Research projects

Incorporating competitors' behavior in demand based optimization models
Incorporating competitors' behavior in demand based optimization modelsSwiss National Science Foundation

The starting point of this research project is the general framework developed in the SNF research project 200021_165636 entitled “Incorporating advanced behavioral models in mixed integer linear optimization”. The project aims at formulating explicitly the complex interaction between the supply and demand actors. We hypothesize that the decisions of supply actors (such as capacity, assortment, and price) are highly influenced by the decisions of other actors, through competition within the market. In this project, we will therefore explicitly consider multiple operators that compete for the same pool of customers. Each operator will take the supply-side decisions that optimize its performance function (e.g., maximization of revenue). Non-cooperative game theory is commonly used to model such oligopolistic competition. We plan to investigate how to integrate these games in the already developed framework. In this context, the objective will be to analyze the concept of equilibrium, that is, stationary states of the system where no actor has an incentive to change his/her decisions.

Sponsor: Swiss National Science Foundation. November 01, 2017-October 31, 2020. PI: Michel Bierlaire. PM: Virginie Lurkin. Research team: Stefano Bortolomiol


Design of a car-free city center: a fringe parking system with accelerated moving walkways
Design of a car-free city center: a fringe parking system with accelerated moving walkwaysEuropean Commission

This project is conducted on a fellowship "The EuroTech Postdoc Programme". A car-free city center is a valuable solution for decreasing traffic congestion and CO2 emissions, and improving active mobility and quality of life. To achieve these goals, one of the biggest challenges is the relocation of parking places scattered in the inner district, which cause cruising for available parking as well as car inflows. A possible solution is a “fringe parking” system, which groups parking into a limited number of spots on the border of the district. However, this may decrease the level of accessibility moving the parking away from the final destinations. The key idea of this research is to use “accelerated moving walkway” (AMW), a novel transport system, in combination with a fringe parking system to design a car-free city center with high accessibility. The goal of the research is to propose and identify the optimal configuration of a fringe parking system with AMWs, as a solution to city centers. The main methodologies are network design optimization and traffic assignment.

Sponsor: European Commission. October 01, 2018-September 30, 2020. PI: Michel Bierlaire. PM: Yuki Oyama. External collaboration: Constantinos Antoniou (TUM)


ACTIVITY BASED TRAVEL DEMAND FORECASTING
ACTIVITY BASED TRAVEL DEMAND FORECASTINGSwiss Federal Railways (SBB)

This research project aims to update and improve the microscopic activity-based demand model developed and maintained by SBB. Specifically the research intends to address the following questions: 1. Ownership of mobility instruments: Which metrics and specifications can be added to the current model, in order to improve its ability to forecast mid-and long-term ownership of mobility instruments? More specifically, how can the notion of accessibility be integrated to the current model to capture more complex mode interactions? 2. Mode choice model: Can a tour-based approach be used to model mode choice? In addition, how can the processes to estimate destination and mode choice (currently nested) be combined to generate results that are consistent with observed mobility behaviors at different time horizons (short, mid, and long-term)? 3. Tour and activity generation: How can the generation of tours and activity patterns be combined to allow modelling of joint decisions?

Sponsor: Swiss Federal Railways (SBB). March 01, 2019-March 01, 2020. PI: Michel Bierlaire. PM: Tim Hillel. Research team: Janody Pougala


Capacity building program in urban mobility and transportation
Capacity building program in urban mobility and transportationState Secretariat for Economic Affairs

The purpose of this project is to develop graduate curriculum in urban mobility and transportation. The relevant courses of this curriculum will be available in MOOC format. This program is a collaborative project between Kwame Nkrumah University of Science and Technology (KNUST) and Urban Transport Systems Laboratory (LUTS) and Transport and Mobility Laboratory (TRANSP-OR) at EPFL.

Sponsor: State Secretariat for Economic Affairs. September 01, 2016-September 01, 2019. PI: Michel Bierlaire. PMs: Yousef Maknoon, Riccardo Scarinci, Yuki Oyama. External collaboration: Kwame Nkrumah University of Science and Technology (KNUST) , LUTS


PAM Personal Autonomous Moving platforms
PAM Personal Autonomous Moving platformsSchindler

In this project, Schindler and TRANSP-OR imagine a revolution of urban mobility focused on pedestrians. The Personal Autonomous Moving (PAM) platforms are similar to hoverborads or segways, and move from a point A (origin) to a point B (destination) on their own and carry the user with minimum interaction. They are a “light” mode of transport that does not require large space or infrastructural investment for the installation. This innovative mode of transport is ideal for short distance trip in large pedestrian facilities such as university campuses, larger business districts and airports as well as city centers. A great advantage is the possibility to directly access elevators with PAM platforms. This could lead to a real three-dimensional mobility taking advantage of elevators already installed in buildings. A possible deployment of this system generates several scientific and technological challenges. TRANP-OR focuses on the research questions that are related to the algorithms and mathematical models used by decision support tools needed for the planning and operation of the system.

Sponsor: Schindler. November 15, 2018-May 14, 2019. PI: Michel Bierlaire. PM: Yuki Oyama. External collaboration: Schindler


Incorporating advanced behavioral models in mixed integer linear optimization
Incorporating advanced behavioral models in mixed integer linear optimizationSwiss National Science Foundation

Discrete choice models are used for detailed representation of the "demand". However, their complexity makes mathematical formulations highly non convex in the explanatory variables. On the other hand, Mixed Integer Linear Programs (MILP) are optimization problems with discrete variables that are used in many applications to design and configure the "supply". In this project, we propose a new modeling framework that allows to include any random utility model in a mixed integer optimization formulation. The heterogeneity of demand is captured within the general choice model framework and the offers are tailored in a way that is beneficial for users as wells as providers. The main objective of the project is to obtain a framework that is both general, so that it can be applied in many applications, and operational, so that it can be used in practice.

Sponsor: Swiss National Science Foundation. April 01, 2016-March 31, 2019. PI: Michel Bierlaire. PM: Shadi Sharif Azadeh. Research team: Meritxell Pacheco


TRANS-FORM: Smart transfers through unravelling urban form and travel flow dynamics
TRANS-FORM: Smart transfers through unravelling urban form and travel flow dynamicsThe Federal Department of the Environment, Transport, Energy and Communications (DETEC)

TRANS-FORM, a cooperation between universities, industrial partners, public authorities and private operators, will develop, implement and test a data driven decision making tool that will support smart planning, and proactive and adaptive operations. The objective of the project is to better understand transferring dynamics in multi-modal public transport systems and develop insights, strategies and methods to support decision makers in transforming public transport usage to a seamless travel experience by using smart data. The tool will integrate new concepts and methods of behavioral modelling, passenger flow forecasting and network state predictions into real-time operations. TRANS-FORM is funded under the European Commission Horizon 2020 ERA-NET program.

