Ruochuan Fan

Ms. Ruochuan Fan

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 April 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
RFRuochuan Fan
Ruochuan Fan
JLJian Lu
Jian Lu
DWDavid Z. W. Wang
David Z. W. Wang
FZFang Zhang
Fang Zhang
Signalized intersections play a pivotal role in urban traffic networks and are simultaneously impacted by congestion and pollution. The rapid advancement of Connected Automated Vehicles (CAVs) and associated technologies offers a promising solution to these efficiency and ecological challenges. Within the Cooperative Vehicle Infrastructure System (CVIS), Level 4 CAVs enable real-time information exchange and autonomous driving at intersections. The heterogeneous traffic flow of CAVs and Human-driven Vehicles (HVs) is expected to persist in the foreseeable future, increasing the complexity of traffic flow. This study introduces an adaptive speed optimization control model using the Mixed-Integer Linear Programming (MILP) method, which predicts traffic conditions and offers optimal speed recommendations for CAVs through a multi-objective function. Additionally, this model incorporates local decision and fault tolerance mechanisms to mitigate the impact of potential network delays. Simulation results demonstrate that the optimized CAVs smoothly and swiftly guide the entire heterogeneous traffic flow through intersections, and significantly reducing average delays and carbon emissions. Moreover, upstream intersections consideration has little impact on optimization outcomes. The model shows noticeable optimization effects as CAV penetration rates reach 30%, and becomes even more pronounced at 50% penetration rate, with optimization trends intensifying with increased flow rate. Compared to HVs, CAVs at a flow rate of 1000 veh/h witness a reduction in average delay and waiting time by 56.31 and 15.89 s, respectively, and a total decrease in CO $_{2}$ emissions by 18.5%.

20 September 2022 in Research in Transportation Economics
Verified
Journal Article
Closed access
FZFang Zhang
Fang Zhang
JLJian Lu
Jian Lu
XHXiaojian Hu
Xiaojian Hu
RFRuochuan Fan
Ruochuan Fan
JCJunlan Chen
Junlan Chen

11 January 2026 in Sensors
Verified
Journal Article
Open access
PDF file
RFRuochuan Fan
Ruochuan Fan
JLJian Lu
Jian Lu
With the advancement of sensing, communication, and cooperative capabilities of connected automated vehicles (CAVs), the capacity and operational state of signalized intersections have become increasingly observable and suitable for prospective assessment. However, existing capacity models based on homogeneous traffic assumptions are insufficient to describe the capacity evolution of mixed traffic under varying CAV penetration levels. Motivated by this limitation, this study proposes a quantitative capacity estimation method for signalized intersections considering CAV penetration, serving as an evaluation and prediction baseline for intersection operations. The proposed method improves the CAV gain parameter and accounts for multiple typical car-following states in mixed traffic to derive equivalent headways and spacing coefficients, enabling a continuous estimation of intersection capacity with respect to CAV penetration. Using data from an actual signalized intersection, capacity and saturation trends are analyzed across different movement directions and traffic demand conditions. The results indicate a nonlinear increasing pattern of intersection capacity as CAV penetration rises, with distinct growth rates between straight-through and left-turn movements. The proposed approach provides an engineering-oriented reference for capacity estimation and traffic state prediction under mixed traffic conditions.

1 October 2026 in Journal of Transportation Engineering, Part A: Systems
Verified
Journal Article
Closed access
PDF file
RFRuochuan Fan
Ruochuan Fan
JLJian Lu
Jian Lu
XLXian Liu
Xian Liu
Connected and automated vehicles (CAVs) have the potential to significantly improve the efficiency and safety of urban intersections, yet their benefits depend strongly on penetration rates and their interaction with signal control strategies. This study proposes a joint optimization model that integrates a multiagent deep Q-network (MADQN)-based strategy for CAV trajectory control and an adaptive strategy for signal phase adjustment in mixed traffic. The proposed model incorporates key states from both vehicles and signals, including speed, acceleration, queue length, and phase information, and employs a global reward that combines average delay and energy consumption. An adaptive signal control driven by queue pressure dynamically adjusts phase durations in response to real-time traffic conditions, with its outcomes feeding back into the environment for CAVs training. Simulation experiments conducted on a real-world multidirectional intersection demonstrate that the proposed model effectively reduces delays across most movements even at low CAV penetration rates. As the CAV penetration rate increases, consistent and more pronounced reductions in both delay and energy consumption are observed for all movements.