Renxin Zhong

Renxin Zhong


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
5 May 2022 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
SWShimin Wang
Shimin Wang
HZHongwei Zhang
Hongwei Zhang
SBSimone Baldi
Simone Baldi
RZRenxin Zhong
Renxin Zhong
This article studies the leaderless consensus problem of heterogeneous multiple networked Euler–Lagrange systems subject to persistent disturbances with unknown constant biases, amplitudes, initial phases, and frequencies. The main characteristic of this study is that none of the agents has information of a common reference model or of a common reference trajectory. Therefore, the agents must simultaneously and in a distributed way: achieve consensus to a common reference model (group model); achieve consensus to a common reference trajectory; and reject the unknown disturbances. We show that this is possible via a suitable combination of techniques of distributed “observers,” internal model principle and adaptive regulation. The proposed design generalizes recent results on group model learning, which have been studied for linear agents over undirected networks. In this article, group model learning is achieved for Euler–Lagrange dynamics over directed networks in the presence of persistent unknown disturbances.

2 March 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
ELEnming Liang
Enming Liang
KWKexin Wen
Kexin Wen
WLWilliam H. K. Lam
William H. K. Lam
ASAgachai Sumalee
Agachai Sumalee
RZRenxin Zhong
Renxin Zhong
Balancing the supply and demand for ride-sourcing companies is a challenging issue, especially with real-time requests and stochastic traffic conditions of large-scale congested road networks. To tackle this challenge, this article proposes a robust and scalable approach that integrates reinforcement learning (RL) and a centralized programming (CP) structure to promote real-time taxi operations. Both real-time order matching decisions and vehicle relocation decisions at the microscopic network scale are integrated within a Markov decision process framework. The RL component learns the decomposed state-value function, which represents the taxi drivers’ experience, the off-line historical demand pattern, and the traffic network congestion. The CP component plans nonmyopic decisions for drivers collectively under the prescribed system constraints to explicitly realize cooperation. Furthermore, to circumvent sparse reward and sample imbalance problems over the microscopic road network, this article proposed a temporal-difference learning algorithm with prioritized gradient descent and adaptive exploration techniques. A simulator is built and trained with the Manhattan road network and New York City yellow taxi data to simulate the real-time vehicle dispatching environment. Both centralized and decentralized taxi dispatching policies are examined with the simulator. This case study shows that the proposed approach can further improve taxi drivers’ profits while reducing customers’ waiting times compared to several existing vehicle dispatching algorithms.

28 June 2022 in Transportation Research Part C: Emerging Technologies
Verified
Journal Article
Closed access
CCC. Chen
C. Chen
YHY.P. Huang
Y.P. Huang
WLW.H.K. Lam
W.H.K. Lam
TPT.L. Pan
T.L. Pan
SHShu-Chien Hsu
Shu-Chien Hsu
RZRenxin Zhong
Renxin Zhong

7 February 2019 in Transportmetrica A: Transport Science
Verified
Journal Article
Closed access
TPTianlu Pan
Tianlu Pan
WLWilliam H. K. Lam
William H. K. Lam
ASAgachai Sumalee
Agachai Sumalee
RZRenxin Zhong
Renxin Zhong
In view of the advantages and a promising market prospect of the emerging connected automated vehicles (CAVs), it will be very likely that the roadway is shared by CAVs and RHVs in the near future. To support traffic control design, this paper develops a multiclass multilane cell transmission model (CTM) to simulate traffic flow dynamics mixed with CAVs and RHVs by capturing the interaction between the two vehicle classes. First, headway distributions and variations in the fundamental diagram with respect to different penetration rates of CAVs are quantified. Then, the minimum headway acceptance criteria are determined for the lane changing (LC) maneuvers proposed by CAVs and RHVs with consideration on drivers’ anticipation. Finally, the cell-lane-specific multiclass flow conservation law is developed to propagate traffic flow and density considering the vehicle LC maneuvers. Numerical simulations explore the potential operational capacity increase, delay reduction, and traffic flow smoothing under several penetration scenarios.

12 October 2022 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
SJSimin Jiang
Simin Jiang
TPTianlu Pan
Tianlu Pan
RZRenxin Zhong
Renxin Zhong
CCCan Chen
Can Chen
XLXin-An Li
Xin-An Li
SWShimin Wang
Shimin Wang
This paper investigates the collaborative control of vehicular traffic for a signal-free intersection. The traffic under consideration is mixed with connected autonomous vehicles (CAVs) and human-piloted vehicles with advanced driver assistance systems (ADAS). The proposed collaborative control is of two levels. At the upper level, the objective is to minimize total delay via platoon control and dynamic priority control of conflicting movements. We formulate the platoon coordination of mixed traffic as a mixed-integer linear programming problem (MILP). This MILP determines whether adjacent vehicles will form a platoon and prioritize any two conflicting movements subject to lateral safety and rear-end safety constraints. At the lower level, we propose an eco-driving strategy to minimize the energy consumption by optimizing the speed profile of the platoon leading vehicles subject to the dynamic priority control from the upper level, i.e., the entry time to the merging zone. We deduce an analytical solution to the eco-driving problem using optimal control theory. Compared with existing benchmarks, such as the first-come-first-served policy, the proposed method outperforms the state-of-the-art controllers in reducing the total delay. Sensitivity analysis regarding the penetration rate of CAVs shows that substantial improvements can be achieved even at low to medium penetration rates of CAVs.

1 July 2024 in Transportation Science
Verified
Journal Article
Closed access
CCCan Chen
Can Chen
NGNikolas Geroliminis
Nikolas Geroliminis
RZRenxin Zhong
Renxin Zhong
Macroscopic fundamental diagrams (MFDs) have been widely adopted to model the traffic flow of large-scale urban networks. Coupling perimeter control and regional route guidance (PCRG) is a promising strategy to decrease congestion heterogeneity and reduce delays in large-scale MFD-based urban networks. For MFD-based PCRG, one needs to distinguish between the dynamics of (a) the plant that represents reality and is used as the simulation tool and (b) the model that contains easier-to-measure states than the plant and is used for devising controllers, that is, the model-plant mismatch should be considered. Traditional model-based methods (e.g., model predictive control (MPC)) require an accurate representation of the plant dynamics as the prediction model. However, because of the inherent network uncertainties, such as uncertain dynamics of heterogeneity and demand disturbance, MFD parameters could be time-varying and uncertain. Conversely, existing data-driven methods (e.g., reinforcement learning) do not consider the model-plant mismatch and the limited access to plant-generated data, for example, subregional OD-specific accumulations. Therefore, we develop an iterative adaptive dynamic programming (IADP)-based method to address the limited data source induced by the model-plant mismatch. An actor-critic neural network structure is developed to circumvent the requirement of complete information on plant dynamics. Performance comparisons with other PCRG schemes under various scenarios are carried out. The numerical results indicate that the IADP controller trained with a limited data source can achieve comparable performance with the “benchmark” MPC approach using perfect measurements from the plant. The results also validate the IADP’s robustness against various uncertainties (e.g., demand noise, MFD error, and trip distance heterogeneity) when minimizing the total time spent in the urban network. These results demonstrate the great potential of the proposed scheme in improving the efficiency of multiregion MFD systems. Funding: The work was jointly funded by the National Natural Science Foundation of China under [Grant 72071214] (R. Zhong), the Dit4Tram project from the European Union’s Horizon 2020 Research and Innovation Programme under [Grant 953783] (N. Geroliminis), and the Research Student Attachment Programme of The Hong Kong Polytechnic University (C. Chen). Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2023.0091 .