Directed by Michel Bierlaire, the Transport and Mobility Laboratory is active in modeling, optimization and simulation of transportation systems, with a specific emphasis on the mobility of individuals.

This webpage contains the academic output of the laboratory. We are committed to open science. Links to the specific documents are available. Also, if you click on the bibtex button next to a reference, it gives you access to the reference in bibtex format, that you can copy and paste to your bibliography file.

• Prof. Domokos Esztergar-Kiss,
  • Mobility as a service in theory and practice
  • May 20, 2025, 14:30
  • bio
    Domokos Esztergár-Kiss is a senior lecturer at Budapest University of Technology and Economics (BME) and international project coordinator of the Faculty of Transportation Engineering and Vehicle Engineering. His main research topics are the optimization of multimodal travel chains for passengers, the development of Mobility as a Service related solutions, and the establishment of workplace mobility plans for promoting sustainable commuting. He has published 85 papers in leading journals with Impact Factor. He was the main organizer of several international conferences (e.g. MT-ITS 2015, EWGT 2017, hEART 2019, and TRA 2026) and is involved in several Horizon 2020 projects, Interreg projects, and COST Actions (e.g. MoveCit, LinkingDanube, MaaS4EU, Electric travelling, BE OPEN, RegiaMobil, OJP4Danube, metaCCAZE). Moreover, he was a Fulbright scholar at the University of California, Davis in 2021, he was the chair of IEEE HS YP, and he is a council member of AET and ECTRI.
  • abstract
    An emerging trend towards seamless mobility is the integration of on-demand modes into public transport leads to the Mobility-as-a-Service (MaaS) concept. MaaS is a user-centric, intelligent mobility distribution model, in which user needs are met via a single platform and are offered by a service provider, the mobility operator. Presently there are no established frameworks and quantifiable evidence about MaaS costs and benefits, users’ needs, as well as its influence on travel patterns and car ownership of various user groups. The main goal of MaaS4EU project is to provide quantifiable evidence, frameworks and tools, to remove the barriers and enable a cooperative and interconnected EU single transport market for the MaaS concept, by addressing challenges at 4 levels: business, end-users, technology and policy. This will be achieved by defining sustainable business models that support the cooperation across transport stakeholders, understanding user needs and choices, implementing the required technological infrastructure (MaaS mobility hub) and identifying the enabling policy and regulatory frameworks. The project will provide quantifiable evidence about MaaS costs and benefits in real-life, complementary pilot cases, demonstrating the concept in urban, intercity and cross-border trips. The focus will be on the pilot realized in Budapest.

• Action versus Inaction facing Climate Change: the Symposium, Hotel Europe, Zinal, Jun 01, 2025 - Jun 03, 2025
  • Role: Chair

2025

• Ilinov P., Matveenko A., Tsakas E., Mark V. (2025). Sequential Search with Flexible Information. Report TRANSP-OR 250331bibtex

  
  @TechReport{IlinMatvSharTsakVoor25,
    author = {Pavel Ilinov and Andrei Matveenko and Elias Tsakas and Voorneveld Mark},
    title = {Sequential Search with Flexible Information},
    institution = {Transport and Mobility Laboratory, Ecole Polytechnique F\'ed\'erale de Lausanne},
    year = {2025},
    type = {Technical Report},
    number = {TRANSP-OR 250331},
    address = {Lausanne, Switzerland}}}
  

• Ricard L., Desaulniers G., Lodi A., Rousseau L. (2025). Chance-constrained battery management strategies for the electric bus scheduling problem. Report arXiv:2503.19853bibtex

  
  @TechReport{RicaDesLodiRouss25,
    author = {L\'ea Ricard and Guy Desaulniers and Andrea Lodi and Louis-Martin Rousseau},
    title = {Chance-constrained battery management strategies for the
  
  electric bus scheduling problem},
    institution = {Transport and Mobility Laboratory, Ecole Polytechnique F\'ed\'erale de Lausanne},
    year = {2025},
    type = {Technical Report},
    number = {arXiv:2503.19853},
    address = {Lausanne, Switzerland}}}
  

• Haering T., Bierlaire M. (2025). BHAMSLE: A Breakpoint Heuristic Algorithm for Maximum Simulated Likelihood Estimation of Advanced Discrete Choice Models . Report TRANSP-OR 250404bibtex

  
  @TechReport{HaerBier2025,
    author = {Tom Haering and Michel Bierlaire},
    title = {BHAMSLE: A Breakpoint Heuristic Algorithm for Maximum Simulated Likelihood Estimation of Advanced Discrete Choice Models
  
