar] [CrossRef] 
[3] Wu, J., Luo, C., Luo, Y., et al. (2021) Distributed UAV Swarm Formation and Collision Avoidance Strategies Over Fixed and Switching Topologies. IEEE Transactions on Cybernetics, 52, 10969-10979. [Google Scholar] [CrossRef] 
[4] Guo, J., Liu, Z., Song, Y., et al. (2023) Research on Multi-UAV Formation and Semi-Physical Simulation with Virtual Structure. IEEE Access, 11, 126027-126039. [Google Scholar] [CrossRef] 
[5] Nursyeha, M.A., Rivai, M. and Purwanto, D. (2020) LiDAR Equipped Robot Navigation on Behavior-Based Formation Control for Gas Leak Localization. 2020 International Seminar on Intelligent Technology and Its Applications (ISITIA), Surabaya, 22-23 July 2020, 89-94. [Google Scholar] [CrossRef] 
[6] Lee, G. and Chwa, D. (2018) Decentralized Behavior-Based Formation Control of Multiple Robots Considering Obstacle Avoidance. Intelligent Service Robotics, 11, 127-138. [Google Scholar] [CrossRef] 
[7] Chen, Q., Wang, Y. and Lu, Y. (2021) Formation Control for UAVs Based on the Virtual Structure Idea and Nonlinear Guidance Logic. 2021 6th International Conference on Automation, Control and Robotics Engineering (CACRE), Dalian, 15-17 July 2021, 135-139. [Google Scholar] [CrossRef] 
[8] Zhou, D., Wang, Z. and Schwager, M. (2018) Agile Coordination and Assistive Collision Avoidance for Quadrotor Swarms Using Virtual Structures. IEEE Transactions on Robotics, 34, 916-923. [Google Scholar] [CrossRef] 
[9] Wen, G., Chen, C.L.P., Liu, Y.J., et al. (2016) Neural Network-Based Adaptive Leader-Following Consensus Control for a Class of Nonlinear Multiagent State-Delay Systems. IEEE Transactions on Cybernetics, 47, 2151-2160. [Google Scholar] [CrossRef] 
[10] Xiao, H. and Chen, C.L.P. (2019) Leader-Follower Consensus Multi-Robot Formation Control Using Neurodynamic-Optimization-Based Nonlinear Model Predictive Control. IEEE Access, 7, 43581-43590. [Google Scholar] [CrossRef] 
[11] Le, J., Zhao, L., Wang, C., et al. (2020) Leader-Follower Optimal Selection Method for Distributed Control System in Active Distribution Networks. CSEE Journal of Power and Energy Systems, 10, 314-323.
[12] Lyu, Y., Hu, J., Chen, B.M., et al. (2019) Multivehicle Flocking with Collision Avoidance via Distributed Model Predictive Control. IEEE Transactions on Cybernetics, 51, 2651-2662. [Google Scholar] [CrossRef] 
[13] Chen, Q., Jin, Y., Wang, T., et al. (2022) UAV Formation Control Under Communication Constraints Based on Distributed Model Predictive Control. IEEE Access, 10, 126494-126507. [Google Scholar] [CrossRef] 
[14] Luo, L., Wang, X., Ma, J., et al. (2021) GrpAvoid: Multigroup Collision-Avoidance Control and Optimization for UAV Swarm. IEEE Transactions on Cybernetics, 53, 1776-1789. [Google Scholar] [CrossRef] 
[15] Zhu, X., Liang, Y. and Yan, M. (2019) A Flexible Collision Avoidance Strategy for the Formation of Multiple Unmanned Aerial Vehicles. IEEE Access, 7, 140743-140754. [Google Scholar] [CrossRef] 
[16] Liu, D., Dou, L., Zhang, R., et al. (2022) Multi Agent Reinforcement Learning-Based Coordinated Dynamic Task Allocation for Heterogenous UAVs. IEEE Transactions on Vehicular Technology, 72, 4372-4383. [Google Scholar] [CrossRef] 
[17] Yan, C., Xiang, X. and Wang, C. (2020) Fixed-Wing UAVs Flocking in Continuous Spaces: A Deep Reinforcement Learning Approach. Robotics and Autonomous Systems, 131, Article 103594. [Google Scholar] [CrossRef] 
[18] Raja, G., Essaky, S., Ganapathisubramaniyan, A., et al. (2022) Nexus of Deep Reinforcement Learning and Leader-Follower Approach for AIOT Enabled Aerial Networks. IEEE Transactions on Industrial Informatics, 19, 9165-9172. [Google Scholar] [CrossRef] 
[19] Mousavifard, R., Alipour, K., Najafqolian, M.A., et al. (2022) Formation Control of Multi-Quadrotors Based on Deep Q-Learning. 2022 10th RSI International Conference on Robotics and Mechatronics (ICRoM), Tehran, 22-24 November 2022, 172-177. [Google Scholar] [CrossRef] 
[20] Wang, W., Wang, L., Wu, J., et al. (2022) Oracle-Guided Deep Reinforcement Learning for Large-Scale Multi-UAVs Flocking and Navigation. IEEE Transactions on Vehicular Technology, 71, 10280-10292. [Google Scholar] [CrossRef] 

为你推荐