I am looking for partners in the research area.

I am looking for partners interested in the Horizon Europe Call.

I am looking for partners for the Horizon Europe research area.

I am looking for laboratory facilities in the research/application area.

Vehicle Control and Machine Learning Research Group

Dr. Tamás Bécsi

Associate Professor


H-1111 Budapest, Stocek u. 2., BME St. bld. 106



Dr. Szilárd Aradi

Senior Researcher

Dr. Péter Gáspár

Full Professor

Dr. Ádám Szabó


Dr. Olivér Törő

Assistant Research Fellow

Dr. Balázs Németh

Research Fellow

Introduction of the Research Group

The Vehicle Control and Machine Learning Research Group deals with two research areas in the field of highly automated vehicles. The first area is vehicle dynamics modeling and control using classical and robust control techniques and machine learning. Research is carried out at several levels of motion planning, from strategic decision-making through various tasks of trajectory planning to low-level control. Our narrower area of study within machine learning is research on reinforced learning methods, where, unlike supervised learning, no training data is available. In this case, the control planning or decision-making agent can learn the expected behavior in a simulated environment modeled as a Markov decision process based on self-generated experience. We carry out basic research in the field with the further development of various agents, for example, in planning agents or multi-agent systems, and use them in the automotive industry. Thus, we have achieved new results in traffic management, motion planning in a static and dynamic environment, and trajectory tracking tasks. The second area is environmental perception and sensor fusion in the automotive industry, based on supervised learning and Bayesian inference. The goal here is to process the measurements provided by the radar, camera, and lidar sensors, loaded with various errors and noises, and create the most stable and accurate environmental representation possible. Our research aims to generate linearly scalable models that also have a real-time implementation capability. These supply essential information for vehicle control planning. The generated data sets can be used to estimate the probability of vehicle movement on a model basis or using supervised learning.

Watch our 3-minute introductory video:


  • Development of a new planning agent-based reinforcement learning agent
  • Traffic management through learning in a single- and multi-agent environment
  • Hierarchical trajectory design with reinforced learning to avoid static and dynamic objects
  • GM-PHD filter-based, linearly scalable sensor fusion for processing radar and camera measurements


L. Lindenmaier, S. Aradi, T. Becsi, O. Toro and P. Gaspar, "GM-PHD Filter Based Sensor Data Fusion for Automotive Frontal Perception System," in IEEE Transactions on Vehicular Technology, doi: 10.1109/TVT.2022.3171040. (https://ieeexplore.ieee.org/document/9765356)

L. Szoke, S. Aradi, T. Bécsi and P. Gáspár, "Skills to Drive: Successor Features for Autonomous Highway Pilot," in IEEE Transactions on Intelligent Transportation Systems, doi: 10.1109/TITS.2022.3150493. (https://ieeexplore.ieee.org/document/9719995)

Á. Fehér, S. Aradi and T. Bécsi, "Hierarchical Evasive Path Planning Using Reinforcement Learning and Model Predictive Control," in IEEE Access, vol. 8, pp. 187470-187482, 2020, doi: 10.1109/ACCESS.2020.3031037. (https://ieeexplore.ieee.org/document/9223644)

Dániel Fényes, Máté Fazekas, Balázs Németh & Péter Gáspár (2021) Implementation of a variable-geometry suspension-based steering control system, Vehicle System Dynamics, https://doi.org/10.1080/00423114.2021.1890798

Németh, B, Gáspár, P. Ensuring performance requirements for semiactive suspension with nonconventional control systems via robust linear parameter varying framework. Int J Robust Nonlinear Control. 2021; 31: 8165– 8182. https://doi.org/10.1002/rnc.5282


IEEE Transactions on Vehicular Technology
IEEE Transactions on Intelligent Transportation Systems
IEEE Access
Vehicle System Dynamics
Int J Robust Nonlinear Control


The research team uses automotive sensors, measuring vehicles, and automated vehicles of various sizes to perform measurements and demonstrations.


EFOP-3.6.3-VEKOP-16-2017-00001:Tehetséggondozás és kutatói utánpótlás fejlesztése autonóm járműirányítási technológiák területén, 2017-2022, NKFIH

Felsőoktatási Intézményi Kiválósági Program (20458-3/2018/FEKUTSTRAT): Future Mobility, 2018-2021

Autonóm Rendszerek Nemzeti Kutatólaboratórium, 2020-, NKFIH

TKP2021-NVA-02, Tématerületi Kiválósági Program 2021- Nemzetvédelem, nemzetbiztonság alprogram, NKFIH

Industry relations

Knorr-Bremse, Robert Bosch


IFAC World Congress 2020, Germany

The 24th Euro Working Group on Transportation Meeting (EWGT 2021), virtual

European Control Conference (ECC 20), Saint Petersburg, Russia, May 12‑15, 2020

IEEE 25th International Conference on Intelligent Engineering Systems 2021 (INES 2021) July 7-9, Budapest, Hungary.

IEEE 19th World Symposium on Applied Machine Intelligence and Informatics 2022 (SAMI), Herl'any, Slovakia

Other activities

Memberships in Institute of Electrical and Electronics Engineers (IEEE), International Federation of Automatic Control (IFAC), Hungarian Academy of Sciences.

The research group publishes its results in several conferences and renowned journals, and we give special importance to the development of education and youth education, and we have given several series of professional lectures.