Fényes, Dániel and Hegedűs, Tamás and Gáspár, Péter (2025) Control-Informed Neural Network for Controller Selection. In: International Conference on Control, Decision and Information Technologies - 11th CoDIT 2025., 2025.07.14-17, Split, Horvátország. (In Press)
|
Text
0526_FI.pdf Download (1MB) | Preview |
Abstract
This paper proposes a reinforcement learning (RL)-based approach for dynamically selecting the most suitable control method according to changing operating conditions. Using the nominal model of the actual system, several feedback controllers are developed, each offering different levels of performance depending on the scenario. The RL algorithm is employed to determine and apply the optimal control strategy within a given operational range. Four control methods are investigated: Linear Parameter Varying (LPV), Ultra-local Model-based (ULM), Linear Quadratic Regulator (LQR), and a kinematic model-based controller. The performance and effectiveness of the proposed approach are assessed through three test scenarios using the high-fidelity vehicle simulation platform, CarMaker.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Subjects: | T Technology / alkalmazott, műszaki tudományok > TK Electrical engineering. Electronics Nuclear engineering / elektrotechnika, elektronika, atomtechnika T Technology / alkalmazott, műszaki tudományok > TL Motor vehicles. Aeronautics. Astronautics / járműtechnika, repülés, űrhajózás |
| Depositing User: | Dr Dániel Fényes |
| Date Deposited: | 23 Sep 2025 10:11 |
| Last Modified: | 23 Sep 2025 10:11 |
| URI: | https://real.mtak.hu/id/eprint/224941 |
Actions (login required)
 |
Edit Item |
