Learning Based Model Predictive Control for Quadcopters with Dual Gaussian Process

被引:3
|
作者
Liu, Yuhan [1 ,2 ]
Toth, Roland [2 ,3 ]
机构
[1] Harbin Inst Technol, Dept Control Sci & Engn, Harbin, Peoples R China
[2] Eindhoven Univ Tech, Dept Elect Engn, Control Syst Grp, Eindhoven, Netherlands
[3] Inst Comp Sci & Control, Budapest, Hungary
关键词
TRACKING;
D O I
10.1109/CDC45484.2021.9683258
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
An important issue in quadcopter control is that an accurate dynamic model of the system is nonlinear, complex, and costly to obtain. This limits achievable control performance in practice. Gaussian process (GP) based estimation is an effective tool to learn unknown dynamics from input/output data. However, conventional GP-based control methods often ignore the computational cost associated with accumulating data during the operation of the system and how to handle forgetting in continuous adaption. In this paper, we present a novel Dual Gaussian Process (DGP) based model predictive control strategy that improves the performance of a quadcopter during trajectory tracking. The bio-inspired DGP structure is a combination of a long-term GP and a short-term GP, where the long-term GP is used to keep the learned knowledge in memory and the short-term GP is employed to rapidly compensate unknown dynamics during online operation. Furthermore, a novel recursive online update strategy for the short-term GP is proposed to successively improve the learnt model during online operation in an efficient way. Numerical simulations are used to demonstrate the effectiveness of the proposed strategy.
引用
收藏
页码:1515 / 1521
页数:7
相关论文
共 50 条
  • [1] Gaussian process model based predictive control
    Kocijan, J
    Murray-Smith, R
    Rasmussen, CE
    Girard, A
    [J]. PROCEEDINGS OF THE 2004 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2004, : 2214 - 2219
  • [2] Constrained Gaussian Process Learning for Model Predictive Control
    Matschek, Janine
    Himmel, Andreas
    Sundmacher, Kai
    Findeisen, Rolf
    [J]. IFAC PAPERSONLINE, 2020, 53 (02): : 971 - 976
  • [3] Stability of Gaussian Process Learning Based Output Feedback Model Predictive Control
    Maiworm, Michael
    Limon, Daniel
    Maria Manzano, Jose
    Findeisen, Rolf
    [J]. IFAC PAPERSONLINE, 2018, 51 (20): : 455 - 461
  • [4] Gaussian Process-Based Learning Model Predictive Control With Application to USV
    Li, Fei
    Li, Huiping
    Wu, Chao
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2024, 71 (12) : 16388 - 16397
  • [5] Enhanced Gaussian Process Regression for Active Learning Model-based Predictive Control
    Ren, Rui
    Li, Shaoyuan
    [J]. 2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC), 2021, : 2731 - 2736
  • [6] Backflipping With Miniature Quadcopters by Gaussian-Process-Based Control and Planning
    Antal, Peter
    Peni, Tamas
    Toth, Roland
    [J]. IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2024, 32 (01) : 3 - 14
  • [7] Gaussian Process Based Model Predictive Controller for Imitation Learning
    Joukov, Vladimir
    Kulic, Dana
    [J]. 2017 IEEE-RAS 17TH INTERNATIONAL CONFERENCE ON HUMANOID ROBOTICS (HUMANOIDS), 2017, : 850 - 855
  • [8] Active Learning Gaussian Process Model Predictive Control Method for Quadcopter
    Zhao, Shulong
    Yi, Feng
    Wang, Qipeng
    Wang, Xiangke
    [J]. 2022 41ST CHINESE CONTROL CONFERENCE (CCC), 2022, : 2664 - 2669
  • [9] Online learning-based model predictive control with Gaussian process models and stability guarantees
    Maiworm, Michael
    Limon, Daniel
    Findeisen, Rolf
    [J]. INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2021, 31 (18) : 8785 - 8812
  • [10] Nonlinear predictive control with a Gaussian process model
    Kocijan, J
    Murray-Smith, R
    [J]. SWITCHING AND LEARNING IN FEEDBACK SYSTEMS, 2005, 3355 : 185 - 200