Balazs Nemeth

22035873500

Publications - 4

Reinforcement Learning-Based Robust Vehicle Control for Autonomous Vehicle Trajectory Tracking †

Balazs Nemeth Peter Gaspar Attila Lelkó

Publication Name: Engineering Proceedings

Publication Date: 2024-01-01

Volume: 79

Issue: 1

Page Range: Unknown

Description:

This publication presents a new method by which control methods based on reinforcement learning can be combined with classical robust control methods. The combination results in a robust management system that meets high-quality criteria. The described method is presented through the control of an autonomous vehicle. By choosing the reward function chosen during reinforcement learning, various driving styles can be realized, e.g., lap time minimization, track tracking, and travel comfort. The neural network was trained using the Proximal Policy Optimization algorithm, and the robust control is based on (Formula presented.). The two controllers are combined using a supervisor structure, in which a quadratic optimization task is implemented. The result of the method is a control structure that realizes the longitudinal and lateral control of the vehicle by specifying the reference speed and the steering angle. The effectiveness of the algorithm is demonstrated through simulations.

Open Access: Yes

DOI: 10.3390/engproc2024079030

Robustness analysis and reconfiguration strategy of autonomous vehicles in intersections

Balazs Nemeth Dániel Pup Peter Gaspar Peter Szilassy Ferenc Szauter

Publication Name: Saci 2019 IEEE 13th International Symposium on Applied Computational Intelligence and Informatics Proceedings

Publication Date: 2019-05-01

Volume: Unknown

Issue: Unknown

Page Range: 45-50

Description:

The paper proposes the design of a neural-network-based control strategy of autonomous vehicles in intersections. The motivation of the neural network approach is to reduce the numerically-intensive computation of the optimization problem in which the motions of autonomous vehicles are formed. In the method the neural network is trained through a preliminary optimal off-line solution. Moreover, a robustness analysis and a reconfiguration strategy for the scenarios with vehicle position disturbances are proposed. The design and the analysis are illustrated through CarSim simulation examples.

Open Access: Yes

DOI: 10.1109/SACI46893.2019.9111527

Study on a road surface estimation method based on big data analysis

Balazs Nemeth Dániel Pup Daniel Fenyes Peter Gaspar Ferenc Szauter

Publication Name: Saci 2019 IEEE 13th International Symposium on Applied Computational Intelligence and Informatics Proceedings

Publication Date: 2019-05-01

Volume: Unknown

Issue: Unknown

Page Range: 57-62

Description:

The paper presents a new method to classify the road surfaces according to the adhesion coefficient between the tire and road surface using big data approach. In this research, three different categories of the road surface are considered, such as dry, wet and icy. The purpose of classification is to create a model, which is able to determine the type of the actual road surface using only the measured data of the vehicle. The classification method is, basically, based on the C4.5 decision tree algorithm, while the data is provided the high-fidelity simulation software, CarSim. Finally, the efficiency of the resulted model is demonstrated through a complex simulation.

Open Access: Yes

DOI: 10.1109/SACI46893.2019.9111487

Learning-aided observer design for improving autonomous vehicle safety

Balazs Nemeth Andras Mihaly Peter Gaspar Mihály Kopasz Ferenc Szauter

Publication Name: Scientific Reports

Publication Date: 2026-12-01

Volume: 16

Issue: 1

Page Range: Unknown

Description:

This paper introduces a novel method for the enhancement of automated vehicle safety and efficiency during critical manoeuvres. The fundamental of the presented method is the observer design architecture, in which lateral dynamic states of the vehicle are evaluated. The novel observer consists of both model-based and machine-learning-based methods to ensure the selected design performances, such as efficient trajectory tracking and safety evaluation of the autonomous vehicle. In contrast to the already introduced and applied stability index-based methods, the proposed safety evaluation process is able detect stability loss and performance degradation of the autonomous vehicle. In the proposed observer-based safety evaluation method, stability and performance loss detection is based on the comparison of model-based and learning-based state observation. The main novelty of the paper is the design of the reinforcement learning (RL) based observer in a guaranteed structure that results in small observation error even under nonlinear vehicle dynamics. Furthermore, a lateral safety index is defined based on the value of the improvement vector representing the addition to the model-based estimation. By this means, with the proposed safety evaluation method both safety and performance loss hazards can be identified simultaneously.

Open Access: Yes

DOI: 10.1038/s41598-026-35378-9