Research

2026

1. SIAM

   Supervised and Unsupervised Neural Network Solver for First Order Hyperbolic Nonlinear PDEs

   Zhe Fu^*†, Zakaria Baba^*, Alexandre M. Bayen, and 6 more authors

   SIAM Journal on Numerical Analysis, 2026

   Under Review, *Equal First Author, †Corresponding Author

   Abs

   We develop neural network solvers for first-order hyperbolic nonlinear partial differential equations using both supervised and unsupervised learning approaches.

2. TRB

   Unsupervised Anomaly Detection in Multi-agent Trajectory Prediction via Transformer-based Models

   Qing Lyu, Zhe Fu^†, and Alexandre M. Bayen

   In Proceedings of the Transportation Research Board Annual Meeting, 2026

   Under Review, †Corresponding Author

   Abs

   We develop transformer-based models for unsupervised anomaly detection in multi-agent trajectory prediction.

2025

1. CDC

   Position and Speed Estimation Using Deep Learning-based KKL Observer in Mixed Autonomy Traffic Systems

   Yasmine Marani, Zhe Fu, Ibrahima N’Doye, and 3 more authors

   In Proceedings of the IEEE Conference on Decision and Control, 2025

   Oral presentation

   Abs

   We develop a deep learning-based KKL observer for position and speed estimation in mixed autonomy traffic systems.

2. NeuS

   Neural Network-Based Solvers for Hyperbolic Conservation Laws: Supervised vs. Unsupervised Learning, and Applications to Traffic Modeling

   Zhe Fu^*, Alexi Canesse^*, Nathan Lichtlè^*, and 4 more authors

   In Proceedings of the 2nd International Conference on Neuro-symbolic Systems, 2025

   Oral presentation, *Equal contribution

   Abs

   We compare supervised and unsupervised learning approaches for neural network-based solvers of hyperbolic conservation laws in traffic modeling.

3. ACC

   Pareto Control Barrier Function for Inner Safe Set Maximization Under Input Constraints

   Xiaoyang Cao, Zhe Fu^†, and Alexandre M. Bayen

   In Proceedings of the American Control Conference, 2025

   Oral presentation, †Corresponding author

   Abs

   We develop Pareto control barrier functions for maximizing inner safe sets under input constraints in control systems.

4. NeurIPS

   (U)NFV: Supervised and Unsupervised Neural Finite Volume Methods for Solving Hyperbolic PDEs

   Zhe Fu^*, Nathan Lichtlè^*, Alexi Canesse^*, and 3 more authors

   In Proceedings of the Annual Conference on Neural Information Processing Systems, 2025

   Under Review, *Equal First Author

   Abs

   We present supervised and unsupervised neural finite volume methods for solving hyperbolic partial differential equations.

2024

1. TR-C

   Kernel-based Planning and Imitation Learning Control for Flow Smoothing in Mixed Autonomy Traffic

   Zhe Fu^†, Arwa Alanqary, Abdul Rahman Kreidieh, and 1 more author

   Transportation Research Part C: Emerging Technologies, 2024

   Accepted, †Corresponding Author

   Abs

   This paper presents a kernel-based planning and imitation learning control approach for flow smoothing in mixed autonomy traffic systems. The work won first place at the INFORMS Annual Meeting Poster Competition and was accepted by the 25th International Symposium on Transportation and Traffic Theory (ISTTT25).

2. IEEE-CSM

   Hierarchical Speed Planner for Automated Vehicles: A Framework for Lagrangian Variable Speed Limit in Mixed Autonomy Traffic

   Han Wang, Zhe Fu, Jonathan Lee, and 14 more authors

   IEEE Control Systems Magazine, 2024

   Accepted

   Abs

   We develop a hierarchical speed planning framework for automated vehicles operating in mixed autonomy traffic environments.

3. IEEE-CSM

   Traffic Smoothing via Connected & Automated Vehicles: A Modular, Hierarchical Control Design Deployed in a 100-cav Flow Smoothing Experiment

   Zhe Fu, and  others

   IEEE Control Systems Magazine, 2024

   Accepted

   Abs

   This paper presents a modular, hierarchical control design for traffic smoothing using connected and automated vehicles, deployed in a large-scale 100-CAV experiment.