  },
    institution = {Transport and Mobility Laboratory, Ecole Polytechnique F\'ed\'erale de Lausanne},
    year = {2025},
    type = {Technical Report},
    number = {TRANSP-OR 250404},
    address = {Lausanne, Switzerland}}}
  

2024

• Haering T., Legault R., Torres F., Bierlaire M. (2024). Heuristics and Exact Algorithms for Choice-Based Capacitated and Uncapacitated Continuous Pricing. Report TRANSP-OR 240905bibtex

  
  @TechReport{HaerLegaTorrBier2024,
    author = {Tom Haering and Robin Legault and {Fabian Alejandro} Torres and Michel Bierlaire},
    title = {Heuristics and Exact Algorithms for Choice-Based Capacitated and Uncapacitated Continuous Pricing},
    institution = {Transport and Mobility Laboratory, Ecole Polytechnique F\'ed\'erale de Lausanne},
    year = {2024},
    type = {Technical Report},
    number = {TRANSP-OR 240905},
    address = {Lausanne, Switzerland}}}
  

• Torres F., Gendreau M., Rei W. (2024). Pricing Routes: Compensation of Crowd-Drivers. Report TRANSP-OR 240717bibtex

  
  @TechReport{Torres2024_0,
    author = {{Fabian Alejandro} Torres and Michel Gendreau and Walter Rei},
    title = {Pricing Routes: Compensation of Crowd-Drivers},
    institution = {Transport and Mobility Laboratory, Ecole Polytechnique F\'ed\'erale de Lausanne},
    year = {2024},
    type = {Technical Report},
    number = {TRANSP-OR 240717},
    address = {Lausanne, Switzerland}}}
  

2025

• Ilinov P., Matveenko A., Rastislav R., Rava d. Efficient Social Defaults March 21, 2025. THEEM 2025, Thurgau Institute of Economics at the University of Konstanz, Kreuzlingen, Switzerland.bibtex

  
  @Misc{Ilinov_Kreuz2025,
    author = {Pavel Ilinov and Andrei Matveenko and Rehak Rastislav and {de Silveira} Rava},
    title = {Efficient Social Defaults},
    howpublished = {\url{https://transp-or.epfl.ch/documents/talks/Ilinov_Kreuz2025.pdf}},
    year = {2025},
    note = {Presented at THEEM 2025, Thurgau Institute of Economics at the University of Konstanz, Kreuzlingen, Switzerland}}}
  

• Haering T., Bierlaire M. BHAMSLE: A Breakpoint Heuristic Algorithm for Maximum Simulated Likelihood Estimation of Advanced Discrete Choice Models February 13, 2025. 3rd EPFL Symposium on Transportation Research, EPFL, Barcelona, Spain.bibtex

  
  @Misc{2025HaeringBarc,
    author = {Tom Haering and Michel Bierlaire},
    title = {BHAMSLE: A Breakpoint Heuristic Algorithm for Maximum Simulated Likelihood Estimation of Advanced Discrete Choice Models},
    howpublished = {\url{https://transp-or.epfl.ch/documents/talks/2025HaeringBarc.pdf}},
    year = {2025},
    note = {Presented at 3rd EPFL Symposium on Transportation Research, EPFL, Barcelona, Spain}}}
  

• Kukic M., Bierlaire M. Gibbs Sampler for Generating Longitudinal Synthetic Populations February 13, 2025. 3rd EPFL Symposium on Transportation Research, EPFL, Barcelona, Spain.bibtex

  
  @Misc{2025KukicBarc,
    author = {Marija Kukic and Michel Bierlaire},
    title = {Gibbs Sampler for Generating Longitudinal Synthetic Populations},
    howpublished = {\url{https://transp-or.epfl.ch/documents/talks/2025KukicBarc.pdf}},
    year = {2025},
    note = {Presented at 3rd EPFL Symposium on Transportation Research, EPFL, Barcelona, Spain}}}
  

• Rezvany N., Hillel T., Bierlaire M. A strategic dynamic model for integrating housing and transport interactions February 13, 2025. 3rd EPFL Symposium on Transportation Research, EPFL, Barcelona, Spain.bibtex

  
  @Misc{2025Rezvany_Barc,
    author = {Negar Rezvany and Tim Hillel and Michel Bierlaire},
    title = {A strategic dynamic model for integrating housing and transport interactions},
    howpublished = {\url{https://transp-or.epfl.ch/documents/talks/2025Rezvany_Barc.pdf}},
    year = {2025},
    note = {Presented at 3rd EPFL Symposium on Transportation Research, EPFL, Barcelona, Spain}}}
  