Sponsor: The Federal Department of the Environment, Transport, Energy and Communications (DETEC). March 03, 2016-March 03, 2019. PI: Michel Bierlaire. PMs: Shadi Sharif Azadeh, Riccardo Scarinci, Yuki Oyama. Research team: Nicholas Molyneaux, Nikola Obrenovic


Accessibility based optimization of educational infrastructure networks
Accessibility based optimization of educational infrastructure networksWorld Bank

The aim of this project is to propose a methodology to assess and optimize educational infrastructure networks based on accessibility. In 2014, the World Bank launched the Global Program for Safer Schools (GPSS) with a focus on integrating risk reduction considerations into education infrastructure policies and investments. The GPSS aims to boost and facilitate informed, large-scale investments for the safety and resilience of new and existing school infrastructure at risk from natural hazards, contributing to high-quality learning environments. Understanding accessibility of school infrastructure networks is an important element to optimize risk reduction interventions as well as to improve the quality and efficiency of the educational service. To support this goal, the Transportation and Mobility Laboratory proposes a methodology to assess and optimize educational infrastructure networks based on accessibility; and proposes solutions to improve the performance of educational infrastructure networks. In other words, researchers will evaluate the risks based on the school network, including parameters like transportation network, home location of the students, mobility patterns... They will then provide a methodology in order to help direct investments to reduce the risks in case of disaster.

Sponsor: World Bank. January 01, 2018-December 31, 2018. PI: Michel Bierlaire. PM: Riccardo Scarinci. External collaboration: EPFL-TRACE


Drive For You: a driving assistant tool to detecting pedestrians
Drive For You: a driving assistant tool to detecting pedestriansMINES ParisTech

This project aims to develop an onboard pedestrian tracking system to assist the driver detect them and, ultimately, to increase security. The project, with a duration of four years, will focus on pedestrians detection, tracking and trajectory prediction, and will be will be closely related to vehicle command strategies. The project is part of the automated driving research Chair "Drive for you" led by MINES ParisTech in partnership with French industrialists and three prestigious academic institutions the Ecole Polytechnique Fédérale de Lausanne EPFL (Switzerland), the University of Shanghai Jiao Tong (China) and the University of Berkeley (USA). Supported by the Foundation MINES ParisTech, with Valeo industrial, PSA Peugeot Citroën and Safran contributing 3.7 million euros in funds, the Chair will work for five years on the subject of automated driving. The three main objectives are expand knowledge of self-driving vehicles, develop intelligent onboard systems, get self-driving vehicles on the road in Asia, Europe and the United States.

Sponsor: MINES ParisTech. December 01, 2014-November 30, 2018. PI: Michel Bierlaire. PM: Riccardo Scarinci. External collaboration: Damien Matti (EPFL Signal Processing Laboratory 5 LTS5)


Leveraging Public and Open Data for Transportation Mode detection
Leveraging Public and Open Data for Transportation Mode detectionSwisscom

Modern smartphones are more than just calling devices. They harbor a wealth of information that provides the transportation field with a new potential. In this project, researchers will create a transportation mode detection model based on telecommunication data from smartphone users combined with public transport-related data sources. The researchers are provided with anonymized telecommunication traces. As those data remain scarce, additional data will be identified from external sources including network infrastructure, route maps, time schedules in static or real-time form, microcensus, weather, etc. A probabilistic model will be developed to infer the transportation modes from those various data sources. The project lasts one year, and will be carried out by the Transport and Mobility Laboratory, directed by Prof. Michel Bierlaire. It is sponsored by Swisscom.

Sponsor: Swisscom . September 04, 2017-September 04, 2018. PI: Michel Bierlaire. PMs: Marija Nikolic, Riccardo Scarinci. External collaboration: Swisscom


Network Design for SBB Cargo
Network Design for SBB CargoSwiss Federal Railways (SBB)

This project aims at developing an algorithm for the overall design of SBB cargo’s network of bundling points. SBB Cargo operates a network of 2 marshaling yards, 65 shunting yards and about 350 of small bundling points. The operation as such is costly and the network might contain redundant bundling points. The overall interest of SBB Cargo is to minimize the operating cost of their network and to compare its performance to a better network, completely designed from scratch. The resulting framework is then planned to be used to improve the current network of SBB cargo and its future development. The main research challenge of this project is to incorporate the SBB Cargo needs into one model while taking into account the specifics of the railway network and its operation. The researchers from the Transport and Mobility Laboratory (TRANSP-OR) will develop a heuristic algorithm that gives as an output a complete network design based on the inputs (cargo demand, capacity, types and costs of different bundling points). The algorithm can be further adjusted by entering the already existing bundling points. The effectiveness of the proposed algorithm will be tested thorough comparison with existing solutions. TRANSP-OR, led by prof. Michel Bierlaire, has a track record of successful projects of solving highly complex problems arising in industrial sector. This one-year project is sponsored by SBB-CFF-FFS.

Sponsor: Swiss Federal Railways (SBB). September 01, 2017-August 31, 2018. PI: Michel Bierlaire. PMs: Nikola Obrenovic, Virginie Lurkin. External collaboration: SBB


Cost reduction using passenger centric timetabling
Cost reduction using passenger centric timetabling Swiss Federal Railways (SBB)

To design their timetables, train-operating companies mostly focus on operational aspects and cost. In Switzerland, a paradigm of transportation planning is to create regular-interval timetables (a.k.a. cyclic timetables) which aim for maximal transfer connections, simplicity and hence user friendlyness. SBB uses travel simulation models to predict the impact of timetable changes on travel demand and revenue. Mathematical timetable optimization methods are not yet used by SBB. But a recent EPFL thesis (2016) shows that the timetable itself has a significant impact on the performance of the operator in terms of the number of transported passengers: a timetable design that considers the behavior of passengers leads to higher revenue(s), market share(s), higher value of passenger-km etc. In this project, the aim is to use the optimization methods developed by the TRANSP-OR Lab consisting in combining cyclic and non-cyclic timetables and apply it to the Swiss Federal Railways’ timetable design. The goal is to evaluate the performance of the current Swiss interval timetable and to compare it to the optimal one. Suitability of hybrid timetables for the Swiss railway network will be investigated. This one-year project is carried out by the Transport and Mobility Laboratory, led by prof. Michel Bierlaire. TRANSP-OR has vast competence in modeling, optimization and simulation of transportation systems. The project is sponsored by SBB CFF FFS.

Sponsor: Swiss Federal Railways (SBB). September 01, 2017-August 31, 2018. PI: Michel Bierlaire. PM: Virginie Lurkin. External collaboration: SBB


myTOSA 2.0 - Enhanced simulation and optimization tool for cost-optimal deployment of TOSA electric buses
Commission pour la technologie et de l'innovation, Office Fédéral de la formation professionnelle et de la technologie.

The TOSA catenary-free electric bus system is the ABB response to the challenge of decreasing the environmental impact of public transportation. The project builds on the previous CTI project - myTOSA - and it aims to introduce new business analytics features and to improve the fidelity of the simulation and (robust) optimization modules used for a cost-optimal deployment of the TOSA charging infrastructure and component sizing.

Sponsor: Commission pour la technologie et de l'innovation, Office Fédéral de la formation professionnelle et de la technologie.. September 30, 2015-November 16, 2017. PI: Michel Bierlaire. PMs: Riccardo Scarinci, Virginie Lurkin. Research team: Shadi Sharif Azadeh, Yousef Maknoon. External collaboration: ABB, ABB Sécheron, HES-SO Haute Ecole Spécialisée de Suisse occ.


Electric vehicle adoption dynamics: exploring market potentials
Electric vehicle adoption dynamics: exploring market potentialsNissan

This project proposes innovative methods to identify the determinants of acceptance of alternative vehicles and their impact on everyday mobility.

The greatest challenge faced by the promoters of the transition towards this low carbon engine technology lies in understanding how consumers accept the financial and lifestyle investments associated with the leap from traditional to electric powertrains. This project proposes innovative methods to identify the determinants of acceptance of alternative vehicles and their impact on everyday mobility. A deeper understanding of adoption dynamics is critical to predict who will opt for EVs when and under which conditions.

