Knowledge Transfer Between Different UAVs for Trajectory Tracking

被引:14
|
作者
Chen, Zhu [1 ]
Liang, Xiao [2 ]
Zheng, Minghui [1 ]
机构
[1] Univ Buffalo, Dept Mech & Aerosp Engn, Buffalo, NY 14260 USA
[2] Univ Buffalo, Dept Civil Struct & Environm Engn, Buffalo, NY 14260 USA
关键词
Knowledge transfer; learning algorithm; heterogeneous systems; motion control; aerial systems; applications; ADAPTIVE-CONTROL; QUADROTOR; SYSTEMS;
D O I
10.1109/LRA.2020.3004776
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
Robots are usually programmed for particular tasks with a considerable amount of hand-crafted tuning work. Whenever a new robot with different dynamics is presented, the well-designed control algorithms for the robot usually have to be retuned to guarantee good performance. It remains challenging to directly program a robot to automatically learn from the experiences gathered by other dynamically different robots. With such a motivation, this letter proposes a learning algorithm that enables a quadrotor unmanned aerial vehicle (UAV) to automatically improve its tracking performance by learning from the tracking errors made by other UAVs with different dynamics. This learning algorithm utilizes the relationship between the dynamics of different UAVs, named the target and training UAVs, respectively. The learning signal is generated by the learning algorithm and then added to the feedforward loop of the target UAV, which does not affect the closed-loop stability. The learning convergence can be guaranteed by the design of a learning filter. With the proposed learning algorithm, the target UAV can improve its tracking performance by learning from the training UAV without baseline controller modifications. Both numerical studies and experimental tests are conducted to validate the effectiveness of the proposed learning algorithm.
引用
收藏
页码:4939 / 4946
页数:8
相关论文
共 50 条
  • [1] A novel approach for trajectory tracking of UAVs
    De Filippis, Luca
    Guglieri, Giorgio
    Quagliotti, Fulvia B.
    AIRCRAFT ENGINEERING AND AEROSPACE TECHNOLOGY, 2014, 86 (03): : 198 - 206
  • [2] Trajectory Tracking for UAVs: An Interpolating Control Approach
    Boucek, Zdenek
    Flidr, Miroslav
    Straka, Ondfej
    2024 28TH INTERNATIONAL CONFERENCE ON METHODS AND MODELS IN AUTOMATION AND ROBOTICS, MMAR 2024, 2024, : 387 - 392
  • [3] Knowledge Transfer Between Robots with Similar Dynamics for High-Accuracy Impromptu Trajectory Tracking
    Zhou, Siqi
    Sarabakha, Andriy
    Kayacan, Erdal
    Helwa, Mohamed K.
    Schoellig, Angela P.
    2019 18TH EUROPEAN CONTROL CONFERENCE (ECC), 2019, : 1 - 8
  • [4] Trajectory tracking control of thrust-vectoring UAVs
    Invernizzi, Davide
    Lovera, Marco
    AUTOMATICA, 2018, 95 : 180 - 186
  • [5] Nonlinear Trajectory Tracking Control for Winged eVTOL UAVs
    Willis, Jacob B.
    Beard, Randal W.
    2021 AMERICAN CONTROL CONFERENCE (ACC), 2021, : 1687 - 1692
  • [6] Proactive Eavesdropping via Jamming for Trajectory Tracking of UAVs
    Li, Kai
    Kanhere, Salil S.
    Ni, Wei
    Tovar, Eduardo
    Guizani, Mohsen
    2019 15TH INTERNATIONAL WIRELESS COMMUNICATIONS & MOBILE COMPUTING CONFERENCE (IWCMC), 2019, : 477 - 482
  • [7] Safety-critical trajectory tracking control of quadrotor UAVs
    Sun G.-H.
    Zeng Q.-S.
    Cai Z.-Z.
    Kongzhi Lilun Yu Yingyong/Control Theory and Applications, 2023, 40 (07): : 1261 - 1269
  • [8] Robust Trajectory Tracking Control for Tail-Sitter UAVs
    Liu Deyuan
    Liu Hao
    Li Zhaoying
    Zhao Wanbing
    2018 37TH CHINESE CONTROL CONFERENCE (CCC), 2018, : 2538 - 2542
  • [9] L1 Adaptive Backstepping for Robust Trajectory Tracking of UAVs
    Zuo, Zongyu
    Mallikarjunan, Srinath
    IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2017, 64 (04) : 2944 - 2954
  • [10] Dynamic Attitude Planning for Trajectory Tracking in Thrust-Vectoring UAVs
    Invernizzi, Davide
    Lovera, Marco
    Zaccarian, Luca
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2020, 65 (01) : 453 - 460