In4Mo. Advanced Information System for the Mobility of People and Vehicles

Description 

In4Mo’s main objective has been to develop the applications that constitute the core of Smart Mobility, one of the fundamental pillars of the concept of Smart City: to provide information for traffic information system in any of its forms, and especially in the form of personal journey planners  and active traffic management systems, which allow road network managers to have a view and estimation of the actual state of traffic and its plausible short-term evolution in order to make more accurate decisions.

In4Mo has been designed and developed according to different expected technological scenarios in the sort and medium term. Traditional traffic management technologies (i.e. induction loops) and up and coming technologies (i.e. magnetometers) coexist in these scenarios where the ICT (Bluetooth, GPS…) and its progressive introduction into society have a relevant role and allow to develop more efficient systems.

The basic thesis of In4Mo is that technology, this means a city equipped with sensors, is a necessary but not sufficient condition for the generation of reliable, timely and value added information that is available at the place and the moment it is necessary. In other words, the degree of "smartness" is the result of efficient data combination and its processing.

However, the data obtained by measuring with sensors that use different technologies are heterogeneous. This is why the essential innovation In4Mo proposes is a methodology for the filtering, fusion and completion of data that adds and integrates a variety of flexible and efficient methods of analysis and processing that constitute a product that sustains a basic platform in order to provide homogeneous and consistent data that can be fed from any control centre for information and traffic management purposes:

  • Filtering techniques (non-linear, Kalman filter…) that generate complete, consistent and solid sequences by deleting outliers and completing lacking data.
  • Fusion techniques (Bayesian, neural networks, traffic models…) that allow to coherently combine data from heterogeneous sources in order to generate better-quality homogeneous information.
  • Prediction and state estimation techniques (state estimation models) that allow estimating the state of the traffic system and its plausible evolution in the short and medium term.

 

The availability of traffic data coming from ICT sensors leads to a considerable improvement in the quality of traffic information compared to the information generated by the systems operating nowadays. However, it will still be long until ICT has spread sufficiently so that it can provide a complete image of the traffic state of the entire road network by itself, particularly in mid- to large-sized urban areas.  This becomes a bigger issue especially when the information system has to support applications that require the computing in real time of paths between any origin-destination pair as it is the case of complete navigation systems that may not be restricted to sets of predetermined paths (however important they may be). In consequence, generating complete, consistent information requires using dynamic traffic models that allow performing a global estimation of the state of the road network and predicting its short-term evolution in the absence of incidents. In4Mo proposes two complementary dynamic traffic models:

  • Models for the estimation of time-dependent Origin-Destination (O-D) matrices based on the use of measurements of traffic variables provided by ICT applications and ad-hoc versions of the Kalman filter.
  • Models that describe the dynamics of the propagation of traffic flows across the road network according to demand patterns defined by time-dependent O-D matrices.

The finding that the same information generated by the combination of fused data and traffic models is needed by the person responsible of traffic management in order to manage a road network, is rendered in In4Mo as an innovative proposal for Smart Mobility: active management based on the Macro Fundamental Diagram (MFD).

An extension of the concept of traffic fundamental diagram applied to road networks allows to estimate the capacity of a network, in such way that using the available information it is possible to identify what area of the MFD you are operating in and make decisions such as restricting access (Gate-In), facilitate evacuation (Gate-Out) or proposing (or imposing) alternative routes.

This project is part of the program Acción Estratégica de Telecomunicaciones y Sociedad de la Información, 2010. Subprograma: Avanza Competitividad I+D+I, (2010-2012) [Strategic Action for telecommunications and the society of information, 2010. Subprogram: Avanza Competitividad R&D (2010-2012) ]

 

Duration of the project 
October, 2010 to December, 2012
Technology 
PostGIS,
JQuery,
Hibernate,
AMPL,
llog CPLEX,
JBoss,
PostgreSQL,
HTML,
JPA,
Java,
C++,
Matlab,
R,
Simulador Aimsun,
Simulador Dynameq
Areas of expertise involved in the project 
Project Manager 
Articles and Presentations 

J.Barceló, F. Gilliéron, M.P. Linares, O. Serch, L.Montero, The detection layout problem. Paper 12-2056, accepted for publication in Transportation Research Records: Journal of the Transportation Research Board, to appear in 2012.

J.Barceló, L.Montero, M.Bullejos, O. Serch and C. Carmona, A Kalman Filter Approach for the Estimation of Time Dependent OD Matrices Exploiting Bluetooth Traffic Data Collection, Paper #12-3843, presented at the 91st TRB Annual Meeting, January 2012, included in the Compendium of Papers.

J.Barceló, L.Montero, L. Marqués and C. Carmona, Travel time forecasting and dynamic of estimation in freeways based on Bluetooth traffic monitoring, Transportation Research Records: Journal of the Transportation Research Board, Vol. 2175 (2010), pp. 19-2

[CAT] "Un equip de la UPC desenvolupa un sistema per una millor gestió de la mobilitat" - Video at XipTV

Follow us on

Els nostres articles del bloc d'inLab FIB

         
         

inLab FIB incorporates esCert

Icona ESCERT

inLab is member of