This project will focus on innovative data-collection and modelling methodologies to uncover the acceptance of EVs at different stages of market-penetration (considering inexperienced/experienced users, early pioneers/late-adopters). A thorough analysis of the consumer decision-making process will lead to uncovering the barriers and success factors related to EV uptake and to forecast buying and usage behaviours related to new vehicle classes.

Sponsor: Nissan. April 01, 2014-March 31, 2017. PI: Michel Bierlaire. PM: Matthieu de Lapparent. Research team: Anna Fernandez Antolin. External collaboration: Dr. Amanda Stathopoulos, Northwestern University


PostCarWorld: A Trans-Discplinary Multi-Dimensional Stimulation
PostCarWorld: A Trans-Discplinary Multi-Dimensional StimulationSwiss National Science Foundation

The goal of this project is to explore the future of mobility through the role of the car. The main originality of this research is to raise the following problem: “What, if the world were a post-car world”. The basic idea is to define a hypothetical situation where the place of the car would have been dramatically reduced and to use qualitative and quantitative simulation methods to examine the consequences of this initial hypothesis. The research is based on the idea that by simulating the future through scenarios we can understand the present better. This project is fully interdisciplinary and trans-disciplinary. It brings together social sciences, engineering sciences, urban planning and urban design in six different laboratories associated to three different universities.

The role of TRANSP-OR in this project is to study and optimize an innovative transport system based on accelerated moving walkways (AMW). Differently from constant moving walkways, AMW can reach speeds up to 15km/h thanks to an acceleration section. The project aims to identify the optimal design of a network of AMW using optimization. A network of accelerated moving walkway in a car-free urban environment may present an innovative solution, and this project could delineate the system feasibility.

Sponsor: Swiss National Science Foundation. December 01, 2013-November 30, 2016. PI: Michel Bierlaire. PM: Riccardo Scarinci. http://postcarworld.epfl.ch/


Revisiting the Route Choice Problem: A Multi-Level Modeling Framework for Route Choice Analysis Based On Latent Constructs
Revisiting the Route Choice Problem: A Multi-Level Modeling Framework for Route Choice Analysis Based On Latent ConstructsSwiss National Science Foundation

This project aims at developing behavioral models integrating the latent constructs that drive travel behavior. The objective of the project is to set the foundations of an innovative framework that facilitates the analysis and prediction of route choice behavior. Motivated by the complexity of the route choice models, we build on solid ground of the current state of the art and add on it by proposing a new approach that reduces model complexity and brings great flexibility to the analysis. The approach is inspired by the fact that people break down the complexity of the environment by forming representations of their surrounding space. Following this reasoning, we replace the conventional representation of routes which is based on paths, i.e. link-by-link sequences on the network model, with more aggregate elements that we denote as mental representation items. This key feature of the framework allows us to reduce the complexity of the model and at the same time is more behaviorally realistic.

Sponsor: Swiss National Science Foundation. October 01, 2013-September 30, 2016. PI: Michel Bierlaire. PM: Matthieu de Lapparent. Research team: Evanthia Kazagli. External collaboration: Dr. Amanda Stathopoulos, Northwestern University


ACTUM
ACTUM

The ACTUM research collaboration project involves development of an activity-based modelling framework for Copenhagen that is aimed at handling the future requirements for transport policy evaluations in Denmark.

Sponsor: The Danish Council for Strategic Research. March 01, 2011-March 01, 2016. PI: Michel Bierlaire. PM: Matthieu de Lapparent. http://www.dtu.dk/subsites/ACTUM/English.aspx


Demand-based facility location problem
Demand-based facility location problem EDF

The project aims at integrating demand models in a state-of-the-art mathematical model for Location-Routing Problem (LRP) in the context of energy. We are investigating different assumptions about the representation of the demand in the context of facility location and routing problem.

Sponsor: EDF. August 01, 2015-December 31, 2015. PI: Michel Bierlaire. PM: Shadi Sharif Azadeh. External collaboration: EDF


Air navigation platform: flights planning by using real-time weather data
Commission pour la technologie et de l'innovation, Office Fédéral de la formation professionnelle et de la technologie.

Flying safer, cheaper, faster are keywords of this new service. This project aims at integrating an automatic route planning system, tightly coupled with the real-time meteorological data, taking into account energy consumption of the mobile device hosting the application. The route will be computed in real time on mobile devices using the information of weather forecast and respecting to the constraints such as airspace/airport restriction and terrain avoidance, etc. The energy efficient implementation of the routing application is crucial, to provide routing information to the pilot during the entire trip. This becomes challenging, as automatic route planning often requires complex algorithms. In this project, we will target at a three-dimensional flight route-planning problem and design an efficient but robust algorithm to solve the problem. The project will last 18 months. It is conducted by TRANSP-OR in collaboration with the Xample Sàrl, ICARE Institut de recherche and Haute Ecole Spécialisée de Suisse Occidentale (HES-SO).

Sponsor: Commission pour la technologie et de l'innovation, Office Fédéral de la formation professionnelle et de la technologie.. March 02, 2014-September 02, 2015. PI: Michel Bierlaire. PMs: Yousef Maknoon, Shadi Sharif Azadeh. External collaboration: Xample Sàrl, ICARE Institut de recherche, Haute Ecole Spécialisée de Suisse Occidentale


Modular Logistics Units in Shared Co-modal Networks
Modular Logistics Units in Shared Co-modal NetworksEuropean Commission

The objective is to achieve the first genuine contribution to the development of intercontinental logistics at the European level, in close coordination with North America partners and the international Physical Internet Initiative. The goal of the project is to enable operations with developed iso-modular logistics units of size adequate for real modal and co-modal flows of fast-moving consumer goods, providing a basis for an interconnected logistics system for 2030.

Sponsor: European Commission. July 01, 2012-June 30, 2015. PI: Michel Bierlaire. PMs: Shadi Sharif Azadeh, Yousef Maknoon


Pedestrian dynamics: flows and behavior
Pedestrian dynamics: flows and behaviorSwiss National Science Foundation

This project aims at developing mathematical models of pedestrian dynamics, both at aggregate and disaggregate levels. Integrated and holistic mathematical models will handle the complexity of this unique transport mode and help us to answer open research questions. in the future, such foundations will also allow to create the tools society needs to better understand pedestrian dynamics.

Sponsor: Swiss National Science Foundation. April 01, 2012-March 31, 2015. PI: Michel Bierlaire. PMs: Bilal Farooq, Riccardo Scarinci. Research team: Antonin Danalet, Flurin Hänseler, Marija Nikolic


Pedflux: Pedestrian flow modeling in train stations
Pedflux: Pedestrian flow modeling in train stationsSwiss Federal Railways (SBB)

The aim of this collaborative research project between the Swiss Federal Railways (SBB-CFF-FFS) and EPFL's transportation center is to analyze, model and optimize pedestrian flows in train stations. In recent years, the growing number of passengers has led to difficulties related to pedestrian flows in major train stations. Congestion of pedestrian walkways is increasingly becoming a problem during peak hours, but also due to clustering of people caused by major events or the beginning or end of holiday season. When capacity limits for pedestrian facilities are reached, normal operation of train schedules can be significantly impaired. Since train stations are important nodes within the multimodal public transportation system, it is of major importance that they are operated as efficiently as possible. In addition to the increase in passenger numbers, train stations have been undergoing a profound transformation from simple transit nodes towards versatile hubs that provide interface to short and long-distance train connections, to other modes including private transport by foot, bike and car, as well as to the city offering public space for shopping, eating and alike. This transformation leads to a further increase in pedestrian numbers and additionally introduces new behavior patterns. A sound understanding of pedestrian flows within a train station can help improve overall level of service, customer experience and safety. The main focus of this study lies on the development of a methodology allowing to estimate pedestrian origin-destination (OD) demand within a train station. Specifically, train time table, customer survey data and flow observations from an exhaustive camera system are used as sources of information in this process. Subsequently, the modeling frame work is applied to several case studies in Switzerland.

