Robust Model Predictive Control-Based Recurrent Neural Networks for Autonomous Vehicles in Avoidance Collisions
Ensuring safe driving under real-time uncertainties remains a critical challenge in autonomous vehicle control. To address this issue for a collision avoidance task, this study proposes a robust model predictive control (RMPC) framework that handles parametric uncertainties using optimization-based...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11031406/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849426067862847488 |
|---|---|
| author | Hung Duy Nguyen Duc Thinh Le Tung Lam Nguyen Minh Nhat Vu |
| author_facet | Hung Duy Nguyen Duc Thinh Le Tung Lam Nguyen Minh Nhat Vu |
| author_sort | Hung Duy Nguyen |
| collection | DOAJ |
| description | Ensuring safe driving under real-time uncertainties remains a critical challenge in autonomous vehicle control. To address this issue for a collision avoidance task, this study proposes a robust model predictive control (RMPC) framework that handles parametric uncertainties using optimization-based linear matrix inequality (LMI). By incorporating system parametric uncertainties, the RMPC enhances driving stability and safety through the use of input-state constraints. However, due to its computational complexity, we employ a data-driven approach by collecting measurements under different road adhesion conditions to train deep neural networks with a long short-term memory layer (DNN-LSTM). The proposed DNN-LSTM effectively captures temporal dependencies, outperforming existing DNNs when using the same hyperparameters in accuracy and generalization. All comparative simulations are conducted and verified using the high-fidelity CarSim/Simulink co-simulation platform. Therefore, the proposed DNN-LSTM approach approximates the RMPC policy with high training performance and significantly reduces computational complexity, which is more beneficial for real-time implementation. Using the DNN-LSTM is further emphasized to maintain the ability to drive stability of autonomous vehicles compared with online and offline RMPCs, which show a stable region violation at some fixed operation points. |
| format | Article |
| id | doaj-art-a468baecf8cb4483bd329bd2aaa25983 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a468baecf8cb4483bd329bd2aaa259832025-08-20T03:29:34ZengIEEEIEEE Access2169-35362025-01-011310611510612810.1109/ACCESS.2025.357921611031406Robust Model Predictive Control-Based Recurrent Neural Networks for Autonomous Vehicles in Avoidance CollisionsHung Duy Nguyen0https://orcid.org/0000-0001-9495-489XDuc Thinh Le1https://orcid.org/0000-0003-1490-5057Tung Lam Nguyen2https://orcid.org/0000-0003-4108-8275Minh Nhat Vu3Automation and Control Institute (ACIN), Vienna University of Technology, Vienna, AustriaFaculty of Electrical and Electronics Engineering, Thuyloi University, Hanoi, VietnamSchool of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, VietnamAutomation and Control Institute (ACIN), Vienna University of Technology, Vienna, AustriaEnsuring safe driving under real-time uncertainties remains a critical challenge in autonomous vehicle control. To address this issue for a collision avoidance task, this study proposes a robust model predictive control (RMPC) framework that handles parametric uncertainties using optimization-based linear matrix inequality (LMI). By incorporating system parametric uncertainties, the RMPC enhances driving stability and safety through the use of input-state constraints. However, due to its computational complexity, we employ a data-driven approach by collecting measurements under different road adhesion conditions to train deep neural networks with a long short-term memory layer (DNN-LSTM). The proposed DNN-LSTM effectively captures temporal dependencies, outperforming existing DNNs when using the same hyperparameters in accuracy and generalization. All comparative simulations are conducted and verified using the high-fidelity CarSim/Simulink co-simulation platform. Therefore, the proposed DNN-LSTM approach approximates the RMPC policy with high training performance and significantly reduces computational complexity, which is more beneficial for real-time implementation. Using the DNN-LSTM is further emphasized to maintain the ability to drive stability of autonomous vehicles compared with online and offline RMPCs, which show a stable region violation at some fixed operation points.https://ieeexplore.ieee.org/document/11031406/Robust model predictive controldeep neural networksdata-driven controllinear matrix inequalityautonomous vehicles |
| spellingShingle | Hung Duy Nguyen Duc Thinh Le Tung Lam Nguyen Minh Nhat Vu Robust Model Predictive Control-Based Recurrent Neural Networks for Autonomous Vehicles in Avoidance Collisions IEEE Access Robust model predictive control deep neural networks data-driven control linear matrix inequality autonomous vehicles |
| title | Robust Model Predictive Control-Based Recurrent Neural Networks for Autonomous Vehicles in Avoidance Collisions |
| title_full | Robust Model Predictive Control-Based Recurrent Neural Networks for Autonomous Vehicles in Avoidance Collisions |
| title_fullStr | Robust Model Predictive Control-Based Recurrent Neural Networks for Autonomous Vehicles in Avoidance Collisions |
| title_full_unstemmed | Robust Model Predictive Control-Based Recurrent Neural Networks for Autonomous Vehicles in Avoidance Collisions |
| title_short | Robust Model Predictive Control-Based Recurrent Neural Networks for Autonomous Vehicles in Avoidance Collisions |
| title_sort | robust model predictive control based recurrent neural networks for autonomous vehicles in avoidance collisions |
| topic | Robust model predictive control deep neural networks data-driven control linear matrix inequality autonomous vehicles |
| url | https://ieeexplore.ieee.org/document/11031406/ |
| work_keys_str_mv | AT hungduynguyen robustmodelpredictivecontrolbasedrecurrentneuralnetworksforautonomousvehiclesinavoidancecollisions AT ducthinhle robustmodelpredictivecontrolbasedrecurrentneuralnetworksforautonomousvehiclesinavoidancecollisions AT tunglamnguyen robustmodelpredictivecontrolbasedrecurrentneuralnetworksforautonomousvehiclesinavoidancecollisions AT minhnhatvu robustmodelpredictivecontrolbasedrecurrentneuralnetworksforautonomousvehiclesinavoidancecollisions |