István Gellért Knáb, B.Sc.

Introduction

István Gellért Knáb obtained his BSc degree in Vehicle Engineering in 2024 from the Faculty of Transportation Engineering and Vehicle Engineering at Budapest University of Technology and Economics. He is currently pursuing his MSc studies in Autonomous Vehicle Control Engineering at the same institution. His research focuses on the application of artificial intelligence in various traffic situations and vehicle control tasks. His goal is to contribute to the development of autonomous vehicles, and through his research, he develops innovative solutions that enhance the safety and efficiency of transportation.

Achievements

• Award: Multi-Agent Reinforcement Learning for Adaptive Traffic Light Control (TDK 2022)
• 1st Place: Multi-Agent Reinforcement Learning-Based Decision Making in Highway Environments (TDK 2023)
• Pro Progressio Foundation Special Prize: Multi-Agent Reinforcement Learning-Based Decision Making in Highway Environments (TDK 2023)
• Asura Technologies Ltd. Special Prize: Multi-Agent Reinforcement Learning-Based Decision Making in Highway Environments (TDK 2023)
• 2nd Place: Adaptability of Homogeneous Agents in Dynamically Scalable Traffic Environments (TDK 2024)
• 3rd Place: Investigation of Experience Replay Prioritization Techniques for Continuous Action Space Agents (TDK 2024)

Publications

• B. Kovari, I. Knab, and T. Becsi, "Variable Speed Limit Control for Highway Scenarios: A Multi-Agent Reinforcement Learning Based Approach," in 2nd International Conference on Cognitive Mobility, 2023.
• Kővári, B., Pelenczei, B., Knáb, I. G., & Bécsi, T. (2024). Beyond Trial and Error: Lane Keeping with Monte Carlo Tree Search-Driven Optimization of Reinforcement Learning. Electronics, 13(11), 2058.
• Kővári, B., Knáb, I., & Bécsi, T. (2024). Variable Speed Limit Control for Highway scenarios a Multi-Agent Reinforcement Learning Based Appraoch (No. 13400). EasyChair.
• Pelenczei, B. ; Knáb, I. ; Kővári, B. ; Bécsi, T. and Palkovics, L. (2024). Adaptive Highway Traffic Management: A Reinforcement Learning Approach for Variable Speed Limit Control with Random Anomalies. In Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics
• Knáb, I. ; Pelenczei, B. ; Kővári, B. ; Bécsi, T. and Palkovics, L. (2024). Expanded Applicability: Multi-Agent Reinforcement Learning-Based Traffic Signal Control in a Variable-Sized Environment. In Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics

Languages

• German (C1)
• English (B2)
• Italian (A2)