About

Maria Laura Delle Monache is an Assistant Professor in the Department of Civil and Environmental Engineering at UC Berkeley. Her research lies at the intersection of transportation engineering, mathematics, and control theory, with a focus on understanding the implications of technology on transportation systems. She is particularly interested in building mathematical models and control strategies to assess how new vehicular technologies impact traffic congestion, traffic emissions, and access to transport. Prior to her current position, she was a research scientist at Inria in Grenoble, France (2016-2021) and a Postdoctoral fellow at Rutgers University - Camden in the USA (2014-2016). She received her Ph.D. in applied mathematics from the University of Nice-Sophia Antipolis, France, in 2014, along with a M.Sc. in Mathematical Engineering from the University of L'Aquila (Italy) and the University of Hamburg (Germany), and a B.Sc. in Industrial Engineering from the University of L'Aquila. Dr. Delle Monache’s work involves building mathematical models and control strategies to evaluate the impact of vehicular technology on traffic flow, safety, and energy consumption. She has received multiple awards, including the 2024 IEEE Intelligent Transportation Systems Society (ITSS) Institutional Lead Award, the 2024 ITS Faculty of the Year, the 2023 IEEE Technical Committee on Cyber-Physical Systems (TCCPS) mid-career award, and the 2023 IEEE ITS Society Young Researcher/Engineer Award.

Research topics

• Artificial Intelligence
• Computer Science
• Machine Learning
• Simulation
• Mathematics

Selected publications

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

  ArXiv.org · 2026-01-10

  articleOpen access

  We present a neural network-based method for learning scalar hyperbolic conservation laws. Our method replaces the traditional numerical flux in finite volume schemes with a trainable neural network while preserving the conservative structure of the scheme. The model can be trained both in a supervised setting with efficiently generated synthetic data or in an unsupervised manner, leveraging the weak formulation of the partial differential equation. We provide theoretical results that our model can perform arbitrarily well, and provide associated upper bounds on neural network size. Extensive experiments demonstrate that our method often outperforms efficient schemes such as Godunov's scheme, WENO, and Discontinuous Galerkin for comparable computational budgets. Finally, we demonstrate the effectiveness of our method on a traffic prediction task, leveraging field experimental highway data from the Berkeley DeepDrive drone dataset.

  PublisherOA PDF

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

  arXiv (Cornell University) · 2026-01-10

  preprintOpen access

  We present a neural network-based method for learning scalar hyperbolic conservation laws. Our method replaces the traditional numerical flux in finite volume schemes with a trainable neural network while preserving the conservative structure of the scheme. The model can be trained both in a supervised setting with efficiently generated synthetic data or in an unsupervised manner, leveraging the weak formulation of the partial differential equation. We provide theoretical results that our model can perform arbitrarily well, and provide associated upper bounds on neural network size. Extensive experiments demonstrate that our method often outperforms efficient schemes such as Godunov's scheme, WENO, and Discontinuous Galerkin for comparable computational budgets. Finally, we demonstrate the effectiveness of our method on a traffic prediction task, leveraging field experimental highway data from the Berkeley DeepDrive drone dataset.

  PublisherDOI

• Optimal-Velocity-Based Car-Following Model With Control Lyapunov-Barrier Functions

  IEEE Control Systems Letters · 2026-01-01

  articleSenior author
  PublisherDOI

• From Links to Networks: A Data-Driven, Physics-Informed Koopman Framework for Traffic Networks

  2025-11-18

  articleSenior author

  Modern transportation systems are high-dimensional, non-linear, and subject to unpredictable disturbances, making real-time forecasting in large freeway networks especially challenging. This paper presents a data-driven framework that integrates Koopman Mode Decomposition (KMD) with physics-based preprocessing using the Cell Transmission Model (CTM) to enable interpretable network forecasting. We apply this framework to high-resolution traffic data from the San Jose metropolitan area, specifically focusing on three primary corridors: the Downtown Loop, Mid Corridors, and Outer Corridors. CTM enforces flow conservation and capacity limits across exchange zones, consistent with Daganzo's theory, enabling realistic congestion propagation. These physically consistent traffic states allow KMD to extract key spatiotemporal modes reflecting daily traffic rhythms and bottlenecks. The method achieves mean absolute error (MAE) below 2 mph and over 90% accuracy during peak hours, yielding reliable short-term forecasts under congested conditions. Validated using Mobiliti data, the framework is generalizable to other simulators or real-world sources. Overall, this approach supports physics-informed forecasting for multi-segment urban traffic networks and integration with connected and automated vehicle data streams.

  PublisherDOI

• Reinforcement Learning-Based Oscillation Dampening: Scaling Up Single-Agent Reinforcement Learning Algorithms to a 100-Autonomous-Vehicle Highway Field Operational Test

  IEEE Control Systems · 2025-01-30 · 4 citations

  articleOpen access

  In this article, we explore the technical details of the reinforcement learning (RL) algorithms that were deployed in the largest field test of automated vehicles designed to smooth traffic flow in history as of 2023, uncovering the challenges and breakthroughs that come with developing RL controllers for automated vehicles. We delve into the fundamental concepts behind RL algorithms and their application in the context of self-driving cars, discussing the developmental process from simulation to deployment in detail, from designing simulators to reward function shaping. We present the results in both simulation and deployment, discussing the flow-smoothing benefits of the RL controller. From understanding the basics of Markov decision processes to exploring advanced techniques such as deep RL, our article offers a comprehensive overview and deep dive of the theoretical foundations and practical implementations driving this rapidly evolving field. We also showcase real-world case studies and alternative research projects that highlight the impact of RL controllers in revolutionizing autonomous driving. From tackling complex urban environments to dealing with unpredictable traffic scenarios, these intelligent controllers are pushing the boundaries of what automated vehicles can achieve. Furthermore, we examine the safety considerations and hardware-focused technical details surrounding deployment of RL controllers into automated vehicles. As these algorithms learn and evolve through interactions with the environment, ensuring their behavior aligns with safety standards becomes crucial. We explore the methodologies and frameworks being developed to address these challenges, emphasizing the importance of building reliable control systems for automated vehicles.