2024

• Kukic M., Bierlaire M. Synthetic populations and activity-based models: a dynamic perspective December 12, 2024. Activity Based Model Symposium, TU Munich, Raitenhaslach, Germany.bibtex

  
  @Misc{2024munich,
    author = {Marija Kukic and Michel Bierlaire},
    title = {Synthetic populations and activity-based models: a dynamic perspective},
    howpublished = {\url{https://transp-or.epfl.ch/documents/talks/2024munich.pdf}},
    year = {2024},
    note = {Presented at Activity Based Model Symposium, TU Munich, Raitenhaslach, Germany}}}
  

2025

• Cortes Balcells C., Krueger R., Bierlaire M. (2025). Modeling Disease Spread: Integrating Mobility, Awareness, and Behavior. Transportationabstract

  The COVID-19 pandemic has underscored the vital link between epidemiology and transportation, particularly in the context of activity-travel behavior. While much research has explored the role of mobility in disease spread, there is a notable gap in understanding how individual behavioral choices, especially regarding testing, influence these dynamics. This paper introduces the Mobility-Aware Behavioral Epidemiological Model (MABEM), an innovative framework that integrates activity-based modeling with latent variables to more accurately represent the impact of testing decisions on disease propagation. Using data from the canton of Vaud, Switzerland, our model simulates the interactions between individual behavior, mobility, and health status, revealing significant underreporting of infections and highlighting the crucial role of testing choices in shaping observed infection rates. The results suggest that testing behaviors vary significantly across different demographic groups and regions, influencing both individual activity patterns and overall disease spread. MABEM model proves to be computationally efficient and offers valuable insights for designing targeted public health interventions. Despite some limitations related to data availability, this research provides a comprehensive approach to understanding the interplay between mobility, individual behavior, and disease dynamics, offering new possibilities for more effective disease containment strategies.

  bibtex

  
  @Article{CortKrueBier25,
    author = {Cloe {Cortes Balcells} and Rico Krueger and Michel Bierlaire},
    title = {Modeling Disease Spread: Integrating Mobility, Awareness, and Behavior},
    journal = {Transportation},
    year = {2025},
    note = {Accepted on Mar 22, 2025}}}
  

• Atac S., Obrenovic N., Bierlaire M. (2025). Bike Sharing Systems: The Impact of Precise Trip Demand Forecasting on Operational Efficiency in Different City Structures . Journal of Cycling and Micromobility Research 3 (100058)abstract

  Increasing environmental concerns drive interest in sustainable solutions across various fields. Vehicle sharing systems such as one-way station-based bike sharing systems (BSSs) offer one such solution in transportation, although they pose operational challenges like vehicle imbalance. While many studies focus on optimizing rebalancing operations using trip demand forecasting, the added value of precise trip demand forecasting remains unexplored. This study assesses the added value of collecting detailed trip demand data and developing trip demand forecasting models. To achieve this, we create a simulation–optimization framework representing a city BSS in operation during the day. We use a discrete-event simulator representing the system dynamics and an enhanced mathematical model optimizing the rebalancing operations. We employ clustering in the optimization module to manage larger case studies, dividing the problem into smaller sub-problems. Our computational experiments compare two main scenarios, perfect demand forecast and unknown future demand, as well as several intermediate scenarios where partial future trip demand information is available. These scenarios allow us to determine the trade-off between lost trip demand and rebalancing operations costs, assess demand forecasting benefits, and identify the budget’s upper limit for precise trip demand forecasting. Subsequently, we conduct experiments on one synthetic (35 stations) and four real-life case studies, ranging from small systems (21 and 298 stations) to large systems (681 and 1361 stations). Results reveal that precise trip demand forecasting has varying impacts on small and large BSSs, with larger BSSs benefiting the most without significantly increasing the rebalancing operations costs. We also observe that the most significant improvements occur between 0% and 40% trip demand knowledge while beyond 60%, the increase in returns diminishes. The findings of this study offer valuable insights for operators in enhancing service levels and optimizing resource allocation.

  bibtex

  
  @Article{AtacObreBier25,
    author = {Selin Atac and Nikola Obrenovic and Michel Bierlaire},
    title = {Bike Sharing Systems: The Impact of Precise Trip Demand Forecasting on Operational Efficiency in Different City Structures 
  
  },
    journal = {Journal of Cycling and Micromobility Research},
    year = {2025},
    volume = {3},
    number = {100058},
    DOI = {10.1016/j.jcmr.2025.100058},
    note = {Accepted on Jan 21, 2025}}}
  

