Yu Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Yu Han has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Panagiotis Antsaklis
Department of Obstetrics and Gynecology, ‘Alexandra’ General Hospital, National and Kapodistrian University of Athens, 80 Vasilissis Sofias Avenue, 11528 Athens, Greece
2 shared publications Annie S. Wu
University of Central Florida
1 shared publication- Bo Zeng
School of Mathematics and Statistics, Chongqing Technology and Business University
1 shared publication - Dan Cristian Marinescu
University of Central Florida
1 shared publication - Fan Ding
School of Transportation, Southeast University, Nanjing, China
1 shared publication - Gengyue Han
Purdue University, West Lafayette, IN, USA
1 shared publication
Latest Publications
- Top Cited Papers
- 1 March 2026
- Published by Elsevier in Transportation Research Part C: Emerging Technologies
- Vol. 186
Cooperative signal and vehicle control in mixed traffic environment using model-guided reinforcement learning
- 1 March 2026
- Published by Elsevier in Transportation Research Part C: Emerging Technologies
- Vol. 186
Top Cited PapersCooperative signal and vehicle control in mixed traffic environment using model-guided reinforcement learning
- Open Access
- 16 January 2025
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2025 (1)
Reinforcement Learning–Based Ramp Metering Strategy Considering Queue Management
This paper introduces an action replacement module for reinforcement learning (RL)–based ramp metering to address the issue of ramp queue spillback during the training process. Ramp queue spillback leads to significant impacts on the traffic efficiency of adjacent road networks, making it a critical concern in ramp control. Existing RL approaches often employ ramp states as reward functions to encourage agents to learn strategies that avoid queue overflow. However, due to the trial‐and‐error nature of RL, these methods frequently generate actions that cause queue spillback during training, posing challenges for real‐time online training in real‐world applications. To overcome this limitation, the proposed action replacement module utilizes the store‐and‐forward model to estimate a lower bound for ramp metering rates. By identifying and replacing actions that fail to meet this constraint, the strategy effectively prevents queue spillback. In addition, penalties are imposed on replaced actions to guide the agent in learning effective and practical control policies. The proposed method is evaluated in both single‐ramp and multiramp scenarios. Experimental results demonstrate that the agent can learn the queue spillback prevention strategies, and nearly eliminate ramp queue spillback without compromising control performance.
- 16 January 2025
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2025 (1)
Open AccessReinforcement Learning–Based Ramp Metering Strategy Considering Queue Management
This paper introduces an action replacement module for reinforcement learning (RL)–based ramp metering to address the issue of ramp queue spillback during the training process. Ramp queue spillback leads to significant impacts on the traffic efficiency of adjacent road networks, making it a critical concern in ramp control. Existing RL approaches often employ ramp states as reward functions to encourage agents to learn strategies that avoid queue overflow. However, due to the trial‐and‐error nature of RL, these methods frequently generate actions that cause queue spillback during training, posing challenges for real‐time online training in real‐world applications. To overcome this limitation, the proposed action replacement module utilizes the store‐and‐forward model to estimate a lower bound for ramp metering rates. By identifying and replacing actions that fail to meet this constraint, the strategy effectively prevents queue spillback. In addition, penalties are imposed on replaced actions to guide the agent in learning effective and practical control policies. The proposed method is evaluated in both single‐ramp and multiramp scenarios. Experimental results demonstrate that the agent can learn the queue spillback prevention strategies, and nearly eliminate ramp queue spillback without compromising control performance.
- 30 November 2012
- Published by AICIT in International Journal of Digital Content Technology and its Applications
- Vol. 6 (21) , 509-516
Warship Damage Assessment Method Using Analytical Hierarchy Process and Fuzzy Comprehensive Assessment
- 30 November 2012
- Published by AICIT in International Journal of Digital Content Technology and its Applications
- Vol. 6 (21) , 509-516
Warship Damage Assessment Method Using Analytical Hierarchy Process and Fuzzy Comprehensive Assessment
- 1 December 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 18 (01912216) , 199-204
Event-triggered output feedback control for networked control systems using passivity: Triggering condition and limitations
Most of the work on event-triggered control in the literature is based on static state-feedback controllers. In this paper, a dynamic output feedback based event-triggered control scheme is introduced for stabilization of Input Feed-forward Output Feedback Passive (IF-OFP) networked control systems (NCSs), which is a more general case compared with the passive and the OFP systems investigated in our previous work [20]. The triggering condition is derived based on the passivity theorem which allows us to characterize a large class of output feedback stabilizing controllers. We show that under the triggering condition derived in this paper, the control system is finite-gain ℒ 2 stable in the presence of bounded external disturbances. We provide some analysis on the inter-event time which reveals the difficulties of obtaining a common lower bound on the inter-event time when the full-state information of the plant is not used. Some challenges of applying event-triggered control to real time NCSs are also discussed.