Sponsor: Swiss Federal Railways (SBB). April 01, 2012-March 31, 2015. PI: Michel Bierlaire. PMs: Michaël Thémans, Riccardo Scarinci. Research team: Flurin Hänseler


Large scale robust optimization of bulk port operations.
Large scale robust optimization of bulk port operations.EPFL Middle East

The primary objective of this research is to develop large scale robust optimization algorithms providing sustainable solutions for bulk port operations accounting for uncertainties and disruptions in operations. While significant contributions have been made for container terminals, relatively little attention has been directed to the use of operations research methods and techniques to optimize bulk port operations. In this research we aim to develop large scale mathematical models for bulk port operations, with emphasis on integrated planning; furthermore, we plan to include robustness to account for uncertainties in operations. A broader objective of our work is to study how the methodologies developed for bulk ports can be extended to multi-modal transport operations, including other domains such as container ports, airlines and railways, with a view to optimize the usage and operations of existing infrastructure to achieve sustainability in the mobility of goods and people. The devised models and algorithms will be tested and validated in a real-world context using as a case study, the SAQR port in Ras Al Khaimah, UAE.

Sponsor: EPFL Middle East. January 01, 2011-April 30, 2014. PI: Michel Bierlaire. PMs: Nitish Umang, Ilaria Vacca. External collaboration: Saqr Port (Emirate of Ras Al Khaimah, UAE)


CLIP-AIR concept: Integrated schedule planning for a new generation of aircrafts
CLIP-AIR concept: Integrated schedule planning for a new generation of aircraftsEPFL Middle East

Sustainability has become a key topic in transportation in the last decades where the aim is to reduce the impact of transportation on the environment. One of the most important paths toward sustainability in this sector is to optimize transportation operations required in several dimensions to fulfill a given transport demand. To achieve this goal in the context of multimodal transport, there is a clear need for flexibility in capacity. This flexibility is adequately provided by a new concept developed at EPFL, named Clip-Air, for air transport. Clip-Air is a modular innovative aircraft with detachable load units which enable to adjust at best capacity according to demand. The decoupling of the load (capsules) and carrying units (wings) allows for simplified fleet management and maintenance operations for airlines and is expected to improve the ground operations for airports. Clip-Air also provides effective possibility of combining commercial freight and passengers on the same flight without any compromise in comfort. Besides, Clip-Air is designed to operate in a multi-modal context and is expected to improve the multi-modality concept by allowing a better integration between air transport and other transport modes. The objective of this research is to assess the actual impact of Clip-Air’s modularity on demand satisfaction, operational costs and environmental issues at the system level. The contributions will consist of models and algorithms designed to perform comparative analysis of operations of airlines and airports in various scenarios.

Sponsor: EPFL Middle East. November 01, 2010-December 31, 2013. PI: Michel Bierlaire. PMs: Bilge Atasoy, Matteo Salani. External collaboration: Dalle Molle Institute for Artificial Intelligence (IDSIA, Lugano, Switzerland))


myTOSA: catenary-free 100% electric urban public mass-transportation system
myTOSA: catenary-free 100% electric urban public mass-transportation systemCommission pour la technologie et de l'innovation, Office Fédéral de la formation professionnelle et de la technologie.

myTOSA is a simulation tool for the dimensioning, commercial promotion and case study set-up for ABB's revolutionary "catenary-free" 100% electric urban public mass-transportation system TOSA 2013. The objective of the project is to provide a simulation tool that will allow ABB to perform the proper dimensioning, promote the commercial idea and allow for specific study cases for the implementation of ABB's new public electric transportation concept, namely TOSA 2013.

Sponsor: Commission pour la technologie et de l'innovation, Office Fédéral de la formation professionnelle et de la technologie.. March 01, 2012-September 30, 2013. PI: Michel Bierlaire. PM: Jianghang Chen. Research team: Bilge Atasoy, Tomás Robenek. External collaboration: ABB Sécheron, HE - ARC


Route choice models and smart phone data
Route choice models and smart phone dataSwiss National Science Foundation

Smart phones are able to collect a great wealth of information about the mobility patterns of individuals, including their itinerary. In addition to GPS tracks, smart phones contain several sensors and software revealing various aspects of the user's behavior (nearby Bluetooth devices, WiFi antenna, media players, etc.) Route choice models rely on the knowledge of the origin and the destination of the trip, and the transportation mode. They may also benefit from other contextual data, such as the trip purpose or the chain of subsequent activities. We plan to investigate how to infer this information from the smart phone data.

Sponsor: Swiss National Science Foundation. October 01, 2010-September 30, 2013. PI: Michel Bierlaire. PM: Jingmin Chen. Research team: Jingmin Chen


NRP 65: Sustainable Urban Patterns (SUPat)
NRP 65: Sustainable Urban Patterns (SUPat)Swiss National Science Foundation

This project aims at developing methodologies for the integration of qualitative an quantitative tools for land use planning and urban project-evaluation . The methodology will allow the interaction between urban design experts and land use modelers, developing techniques to use the description of urban projects and policies as inputs for land use models like UrbanSim and transport models like MATSim. The modeling effort output is used as input for the experts, generating an iterative feedback.

Sponsor: Swiss National Science Foundation. October 01, 2010-September 30, 2013. PI: Michel Bierlaire. PMs: Bilal Farooq, Ricardo Hurtubia. Research team: Dimitrios Efthymiou


Methods and tools for supporting the use, calibration and validation of traffic simulation models
Methods and tools for supporting the use, calibration and validation of traffic simulation modelsEuropean Commission

The main objective of this Action is to develop, implement and promote methodologies and procedures to support the use of traffic simulations, especially on the topics of calibration and validation. To this aim, the sharing and exchanging of available traffic datasets will also be a key task of the Action.

Sponsor: European Commission. May 26, 2009-May 25, 2013. PI: Michel Bierlaire. PM: Bilal Farooq. External collaboration: EPFL ENAC TOPO


A DYNAMIC VEHICLE CHOICE FORECASTING FRAMEWORK
A DYNAMIC VEHICLE CHOICE FORECASTING FRAMEWORKPSA Peugeot-Citroën

The aim of this research project is to develop a dynamic model framework to forecast car demand. The model-system jointly accounts for behavioural variables (e.g. household evolution, individual motivations), institutional factors (e.g. incentives and taxation) and market features (e.g. new fuel or vehicle technology launches) to forecast vehicle acquisition. The project benefits from a large-scale, longitudinal dataset on vehicle transactions from major European markets. Methodologically the framework consists of a system of aggregate, disaggregate and duration-based choice models, accounting for dynamic features of the decision at each stage. Importantly, the proposed dynamic framework enhances realism by representing the durability of possession, rapid changes in value across product and ownership cycles and uncertainty about future market developments and institutional factors. The proposed framework sheds light on the timing and type of vehicle ownership, illustrating the benefits of taking the first steps away from a static approach. The findings will aid the prediction of consumer behaviour in response to critical policy variables, such as incentives, alongside market dynamics, such as the appearance and diffusion of novel technologies. A deeper understanding of future vehicle choice behaviour is critical given sizable institutional and industrial investments to promote alternative vehicle technologies with a final aim to improve energy efficiency in the transportation sector. More information http://transport.epfl.ch/car-market-structure