4. VSD

   Validation and Calibration of Energy Models with Real Vehicle Data from Chassis Dynamometer Experiments

   Joy Carpio, Sulaiman Almatrudi, Nour Khoudari, and 5 more authors

   Vehicle System Dynamics, 2024

   Under Review

   Abs

   We validate and calibrate energy models using real vehicle data from chassis dynamometer experiments to improve accuracy and reliability.

5. ITSC

   Towards Understanding Worldwide Cross-cultural Differences in Implicit Driving Cues: Review, Comparative Analysis, and Research Roadmap

   Yongqi Dong, Chang Liu, Yiyun Wang, and 1 more author

   In Proceedings of the IEEE Intelligent Transportation Systems Conference, 2024

   Oral presentation

   Abs

   We analyze cross-cultural differences in implicit driving cues across different regions and propose a research roadmap for understanding these variations.

6. ISTTT

   Kernel-based Planning and Imitation Learning Control for Flow Smoothing in Mixed Autonomy Traffic

   Zhe Fu^†, Arwa Alanqary, Abdul Rahman Kreidieh, and 1 more author

   In Proceedings of the 25th International Symposium on Transportation and Traffic Theory, 2024

   Abs

   Conference version of our kernel-based planning and imitation learning control approach for mixed autonomy traffic flow smoothing.

7. TRB

   Hierarchical Reinforcement Learning for Scalable Lagrangian Variable Speed Limit in Mixed Autonomy Traffic

   Han Wang, Jonathan W. Lee, Zhe Fu, and 3 more authors

   In Proceedings of the Transportation Research Board 103rd Annual Meeting, 2024

   Abs

   We present a hierarchical reinforcement learning framework for implementing scalable Lagrangian variable speed limits in mixed autonomy traffic.

2023

1. IV

   Cooperative Driving for Speed Harmonization in Mixed-Traffic Environments

   Zhe Fu^†, Abdul Rahman Kreidieh, Han Wang, and 3 more authors

   In Proceedings of the IEEE Intelligent Vehicles Symposium, 2023

   Abs

   We develop cooperative driving strategies for speed harmonization in mixed-traffic environments with both human and automated vehicles.

2. TRB

   A Feedback Control Strategy for Traffic Flow Harmonization in Mixed-traffic Environments

   Zhe Fu^†, Abdul Rahman Kreidieh, and Alexandre M. Bayen

   In Proceedings of the Transportation Research Board 102nd Annual Meeting, 2023

   Abs

   We present a feedback control strategy for harmonizing traffic flow in mixed-traffic environments.

3. OR/MS

   Massive CAV Experiment in Nashville Pits Machine Learning against Traffic Jams

   Zhe Fu, Kara Manke, and Alexandre M. Bayen

   OR/MS Today, 2023

   Abs

   This article describes the massive connected autonomous vehicle experiment conducted in Nashville to test machine learning approaches against traffic congestion.

2022

1. ITSC

   Learning Energy-efficient Driving Behaviors by Imitating Experts

   Abdul Rahman Kreidieh, Zhe Fu, and Alexandre M. Bayen

   In Proceedings of the IEEE Intelligent Transportation Systems Conference, 2022

   Oral presentation

   Abs

   We develop a learning framework for energy-efficient driving by imitating expert driving behaviors.

2021

1. TR-D

   Evaluating Smart Charging Strategies using Real-world Data from Optimized Plugin Electric Vehicles

   Sierra I. Spencer, Zhe Fu, Elpiniki Apostolaki-losifidou, and 1 more author

   Transportation Research Part D: Transport and Environment, 2021

   Accepted

   Abs

   We evaluate smart charging strategies using real-world data from optimized plugin electric vehicles to improve charging efficiency and grid stability.

2. Energies

   Economic and Environmental Benefits for Electricity Grids from Spatiotemporal Optimization of EV Charging

   Soomin Woo, Zhe Fu, Elpiniki Apostolaki-losifidou, and 1 more author

   Energies, 2021

   Accepted

   Abs

   This work demonstrates the economic and environmental benefits of spatiotemporal optimization for electric vehicle charging on electricity grids.

2020

1. UC-ITS

   Streamlining Connected Automated Vehicle Test Data Collection and Evaluation in the Hardware-in-the-Loop Environment

   Zhe Fu, Hao Liu, and Xiao-Yun Lu

   2020

   Abs

   We present a framework for streamlining connected automated vehicle test data collection and evaluation in hardware-in-the-loop environments.