- 1 December 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 18 (01912216) , 199-204
Event-triggered output feedback control for networked control systems using passivity: Triggering condition and limitations
Most of the work on event-triggered control in the literature is based on static state-feedback controllers. In this paper, a dynamic output feedback based event-triggered control scheme is introduced for stabilization of Input Feed-forward Output Feedback Passive (IF-OFP) networked control systems (NCSs), which is a more general case compared with the passive and the OFP systems investigated in our previous work [20]. The triggering condition is derived based on the passivity theorem which allows us to characterize a large class of output feedback stabilizing controllers. We show that under the triggering condition derived in this paper, the control system is finite-gain ℒ 2 stable in the presence of bounded external disturbances. We provide some analysis on the inter-event time which reveals the difficulties of obtaining a common lower bound on the inter-event time when the full-state information of the plant is not used. Some challenges of applying event-triggered control to real time NCSs are also discussed.
- 1 July 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 34 (19325517) , 1-7
Environmental effects evaluation of urban distribution network planning based on a comprehensive model
Based on the in-depth analysis of urban network's characteristics, a comprehensive model composed of an evaluation index system and a novel evaluation methodology is described for studying environmental effects that planning schemes might cause if they were implemented. The novel model focuses on various typical perspectives, such as pollution emissions, carbon emissions and environmental coordination into consideration in a quantitative way. Unlike traditional evaluation approaches which largely depend on the preference of decision makers, the proposed decision-making approach integrates multiple attribute tradeoff analysis with fuzzy satisfying analysis. In this way, it is capable of determining the most robust plan in an objective sense. The simulation results of a real urban network in China are presented and discussed, illustrating the suitability of the proposed model to the urban power grid planning evaluation and its superiority in operation. The model provides useful guidance for the urban power grid going towards an eco-friendly condition in the future.
- 1 July 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 34 (19325517) , 1-7
Environmental effects evaluation of urban distribution network planning based on a comprehensive model
Based on the in-depth analysis of urban network's characteristics, a comprehensive model composed of an evaluation index system and a novel evaluation methodology is described for studying environmental effects that planning schemes might cause if they were implemented. The novel model focuses on various typical perspectives, such as pollution emissions, carbon emissions and environmental coordination into consideration in a quantitative way. Unlike traditional evaluation approaches which largely depend on the preference of decision makers, the proposed decision-making approach integrates multiple attribute tradeoff analysis with fuzzy satisfying analysis. In this way, it is capable of determining the most robust plan in an objective sense. The simulation results of a real urban network in China are presented and discussed, illustrating the suitability of the proposed model to the urban power grid planning evaluation and its superiority in operation. The model provides useful guidance for the urban power grid going towards an eco-friendly condition in the future.
- 1 June 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 07431619,p. 208-213
Passivity-based output synchronization of networked Euler-Lagrange systems subject to nonholonomic constraints
In this paper, we study the output synchronization problem of networked Euler-Lagrange(EL) systems subject to nonholonomic constraints. An EL system subject to nonholonomic constraints can be input-output linearized if a proper decoupling matrix can be found, and the linearized form is equivalent to a double integrator. Although a double integrator is not a passive system, with proper design of the control law and some coordinate transformation, we are able to obtain a new state-space representation of the EL system which is a linear passive system. The underlying assumption is that the communication graph is bidirectional and strongly connected. To deal with time-varying communication delays among the interconnected agents, we embed the scattering transformation into our proposed setup and show that output synchronization can be achieved in this case as well.
- 1 June 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 07431619,p. 208-213
Passivity-based output synchronization of networked Euler-Lagrange systems subject to nonholonomic constraints
In this paper, we study the output synchronization problem of networked Euler-Lagrange(EL) systems subject to nonholonomic constraints. An EL system subject to nonholonomic constraints can be input-output linearized if a proper decoupling matrix can be found, and the linearized form is equivalent to a double integrator. Although a double integrator is not a passive system, with proper design of the control law and some coordinate transformation, we are able to obtain a new state-space representation of the EL system which is a linear passive system. The underlying assumption is that the communication graph is bidirectional and strongly connected. To deal with time-varying communication delays among the interconnected agents, we embed the scattering transformation into our proposed setup and show that output synchronization can be achieved in this case as well.