Sponsor: PSA Peugeot-Citroën. April 01, 2012-April 30, 2013. PI: Michel Bierlaire. PM: Amanda Stathopoulos. Research team: Aurélie Glerum. http://transport.epfl.ch/car-market-structure


SustainCity: Micro-simulation for the prospective of sustainable cities in Europe
SustainCity: Micro-simulation for the prospective of sustainable cities in EuropeEuropean Commission

The goal of this project is to address the modelling and computational issues of integrating modern mobility simulations with the latest micro-simulation land use models. The project intends to advance the state-of-the-art in the field of the micro-simulation of prospective integrated models of Land-Use and Transport (LUTI). On the modelling side, the main challenges are to integrate a demographic evolution module, to add an environmental module, to improve the overall consistency and, last but not least, to deal with the multi-scale aspects of the problem: several time horizons and spatial resolutions are involved.

Sponsor: European Commission. January 01, 2010-December 31, 2012. PI: Michel Bierlaire. PMs: Ricardo Hurtubia, Bilal Farooq. Research team: Dimitrios Efthymiou. External collaboration: Prof. Axhausen, ETHZ. http://www.sustaincity.eu


Models and methods for large scale optimization problems and applications in container terminals
Models and methods for large scale optimization problems and applications in container terminalsSwiss National Science Foundation

We develop new strategies to tackle large scale problems and their optimization. We focus in particular applications arising in the optimization of container terminal operations.

Sponsor: Swiss National Science Foundation. December 01, 2009-November 30, 2012. PI: Michel Bierlaire. PMs: Ilaria Vacca, Matteo Salani


Léman 2030: Flux piétons Gare de Lausanne
Léman 2030: Flux piétons Gare de LausanneSwiss Federal Railways (SBB)

In the framework of a 9-month collaboration with CFF, pedestrian flows in Lausanne train station are estimated and modeled. Specifically, an estimation methodology for pedestrian origin-destination demand is developed and applied to predict a demand scenario for 2030. By means of a pedestrian flow simulator, several infrastructure scenarios are quantitatively evaluated, the result of which helps CFF to design and dimension pedestrian underpasses of Gare de Lausanne for the future.

Sponsor: Swiss Federal Railways (SBB). October 01, 2011-July 15, 2012. PI: Michel Bierlaire. PMs: Michaël Thémans, Bilal Farooq. Research team: Flurin Hänseler, Antonin Danalet, Sohrab Sahaleh


A Solution Technique for the Locomotive Refueling Problem
Transport and Mobility Laboratory, EPFL

This problem corresponds to refueling locomotives at different station yards during the course of its journey. Locomotive tanks have a fixed fuel capacity and prices of fuel vary across yards. In addition, there is a fixed cost for hiring a refueling truck at a yard and every refueling stop that the locomotive makes. Locomotives can power different train sets during a cyclical planning horizon running 14 days. The objective of this exercise is to minimize the total fuel costs – fixed and operational – for a given set of locomotives, trains and yards. In addition, there are numerous constraints relating to refueling, locomotive tank capacity, refueling truck capacity etc. This problem has similarity to the network flow problem. We formulate this problem as a Mixed Integer Program (MIP) and present our experience in this project.

Sponsor: Transport and Mobility Laboratory, EPFL. July 15, 2010-July 15, 2012. PI: Michel Bierlaire. PM: Prem Kumar


SIEU : Urban Energy Information System
SIEU : Urban Energy Information SystemThe Ark Energy

The role of local authorities in reaching climate and energy goals is important. Consolidated data about energy at the local scale is necessary in order to fully measure the effects of policies and to adapt action-plans. The goal of this project is to evaluate the feasibility of a single platform with all the relevant energy data for a local authority, in particular statistics about mobility.

Sponsor: The Ark Energy. September 01, 2011-June 30, 2012. PI: Michel Bierlaire. PM: Antonin Danalet. Research team: Antonin Danalet. External collaboration: Centre de Recherches Energétiques et Municipales (CREM, Martigny, Switzerland)


OPTIMA: Inferring transport mode preferences from attitudes
OPTIMA: Inferring transport mode preferences from attitudesLaPoste

Swiss Post and PostBus have launched a research project to optimize mobility in cooperation with the Federal Institute of Technology in Lausanne (EPFL), represented by EPFL Transportation Center, under Professor Michel Bierlaire. This will show the market potential for combined mobility. Among other things it will look at the factors that influence travellers in their choice of transport. At a later stage, target group-specific new transport offerings and services will be developed and tested, which will have a lasting influence on this choice. The three years research project is conducted by Professors Vincent Kaufmann (LASUR) and Michel Bierlaire (TRANSP-OR).

Sponsor: LaPoste. February 01, 2009-June 30, 2012. PI: Michel Bierlaire. PM: Anne Curchod. Research team: Aurélie Glerum, Bilge Atasoy, Antonin Danalet. External collaboration: Vincent Kaufman (LASUR), Prisca Faure (CEAT), Martin Schuler (CEAT)


NEARCTIS
NEARCTISEuropean Commission

NEARCTIS (Network of Excellence: Advanced Road Cooperative Traffic management in the Information Society) is an academic network involving teams working on the field of traffic management and optimization, with a particular focus on cooperative systems. The main objective of the project is to constitute what could be considered as a virtual research institute.

Sponsor: European Commission. July 01, 2008-June 30, 2012. PI: Michel Bierlaire. PM: Bilal Farooq. External collaboration: Edward Chung, Ashish Bhaskar, LAVOC, PY Gilliéron, TOPO, ERT, INRETS (F), DLR (D), TUC (GR), TU Delft (NL), Imperial College, UCL, Southampton (UK)


CATS City Alternative Transport System
CATS City Alternative Transport SystemEuropean Commission

The CATS project aims to develop a new urban transport service based on a new generation vehicle. Its major innovation is the utilisation of a single type of vehicle for two different usages: individual use or collective transport. This new transport service is aimed at filling the gap between public mass transport and private individual vehicles. It is based on two operating principles: the self service concept where small and clean urban vehicles are offered on a short term rental basis, and the flexible shuttle service where a variable length of vehicles convoy, driven by a professional driver, operates at fixed hours along a line on a permanent basis or on a case by case basis. Four Cristal vehicles and two stations will be made available by Lohr Industrie to the project for experiments. The CATS project will investigate through an in depth mobility needs analysis, on-site demonstration and showcases, the environmental impact and social acceptance of the introduction of such a new system in three different European cities (Strasbourg FR, Ploeisti, RO, Formello, IT). CATS will complement the design and manufacture of the Cristal vehicle via a detailed definition of its operating principles and by a design of its urban settings (stations, infrastructures,) in accordance with cities and citizens needs.

