Our newest paper titled “Reinforcement Learning-Based Dynamic Zone Placement Variable Speed Limit Control for Mixed Traffic Flows Using Speed Transition Matrices for State Estimation” has been accepted for publication and published in the international scientific journal Machines, Special Issue “Current and Future Trends in Control and Automation- Selected Papers from the 30th Mediterranean Conference on Control and Automation (MED ’22)”. The paper is freely available in Open Access with DOI: https://doi.org/10.3390/machines11040479.
This paper was written in the co-authorship of Prof. Edouard Ivanjko with his Ph.D. students Filip Vrbanić, mag. ing. traff., Leo Tišljarić, mag. ing. traff. and Željko Majstorović, mag. ing. traff..
The paper presents the results of applying Q-learning for dynamic variable speed limit zone placement and variable speed limit control using speed transition matrices for state estimation on urban motorways in improving macroscopic traffic measures of effectiveness with a focus on mixed traffic flows that include human-driven vehicles and connected autonomous vehicles.