International Journal of Control, Automation, and Systems 2025; 23(2): 510-519
https://doi.org/10.1007/s12555-024-0475-2
© The International Journal of Control, Automation, and Systems
In this work, we demonstrate the efficiency of approximating nonlinear model predictive control (NMPC) using deep neural networks (DNN). We design an implicit NMPC for forward and backward motions of the truck trailer (TT) to handle complexity of nonlinear system dynamics. However, the high computational load of implicit MPC poses challenges for real-time implementation. To address this issue, we employ a DNN-based NMPC approximation to estimate parametric functions. As a result, the DNN-based NMPC approximation can mimic the optimal control policy of implicit MPC. Additionally, the average computation times for implicit NMPC and the DNN-based NMPC approximation in hardware-in-the-loop (HIL) tests are 36.541 ms and 0.031 ms, respectively.
Keywords Approximation, deep neural network, hardware-in-the-loop, nonlinear model predictive control, trucktrailer system.
International Journal of Control, Automation, and Systems 2025; 23(2): 510-519
Published online February 1, 2025 https://doi.org/10.1007/s12555-024-0475-2
Copyright © The International Journal of Control, Automation, and Systems.
Suyong Park, Duc Giap Nguyen, Yongsik Jin, Jinrak Park, Dohee Kim, Jeong Soo Eo, and Kyoungseok Han*
Hanyang University
In this work, we demonstrate the efficiency of approximating nonlinear model predictive control (NMPC) using deep neural networks (DNN). We design an implicit NMPC for forward and backward motions of the truck trailer (TT) to handle complexity of nonlinear system dynamics. However, the high computational load of implicit MPC poses challenges for real-time implementation. To address this issue, we employ a DNN-based NMPC approximation to estimate parametric functions. As a result, the DNN-based NMPC approximation can mimic the optimal control policy of implicit MPC. Additionally, the average computation times for implicit NMPC and the DNN-based NMPC approximation in hardware-in-the-loop (HIL) tests are 36.541 ms and 0.031 ms, respectively.
Keywords: Approximation, deep neural network, hardware-in-the-loop, nonlinear model predictive control, trucktrailer system.
Vol. 23, No. 2, pp. 359~682
Sunwoo Hwang, Inkyu Jang, Dabin Kim, and H. Jin Kim*
International Journal of Control, Automation, and Systems 2024; 22(10): 2955-2969Na Qin, Tianwei Wang, Deqing Huang*, Yiming Zhang, and Lei Ma
International Journal of Control, Automation, and Systems 2023; 21(10): 3430-3442Fang Deng, Hua-Lin Yang*, Long-Jin Wang, and Wei-Min Yang
International Journal of Control, Automation and Systems 2019; 17(12): 3079-3090