Sponsor: European Commission. March 01, 2009-February 29, 2012. PI: Michel Bierlaire. PM: Sonia Lavadinho. External collaboration: LI - ERT - CUS - GEA - INRIA - Technion - CTL - PMP - AREMOL


SURPRICE: Sustainable mobility through road user charging
Swiss Federal Road Office

Equity effects of congestion charges and intra-individual variation in preferences. A joint research initiative between: Royal Institute of Technology (KTH), Sweden (lead), The Swiss Federal Institute of Technology, Zürich, Switzerland and Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland

Sponsor: Swiss Federal Road Office. July 05, 2010-October 03, 2011. PI: Michel Bierlaire. PM: Michel Bierlaire. Research team: Antonin Danalet. External collaboration: Axhausen Kay, Börjesson Maria, Cherchi Elisabetta. http://www.transport-era.net/action-groups/ent17-surprice.html


Optimizing Staffing Plans at Airports
Transport and Mobility Laboratory, EPFL

Minimizing operating costs for maintaining ground personnel at airports is a complex problem due to uneven flight activities, passenger service expectations and staffing inflexibilities due to shift durations. In this work, we would use the flight schedule and service criteria to develop a method to find optimal shift timings that considers non-productive time due to activity changeovers, the mix of full-time and part-time workers and passenger waiting time criteria.

Sponsor: Transport and Mobility Laboratory, EPFL. October 01, 2010-October 01, 2011. PI: Michel Bierlaire. PM: Prem Kumar


Robust Optimization of Railway Locomotive Assignment
Transport and Mobility Laboratory, EPFL

Locomotive assignment at Railway companies is a complex problem that must optimally assign a set of locomotives to known, scheduled trains. Each train has a power and traction requirement and locomotives may be available in groups known as "consist". There is a cost involved in breaking or adding a locomotive to a consist. Determining an optimal locomotive assignment that would also be robust to handle delays, maintenance requirements and other unknown factors is a complex problem. We are inspired from the research in a similar, closely related subject in the airline industry and would explore the possibilities of extending the same to railways. This project would be a part of the larger concept of "Flexible Transportation Systems"

Sponsor: Transport and Mobility Laboratory, EPFL. October 01, 2010-September 30, 2011. PI: Michel Bierlaire. PM: Prem Kumar. Research team: Francesco Piu


Demande de consommateurs pour des véhicules électriques
Demande de consommateurs pour des véhicules électriquesRenault Suisse SA

Evaluation de la demande des consommateurs pour des véhicules électriques en vue du lancement d'une telle gamme par Renault

Sponsor: Renault Suisse SA. August 01, 2010-April 30, 2011. PI: Michel Bierlaire. PM: Michaël Thémans. Research team: Aurélie Glerum


Behavioural modelling of human experts for scene analysis
Behavioural modelling of human experts for scene analysisSwiss National Science Foundation

Modelling the global appraisal process of experts in the context of scene analysis.

Sponsor: Swiss National Science Foundation. October 01, 2007-September 30, 2010. PI: Michel Bierlaire. PMs: Javier Cruz, Thomas Robin


Column generation methods for the recovery of disrupted airline schedules
Column generation methods for the recovery of disrupted airline schedulesSwiss National Science Foundation

Robust planning and recovery from disruptions for airlines operations

Sponsor: Swiss National Science Foundation. October 01, 2007-August 31, 2010. PI: Michel Bierlaire. PM: Niklaus Eggenberg


Projet d'agglomération Lausanne-Morges - AFTPU - Fourniture d'indicateurs pour alimenter l'analyse multicritère pour le choix de la variante de la desserte Nord

Des axes forts de transport public urbain sont à l'étude dans l'agglomération de Lausanne-Morges. Ce projet vise à fournir, à partir du logiciel Emme, des critères d'évaluation des diverses variantes de desserte de la partie nord de Lausanne

Sponsor: Service des routes et de la mobilité de la Commune de Lausanne. January 01, 2010-June 30, 2010. PI: Michel Bierlaire. PM: Jean-Pierre Leyvraz. External collaboration: Eric Grasset, bureau CITEC, Christophe Jemelin, TL


Disaggregate behavioral models exploiting data from Nokia devices
Disaggregate behavioral models exploiting data from Nokia devicesNokia Research Center

The projects aims at investigating how to perform an appropriate fusion of data from smartphones in order to predict the mobility behavior of a given individual.

Sponsor: Nokia Research Center. December 01, 2008-June 30, 2010. PI: Michel Bierlaire. PM: Jeffrey Newman. Research team: Jingmin Chen


Dépouillement des enquêtes de mobilité aux Hautes Ecoles
Ecole Polytechnique Fédérale de Lausanne

Examens des comportements de transport des usagers des Hautes Ecoles sur la base d'enqêtes de mobilité régulières.

Sponsor: Ecole Polytechnique Fédérale de Lausanne. June 24, 2009-June 01, 2010. PI: Michel Bierlaire. PMs: Jean-Pierre Leyvraz, Sonia Lavadinho. External collaboration: Martin Schuler (CEAT), Alain Jarne (CEAT)


SOPHOS: Simulation-based Optimization of the Performance in Hospital Operating suites
SOPHOS: Simulation-based Optimization of the Performance in Hospital Operating suitesSwiss National Science Foundation

Design an optimization framework combining macroscopic and microscopic models, with applications in hospital management and urban road traffic.

Sponsor: Swiss National Science Foundation. December 01, 2007-November 30, 2009. PI: Michel Bierlaire. PM: Carolina Osorio Pizano


Optimization of container terminal operations
Optimization of container terminal operationsTransport and Mobility Laboratory, EPFL

Design and development of models and algorithms for the optimization of operations in seaport container terminals.

Sponsor: Transport and Mobility Laboratory, EPFL. February 01, 2007-November 30, 2009. PI: Michel Bierlaire. PMs: Ilaria Vacca, Matteo Salani


Invariant features in omnidirectional images
Invariant features in omnidirectional imagesTransport and Mobility Laboratory, EPFL

Design of algorithms to extract invariant features from images captured by omnidirectional cameras.

Sponsor: Transport and Mobility Laboratory, EPFL. May 20, 2008-May 01, 2009. PI: Michel Bierlaire. PM: Javier Cruz. External collaboration: Iva Bogdanova (ESL, EPFL), Benoît Paquier (LTS5, EPFL), Jean-Philippe Thiran (LTS5, EPFL)


A PrototypeTransportation Land-use Model for the Region of Lausanne, Switzerland
A PrototypeTransportation Land-use Model for the Region of Lausanne, SwitzerlandInstitut du développement territorial (INTER), EPFL

Development of a prototype integrated transportation land-use model for the region of Lausanne.

Sponsor: Institut du développement territorial (INTER), EPFL. January 07, 2008-March 01, 2009. PI: Zachary Patterson. PMs: Zachary Patterson, Michel Bierlaire. Research team: Zachary Patterson


Simulation-based optimization of a railroad yard
Simulation-based optimization of a railroad yardVale

Simulation-based optimization of the operations of Vale's railroad yards.

Sponsor: Vale. July 01, 2008-February 28, 2009. PI: Michel Bierlaire. PMs: Matteo Salani, Anne Curchod


Path to purchase
Path to purchaseNestlé

To understand consumer behavior in his or her path to purchase.

Sponsor: Nestlé. July 01, 2006-June 30, 2008. PI: Michel Bierlaire. PM: Kamran Houshang Pour. Research team: Thomas Robin, Gianluca Antonini. External collaboration: Jean-Philippe Thiran, ITS, EPFL


Schedule disruption recovery for airlines
Schedule disruption recovery for airlinesCommission pour la technologie et de l'innovation, Office Fédéral de la formation professionnelle et de la technologie.

Development of a software product dedicated to airlines and providing solutions to recover from schedule disruptions with minimum cost.