• Ahmed S., Fountas G., Lurkin V., Anastasopoulos P., Zhang Y., Bierlaire M., Mannering F. (2025). The State of Urban Air Mobility Research: An Assessment of Challenges and Opportunities. IEEE Transactions on Intelligent Transportation Systems 26 (2):1375-1394bibtex

  
  @Article{AhmeFounLurkAnasZhanBierMann25,
    author = {{Sheikh Shahriar} Ahmed and Grigorios Fountas and Virginie Lurkin and Panagiotis Anastasopoulos and Yu Zhang and Michel Bierlaire and Fred Mannering},
    title = {The State of Urban Air Mobility Research: An Assessment of Challenges and Opportunities},
    journal = {IEEE Transactions on Intelligent Transportation Systems},
    year = {2025},
    volume = {26},
    number = {2},
    pages = {1375-1394},
    DOI = {10.1109/TITS.2024.3511453},
    note = {Accepted on Nov 28, 2024}}}
  

• Ortelli N., de Lapparent M., Varotto S., Bierlaire M. (2025). An integrated ordered logit and latent variable model for accident injury severity and risk-taking behavior. Transportation Research Part A: Policy and Practice 192 (104330)abstract

  This study presents a flexible model for risk-taking behavior and accident injury severity. It is specifically designed to evaluate the impact of Via Sicura, a Swiss road safety program, on the severity of accident outcomes. Our proposed model treats the risk-taking behavior of each driver as a latent variable that depends on a number of socioeconomic and contextual factors, and whose manifestation can be measured by means of behavioral indicators. The aggregated risk, a central feature of our framework, represents the combined latent risk-taking behaviors among all drivers within an accident and is successfully identified as explanatory of the severity of injuries sustained by all individuals involved. Our findings reveal that Via Sicura’s repressive measures successfully deter risk-taking behavior among drivers, preventing an estimated 63 fatal, 876 major and 2,303 minor injuries over a ten-year period.

  bibtex

  
  @Article{OrteDelaVaroBier24,
    author = {Nicola Ortelli and Matthieu {de Lapparent} and Silvia Varotto and Michel Bierlaire},
    title = {An integrated ordered logit and latent variable model for accident injury severity and risk-taking behavior},
    journal = {Transportation Research Part A: Policy and Practice},
    year = {2025},
    volume = {192},
    number = {104330},
    DOI = {10.1016/j.tra.2024.104330},
    note = {Accepted on Nov 15, 2024}}}
  

• Martin-Baos J., Garcia-Rodenas R., Rodriguez-Benitez L., Bierlaire M. (2025). Scalable Kernel Logistic Regression with Nystr�m Approximation: Theoretical Analysis and Application to Discrete Choice Modelling. Neurocomputing 617 (7):128975abstract

  The application of kernel-based Machine Learning (ML) techniques to discrete choice modelling using large datasets often faces challenges due to memory requirements and the considerable number of parameters involved in these models. This complexity hampers the efficient training of large-scale models. This paper addresses these problems of scalability by introducing the Nyström approximation for Kernel Logistic Regression (KLR) on large datasets. The study begins by presenting a theoretical analysis in which: i) the set of KLR solutions is characterised, ii) an upper bound to the solution of KLR with Nyström approximation is provided, and finally iii) a specialisation of the optimisation algorithms to Nyström KLR is described. After this, the Nyström KLR is computationally validated. Four landmark selection methods are tested, including basic uniform sampling, a k-means sampling strategy, and two non-uniform methods grounded in leverage scores. The performance of these strategies is evaluated using large-scale transport mode choice datasets and is compared with traditional methods such as Multinomial Logit (MNL) and contemporary ML techniques. The study also assesses the efficiency of various optimisation techniques for the proposed Nyström KLR model. The performance of gradient descent, Momentum, Adam, and L-BFGS-B optimisation methods is examined on these datasets. Among these strategies, the k-means Nyström KLR approach emerges as a successful solution for applying KLR to large datasets, particularly when combined with the L-BFGS-B and Adam optimisation methods. The results highlight the ability of this strategy to handle datasets exceeding 200,000 observations while maintaining robust performance.

  bibtex

  
  @Article{MartGarcRodrBier24,
    author = {Jos\'e Martin-Baos and Ricardo Garcia-Rodenas and Luis Rodriguez-Benitez and Michel Bierlaire},
    title = {Scalable Kernel Logistic Regression with Nystr\"om Approximation: Theoretical Analysis and Application to Discrete Choice Modelling},
    journal = {Neurocomputing},
    year = {2025},
    volume = {617},
    number = {7},
    pages = {128975},
    DOI = {10.1016/j.neucom.2024.128975},
    note = {Accepted on Nov 14, 2024}}}