  PublisherOA PDFDOI

• Evaluation of Mixed Traffic Modeling: Comparing Microscopic and Macroscopic Components

  2025-06-24

  articleSenior author

  As more and more Connected and Automated Vehicles enter public roads, Lagrangian traffic control strategies that leverage their presence to improve traffic flow are being proposed. As a result, the disparity in driving behaviours between different classes of vehicles is likely to continue increasing. Although numerous multi-class traffic models have been proposed, few adequately capture the complex interactions between vehicles with significantly different driving behaviour. In this work we study the simplest case of two-class traffic, with vehicle classes differentiated only by their desired speeds. The dynamics of this model are analysed in detail through solving the state discontinuity problems, where class traffic densities change, and interface discontinuity problems, where the reference speed of one class changes. The resulting traffic density profiles are compared with those arising from a corresponding microscopic model, incorporating both the car-following and lane-changing behaviour of vehicles of different classes. We show that the studied macroscopic model is congruent with an appropriately calibrated microscopic model.

  PublisherDOI

• Design, Preparation, and Execution of the 100-AV Field Test for the CIRCLES Consortium: Methodology and Implementation of the Largest Mobile Traffic Control Experiment to Date

  IEEE Control Systems · 2025-01-30 · 9 citations

  articleOpen access

  This article presents the comprehensive design, setup, execution, and evaluation of the MegaVanderTest (MVT) experiment conducted by the Congestion Impacts Reduction via CAV-in-the-Loop Lagrangian Energy Smoothing (CIRCLES) Consortium, which aimed to mitigate traffic congestion using partially autonomous vehicles (AVs) (see “Summary”). The experiment involved 100 vehicles on Nashville’s Interstate 24 (I-24) highway, utilizing various control algorithms to smooth stop-and-go traffic waves. The execution of the MVT experiment required a coordinated effort from multiple teams. This article details the meticulous planning process, the coordinated efforts of multiple teams, and the innovative use of a dynamic agent-based simulation framework for traffic evaluation. The contributions of this work include demonstrating and providing a detailed roadmap for large-scale live traffic experiments, illustrating the lessons learned from the MVT experiment, and introducing the other articles in this issue and their complementary relationship in the MVT experiment.

  PublisherOA PDFDOI

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

  IEEE Control Systems · 2025-01-30 · 8 citations

  articleOpen accessSenior author

  This article presents a novel hierarchical speed planning framework for variable speed limits in mixed-autonomy traffic environments, leveraging server-side macroscopic control and vehicle-side microscopic execution. The framework integrates real-time traffic state estimation (TSE) and reinforcement learning (RL)-based control to mitigate congestion and improve traffic flow. A TSE enhancement module combines macroscopic data from sources like INRIX with high-resolution observations from connected autonomous vehicles (CAVs), enabling predictive modeling to address latency and noise. The target speed design module employs kernel smoothing and a buffer zone strategy to optimize traffic density and flow around bottlenecks. The proposed system was validated in the largest open-road test to date with 100 CAVs, demonstrating an overall 8% traffic density decrease, with a specific decrease of 7% upstream, 10% downstream, and a 52% decrease during the congestion formation phase at bottlenecks.

  PublisherOA PDFDOI

• Macroscopic Modeling and Hierarchical Control of Battery Swapping Stations

  2025-12-09

  articleSenior author

  Battery swapping offers a compelling alternative to fast charging for large EV fleets. By decoupling charging from vehicle dwell time, battery swapping stations (BSS) can charge batteries slower, reducing grid strain and extending battery life, while enabling quick vehicle turnaround. In this work, we present a hierarchical control architecture for large-scale BSS that addresses the computational limits of conventional integer programming approaches. By adopting a macroscopic model that represents battery states as a continuous distribution, our method captures nonlinear battery dynamics without sacrificing tractability. In this framework, the upper level optimizes station power procurement in response to market prices, while the lower level enforces realistic charging constraints across hundreds of batteries. This design enables robust operation under stochastic customer arrivals, ensures high service quality, and ultimately maximizes BSS profit, offering a practically scalable solution for heavy-duty EV fleets.

  PublisherDOI

• Strategizing equitable transit evacuations: A data-driven reinforcement learning approach

  Transportation Research Part C Emerging Technologies · 2025-09-14 · 2 citations

  articleSenior authorCorresponding
  PublisherDOI

Frequent coauthors

• Paola Goatin

  Observatoire de la Côte d’Azur

  104 shared

• Benedetto Piccoli

  Rutgers, The State University of New Jersey

  93 shared

• Daniel B. Work

  84 shared

• Carlos Canudas de Wit

  Centre Inria de l'Université Grenoble Alpes

  75 shared

• Benjamin Seibold

  57 shared

• Paolo Frasca

  56 shared

• Raphael Stern

  University of Minnesota

  55 shared

• Jonathan Sprinkle

  Vanderbilt University

  50 shared

Awards & honors

• 2024 IEEE Intelligent Transportation Systems Society (ITSS)…
• 2024 ITS Faculty of the year
• 2023 IEEE Technical committee on cyber-physical systems (TCC…
• 2023 IEEE Intelligent Transportation Systems Society (ITSS)…