Sponsor: Commission pour la technologie et de l'innovation, Office Fédéral de la formation professionnelle et de la technologie.. June 01, 2006-May 31, 2008. PI: Michel Bierlaire. PM: Matteo Salani. Research team: Niklaus Eggenberg. External collaboration: APM Technologies SA


Development of route choice models
Development of route choice modelsSwiss National Science Foundation

Design new discrete choice models capturing route choice behavior

Sponsor: Swiss National Science Foundation. May 01, 2005-April 30, 2008. PI: Michel Bierlaire. PM: Emma Frejinger


Système d'informatique géographique pour l'observatoire de la mobilité
Institut du développement territorial (INTER), EPFL

L’Observatoire de la Mobilité réalise régulièrement des enquêtes sur les déplacements des étudiants et collaborateurs en direction des Hautes Ecoles. Actuellement ces personnes entrent l’origine de leur déplacement en donnant le numéro postal, la localité et le cas échéant une indication supplémentaire (quartier). Ce projet a creusé la possibilité de donner l’origine en pointant sur une carte, compte tenu à la fois des aspects techniques et de facilité d’usage par les utilisateurs.

Sponsor: Institut du développement territorial (INTER), EPFL. July 03, 2007-March 25, 2008. PI: Michel Bierlaire. PM: Jean-Pierre Leyvraz. External collaboration: Panos Tzieropulos, LITEP, Jens Ingensand, LASIG


Projet d'agglomération Lausanne-Morges - Axes forts de transports publics urbains - Mise au point des variantes, choix d'une variante préférentielle et d'un axe fort prioritaire.
Projet d'agglomération Lausanne-Morges - Axes forts de transports publics urbains - Mise au point des variantes, choix d'une variante préférentielle et d'un axe fort prioritaire.

Après avoir retenu certaines variantes d'axes forts de transport en commun dans l'agglomération Lausanne-Morges lors d'une étude précédente, il s'agissait de choisir une variante prérentielle et un axe fort prioritaire. L'étude a été menée en s'aidant du logiciel EMME.

Sponsor: Service de la mobilité du canton de Vaud. October 01, 2007-January 10, 2008. PI: Michel Bierlaire. PM: Jean-Pierre Leyvraz. External collaboration: Philippe Gentizon, bureau Ribi, Patrick Paulus, bureau RGR


SOPHOS: Simulation-based Optimization of the Performance in Hospital Operating Suites
SOPHOS: Simulation-based Optimization of the Performance in Hospital Operating SuitesSwiss National Science Foundation

Design an optimization framework for the operation suites in hospitals, using simulation tools

Sponsor: Swiss National Science Foundation. December 01, 2005-November 30, 2007. PI: Michel Bierlaire. PM: Carolina Osorio Pizano. External collaboration: HUG (Hôpital Universitaire Genève)


Travaux de modélisation Emme2 en liens avec projets : SDOL (image directrice), desserte Le Mont, augmentation de capacité m2
Travaux de modélisation Emme2 en liens avec projets : SDOL (image directrice), desserte Le Mont, augmentation de capacité m2Transports publics lausannois

Etudes TL diverses : comparaison entre 2 variantes de futur réseau, tapis roulant Gare-Flon, prolongation de lignes vers le Mont-sur-Lausanne. en fournissant des indicateurs de qualité grâce à une modélisation Emme

Sponsor: Transports publics lausannois. August 01, 2007-September 30, 2007. PI: Michel Bierlaire. PM: Jean-Pierre Leyvraz


Optimization methods for advanced discrete choice models
Optimization methods for advanced discrete choice modelsSwiss National Science Foundation

Development of optimization algorithms designed for the maximum likelihood estimation of advanced discrete choice models where the objective function is singular, and non-trivial constraints are imposed on the parameters

Sponsor: Swiss National Science Foundation. April 01, 2004-March 31, 2007. PI: Michel Bierlaire. PM: Michaël Thémans


Einbezug von Reisekosten bei der Modelliering des Mobilitätsverhalten
Einbezug von Reisekosten bei der Modelliering des MobilitätsverhaltenSwiss Federal Road Office

Development of route choice models from RP and SP data

Sponsor: Swiss Federal Road Office. November 01, 2005-February 28, 2007. PI: Michel Bierlaire. PM: Emma Frejinger. Research team: Jelena Stojanovic. External collaboration: Prof. K. W. Axhausen (IVT, ETHZ), Prof. R. Maggi (Instituto Ricerche Economiche, Univesità della Svizzera Italiana)


Location of distribution centres
Location of distribution centresTransport and Mobility Laboratory, EPFL

Optimization of the location of distribution centres for Postlogistics, Switzerland

Sponsor: Transport and Mobility Laboratory, EPFL. March 15, 2006-August 21, 2006. PI: Michel Bierlaire. PM: Carolina Osorio Pizano. Research team: Thomas Robin. External collaboration: Daniel Marbach, Postlogistics


Enseignement orienté projet assisté par ordinateur
Enseignement orienté projet assisté par ordinateurFonds d'innovation de la formation de l'EPFL

Develop appropriate case studies for teaching optimization to mechanical engineers

Sponsor: Fonds d'innovation de la formation de l'EPFL. April 01, 2004-March 31, 2006. PI: Michel Bierlaire. PM: Emma Frejinger. External collaboration: LENI, EPFL


Behavioral model-based scene analysis
Behavioral model-based scene analysisNCCR Interactive Multimodal Information Management

Development of disaggregate behavior model for scene analysis in the context of video surveillance

Sponsor: NCCR Interactive Multimodal Information Management. July 01, 2002-June 30, 2005. PI: Michel Bierlaire. PM: Michel Bierlaire. Research team: Gianluca Antonini. External collaboration: Jean-Philippe Thiran, LTS, EPFL


Doped derivative-free algorithms for medical image registration
Doped derivative-free algorithms for medical image registrationSwiss National Science Foundation

Design of a new class of derivative-free algorithms exploiting some derivative information, customized for the image registration problem

Sponsor: Swiss National Science Foundation. April 01, 2002-March 31, 2005. PI: Michel Bierlaire. PM: Rodrigue Oeuvray. External collaboration: Philippe Thévenaz, Biomedical Image Group, EPFL, Jean-Philippe Thiran, Signal Processing Laboratory, EPFL


Développement de modèles suisses de prédiction de la demande en transport pour des applications en temps réel (Development of Swiss models for transportation demand prediction in the context of traffic management systems)
Développement de modèles suisses de prédiction de la demande en transport pour des applications en temps réel (Development of Swiss models for transportation demand prediction in the context of traffic management systems)VSS - Association of Swiss Road and Traffic Engineers

Development of operational disaggregate demand models for efficient dynamic traffic managment systems

Sponsor: VSS - Association of Swiss Road and Traffic Engineers. January 01, 2003-December 31, 2004. PI: Michel Bierlaire. PM: Michel Bierlaire. Research team: Michaël Thémans. External collaboration: Prof. K. W. Axhausen, IVT, ETHZ, A. Robert-Grandpierre, bureau d'ingénieurs RGR-SA, P. Widmer, Büro Widmer, Frauenfeld


Pedestrian simulation
Pedestrian simulationTransport and Mobility Laboratory, EPFL

We develop models of pedestrian movements based on discrete choice analysis.

