Energy saving potentials of connected and automated vehicles

A Vahidi, A Sciarretta - Transportation Research Part C: Emerging …, 2018 - Elsevier
Connected and automated vehicles (CAV) are marketed for their increased safety, driving
comfort, and time saving potential. With much easier access to information, increased …

[HTML][HTML] Leveraging reinforcement learning for dynamic traffic control: A survey and challenges for field implementation

Y Han, M Wang, L Leclercq - Communications in Transportation Research, 2023 - Elsevier
In recent years, the advancement of artificial intelligence techniques has led to significant
interest in reinforcement learning (RL) within the traffic and transportation community …

Dissipation of stop-and-go waves via control of autonomous vehicles: Field experiments

RE Stern, S Cui, ML Delle Monache, R Bhadani… - … Research Part C …, 2018 - Elsevier
Traffic waves are phenomena that emerge when the vehicular density exceeds a critical
threshold. Considering the presence of increasingly automated vehicles in the traffic stream …

Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning

Z Li, H Yu, G Zhang, S Dong, CZ Xu - Transportation Research Part C …, 2021 - Elsevier
Inefficient traffic control may cause numerous problems such as traffic congestion and
energy waste. This paper proposes a novel multi-agent reinforcement learning method …

Optimal perimeter control for two urban regions with macroscopic fundamental diagrams: A model predictive approach

N Geroliminis, J Haddad… - IEEE Transactions on …, 2012 - ieeexplore.ieee.org
Recent analysis of empirical data from cities showed that a macroscopic fundamental
diagram (MFD) of urban traffic provides for homogenous network regions a unimodal low …

A physics-informed reinforcement learning-based strategy for local and coordinated ramp metering

Y Han, M Wang, L Li, C Roncoli, J Gao, P Liu - … Research Part C: Emerging …, 2022 - Elsevier
This paper proposes a physics-informed reinforcement learning (RL)-based ramp metering
strategy, which trains the RL model using a combination of historic data and synthetic data …

Economic model predictive control of large-scale urban road networks via perimeter control and regional route guidance

II Sirmatel, N Geroliminis - IEEE Transactions on Intelligent …, 2017 - ieeexplore.ieee.org
Local traffic control schemes fall short of achieving coordination with other parts of the urban
road network, whereas a centralized controller based on the detailed traffic models would …

Parsimonious shooting heuristic for trajectory design of connected automated traffic part I: Theoretical analysis with generalized time geography

F Zhou, X Li, J Ma - Transportation Research Part B: Methodological, 2017 - Elsevier
This paper studies a problem of designing trajectories of a platoon of vehicles on a highway
segment with advanced connected and automated vehicle technologies. This problem is …

Controllability analysis and optimal control of mixed traffic flow with human-driven and autonomous vehicles

J Wang, Y Zheng, Q Xu, J Wang… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Connected and automated vehicles (CAVs) have a great potential to improve traffic
efficiency in mixed traffic systems, which has been demonstrated by multiple numerical …

A new reinforcement learning-based variable speed limit control approach to improve traffic efficiency against freeway jam waves

Y Han, A Hegyi, L Zhang, Z He, E Chung… - … research part C: emerging …, 2022 - Elsevier
Conventional reinforcement learning (RL) models of variable speed limit (VSL) control
systems (and traffic control systems in general) cannot be trained in real traffic process …