| 1,867 | 19 | 125 |
| Downloads | Citas | Reads |
In order to enable UAV to predict target states autonomously and accurately, and then to track maneuvering targets, an online decision algorithm is proposed based on Kalman filtering combined with deep reinforcement learning DDQN algorithm. By building a UAV maneuvering target tracking model and Markov decision process framework, and associating with Kalman filtering, the target states are accurately predicted and updated. Integrating the UAV's states as neural network inputs and performing targeted training with DDQN algorithm, the UAV's autonomous tracking control of the maneuvering target can be achieved.Comparing with the traditional DQN algorithm, the simulation results prove that the UAV based on the DDQN algorithm can maintain longer tracking time, closer tracking distance and a more stable flight in tracking tasks to achieve the efficient tracking of maneuvering target.
[1]段海滨,申燕凯,王寅,等.2018年无人机领域热点评述[J].科技导报,2019,37(3):82-90.
[2]王林,彭辉,朱华勇,等.应用无人机跟踪地面目标--最新研究进展[J].系统仿真学报,2010,22(S1):172-177.
[3]李希.旋翼无人机的航迹规划与鲁棒控制[D].长沙:湖南大学,2019.
[4]黄亚东.基于目标轨迹估计的无人机航路规划方法[D].西安:西安电子科技大学,2019.
[5]He Z F,Zhao L.The comparison of four UAV path planning algorithms based on geometry search algorithm[C].2017 9th International Conference on Intelligent Human-Machine Systems and Cybernetics(IHMSC).2017:33-36.
[6]Li B,Wu Y.Path planning for UAV ground target tracking via deep reinforcement learning[J].IEEEAccess,2020,8:29064-29074.
[7]Mnih V,Kavukcuoglu K,Silver D,et al.Humanlevel control through deep reinforcement learning[J].Nature,2015,518(7540):529-533.
[8]吴运雄,曾碧.基于深度强化学习的移动机器人轨迹跟踪和动态避障[J].广东工业大学学报,2019,36(1):42-50.
[9]李东雨.基于模型控制的深度强化学习算法研究[D].大连:大连理工大学,2019.
[10]Mnih V,Kavukcuoglu K,Silver D,et al.Playing atari with deep reinforcement learning[C].Proceedings of Workshops at the 26th Neural Information Processing Systems,Lake Tahoe,USA,2013:201-220.
[11]黄叶.基于深度强化学习的机器人视觉控制技术研究[D].上海:上海交通大学,2019.
[12]Julier S J,Uhlmann J K.A new extension of the Kalman filter to nonlinear Systems[J].Proceedings of SPIE-The International Society for Optical Engineering,1999,3068:182-193.
[13]Liu Q,Shi L,Sun L,et al.Path planning for UAV-mounted mobile edge computing with deep reinforcement learning[J].IEEE Transactions on Vehicular Technology,2020,69(5):5723-5728.
[14]Zeng Y,Xu X,Jin S,et al.Simultaneous navigation and radio mapping for cellular-connected UAV with deep reinforcement learning[J].IEEE Transactions on Wireless Communications,2021,20(7):4205-4220.
[15]邓洪明,贺勇,於小杰,等.卡尔曼滤波在无人机姿态中的应用研究[J].自动化技术与应用,2019,38(11):1-4.
[16]Van Hasselt H,Guez A,Silver D.Deep reinforcement learning with double Q-learning[C].Proceedings of the AAAI Conference on Artificial Intelligence,Phoenix,USA,2016:1476-1483.
Basic Information:
DOI：10.16358/j.issn.1009-1300.20210022
China Classification Code:V279;TP18;TN713
Citation Information:
[1]Li Lin,Zhang Xiushe,Han Chunlei ,et al.UAV maneuvering target tracking based on Kalman filter and DDQN algorithm[J].Tactical Missile Technology,2022,No.212(02):98-104.DOI:10.16358/j.issn.1009-1300.20210022.
2022-04-12
2022-04-12
2022-04-12