Sponsor: Transport and Mobility Laboratory, EPFL. October 01, 2002-October 01, 2004. PI: Michel Bierlaire. PM: Michel Bierlaire. Research team: Gianluca Antonini, Thomas Robin, Javier Cruz


SIMBAD: Simulation-Based Automatic Detection
SIMBAD: Simulation-Based Automatic DetectionCommission pour la technologie et de l'innovation, Office Fédéral de la formation professionnelle et de la technologie.

Develop a model-based detection system where the scene analysis is supported by a crowd simulator

Sponsor: Commission pour la technologie et de l'innovation, Office Fédéral de la formation professionnelle et de la technologie.. October 01, 2002-September 30, 2004. PI: Michel Bierlaire. PM: Mats Weber. Research team: Gianluca Antonini. External collaboration: Mats Weber, ROSO, EPFL, Visiowavw S.A, Jean-Philippe Thiran, LTS, EPFL


Modèles de prévision de ventes (Sales forecasting models)
Modèles de prévision de ventes (Sales forecasting models)infoSource S.A.

Develop forecasting models for sales of various products, such as printers

Sponsor: infoSource S.A.. April 01, 2004-May 31, 2004. PI: Michel Bierlaire. PM: Michel Bierlaire. External collaboration: Sébastien Naizot, ROSO, EPFL


Structure and use of human activity spaces
Structure and use of human activity spacesEcole Polytechnique Fédérale de Lausanne

Use of GPS-based data to address three fundamental behavioural questions: (i) size, structure and orientation of the individual activity spaces, (ii) frequency and amplitude of the rythms of visits to different locations, including their competition and (iii) form of the rules of route choice behaviour

Sponsor: Ecole Polytechnique Fédérale de Lausanne. June 01, 2003-May 31, 2004. PI: Michel Bierlaire. PM: Michel Bierlaire. External collaboration: Sébastien Naizot, ROSO, EPFL, Prof. K. W. Axhausen, IVT, ETHZ


Organisation des tournées de bus (Planning of school bus pick-up services)
Organisation des tournées de bus (Planning of school bus pick-up services)Ecole Nouvelle de la Suisse Romande

Develop a prototype of a decision-aiding system for the bus scheduling problem

Sponsor: Ecole Nouvelle de la Suisse Romande. February 01, 2004-March 31, 2004. PI: Michel Bierlaire. PM: Michel Bierlaire. Research team: Michela Thiémard. External collaboration: Michel Tsukahara, ROSO, EPFL


Simulation du bloc opératoire et de la salle de réveil (Simulation of the surgery block)
Simulation du bloc opératoire et de la salle de réveil (Simulation of the surgery block)Hôpitaux Universitaires de Genève

Design and implement a model to simulate the operations of the surgery block in the Geneva Hospital

Sponsor: Hôpitaux Universitaires de Genève. April 01, 2002-March 31, 2004. PI: Michel Bierlaire. PM: Michel Bierlaire. External collaboration: Christophe Weibel, ROSO, EPFL, Dr. Garnerin, HUG


New algorithms for the route guidance generation problem
New algorithms for the route guidance generation problemSwiss National Science Foundation

Development of new algorithms to solve the route guidance generation problem, based on several formulations of the problem, combining a fixed-point approach with an optimization approach

Sponsor: Swiss National Science Foundation. April 01, 2001-March 31, 2004. PI: Michel Bierlaire. PM: Frank Crittin. External collaboration: Prof. M. Ben-Akiva, MIT


Large-scale discrete choice models
Large-scale discrete choice modelsTransport and Mobility Laboratory, EPFL

We investigate methodological developments designed to handle discrete choice models with a large number of alternatives

Sponsor: Transport and Mobility Laboratory, EPFL. March 25, 2003-March 25, 2004. PI: Michel Bierlaire. PM: Michel Bierlaire


TIMS: Tourism Instant Marketing and Shopping
TIMS: Tourism Instant Marketing and ShoppingCommission pour la technologie et de l'innovation, Office Fédéral de la formation professionnelle et de la technologie.

Develop a simulation tool to assess dynamic pricing and yield management strategies in ski resorts

Sponsor: Commission pour la technologie et de l'innovation, Office Fédéral de la formation professionnelle et de la technologie.. October 01, 2003-December 31, 2003. PI: Michel Bierlaire. PM: Michel Bierlaire. External collaboration: Sébastien Naizot, ROSO, EPFL, Groupe de compétence économie et tourisme, HEVs Sierre


Plan de gestion du trafic: Etude pilote pour la Suisse Occidentale (traffic management plan: pilot survey in Western Switzerland)
Plan de gestion du trafic: Etude pilote pour la Suisse Occidentale (traffic management plan: pilot survey in Western Switzerland)Swiss Federal Road Office

Implementation and evaluation of a real-time traffic prediciton model for the Western Switzerland highway network

Sponsor: Swiss Federal Road Office. March 01, 2001-May 31, 2002. PI: Michel Bierlaire. PM: Michel Bierlaire. External collaboration: Constantinos Antoniou, ROSO, EPFL, A. Robert-Grandpierre, bureau d'ingénieurs RGR-SA


Algorithmes d'optimisation performants pour le recalage rigide d'images en radiochirurgie et en radiothérapie stéréotaxique fractionnée assistées par ordinateur
Algorithmes d'optimisation performants pour le recalage rigide d'images en radiochirurgie et en radiothérapie stéréotaxique fractionnée assistées par ordinateurFonds UNIL-EPFL

Development and adaptations of efficient optimisation algorithms dedicated to brain images registration

Sponsor: Fonds UNIL-EPFL. March 01, 2001-March 31, 2002. PI: Michel Bierlaire. PM: Michel Bierlaire. Research team: Rodrigue Oeuvray. External collaboration: Dr. Pica, chef de clinique, Service de Radio-Oncologie, CHUV


Development and Evaluation of DynaMIT, a real-time Dynamic Traffic Assignment system for traffic prediction and guidance generation
Development and Evaluation of DynaMIT, a real-time Dynamic Traffic Assignment system for traffic prediction and guidance generationIntelligent Transportation Systems Program, Massachusetts Institute of Technology

Collaborate with MIT for the development and evaluation of DynaMIT, a Dynamic Traffic Assignment System (DTA) that supports real-time applications such as synamic route guidance and adaptative traffic control

Sponsor: Intelligent Transportation Systems Program, Massachusetts Institute of Technology. October 01, 1998-October 31, 2001. PI: Michel Bierlaire. PM: Michel Bierlaire. Research team: Frank Crittin. External collaboration: Prof. M. Ben-Akiva, MIT


PAPABILES
PAPABILESEtat de Vaud

Evaluation of a traffic control system in Lausanne, using MITSIM laboratory, a state-of-the-art simulation tool developed by the Intelligent Transportation Systems Program, MIT

Sponsor: Etat de Vaud. March 01, 2000-August 31, 2001. PI: Michel Bierlaire. PM: Michel Bierlaire. External collaboration: A. Torday, Dept of Civil Engineering, EPFL, Prof. Dumont, Dept of Civil Engineering, EPFL, Dr. Mattenberger, Dept of Civil Engineering, EPFL


Optimisation de grande taille sans dérivés (Large-scale derivate-free optimization)
Optimisation de grande taille sans dérivés (Large-scale derivate-free optimization)Ecole Polytechnique Fédérale de Lausanne

Develop a new research track in large-scale derivative-free optimization

Sponsor: Ecole Polytechnique Fédérale de Lausanne. August 00, 2000-August 00, 2001. PI: Michel Bierlaire. PM: Michel Bierlaire. Research team: Frank Crittin