28.02.16 - 04.03.16, Seminar 16091

Computational Challenges in Cooperative Intelligent Urban Transport

Diese Seminarbeschreibung wurde vor dem Seminar auf unseren Webseiten veröffentlicht und bei der Einladung zum Seminar verwendet.


Computational transportation science (CTS) is a new discipline that combines computer science and engineering with the modeling, planning, social, and economic aspects of transportation. It clearly goes beyond vehicular technology, addressing pedestrian and bike systems on hand-held devices and also deals with data issues such as, e.g., transportation data mining. The research agenda of CTS is structured into the following five directions: knowledge discovery, decentralized computing, social computing, applications, and societal issues. In this Dagstuhl Seminar, we plan to focus on decentralized computing and data challenges with regard to cooperative intelligent transport in urban areas.

In recent years, urban transportation networks have become more diverse, with a growing mix of public and private operators providing disaggregated services and information. The resulting multitude of transportation options includes non-traditional modes such as car and bike sharing, as well as established public transport and individual car options. In addition, the expectations of businesses for city logistics services have increased in an environment of crowded urban traffic infrastructure.

Cooperative intelligent transportation forms a shift in the basic paradigm of transportation management and thus poses many challenging questions especially from a computational perspective. The shift is made possible by advances in mobile technologies in combination with social networks. With the increased number of transportation options, a variety of data sources describing the experienced and/or the expected quality of the operations of individual transport services have become available. On the one hand, since cooperative intelligent urban transport is inherently multimodal, it is challenging to combine the available transportation options in a user-friendly manner, incorporating distributed quality of service information. On the transportation management side, however, the shift from centralized to decentralized information and service provision challenges currently reliable planning and realization of multimodal transportation, and methods of planning and management of intelligent urban transportation need to be extended.

The seminar aims at discussing how the above-mentioned data sources and services can be made available and used for intelligent planning at the level of travelers as well as in system-wide coordination of urban transportation. We assume that approaches from distributed computing, artificial intelligence, optimization, geographic information sciences, and traffic engineering among others will play a role in getting all involved parties to cooperate in providing and using relevant spatial and temporal information in a timely fashion. Data sources may differ in trustworthiness, impacting upon processes used for their aggregation to provide information for decentralized planning and control purposes. It is not clear how to evaluate reliability of information, how to derive reliable information for planning and control approaches, or how to adapt optimization methodologies to make urban transportation more cooperative and intelligent.

Topics to be discussed in the seminar include:

  • collective travel data gathering and combination of these insuring high quality;
  • modeling and transformation of data into individualized information services for cooperative transportation;
  • potential use and problems of data/information for transport system management;
  • providing traveler information and planning services while enabling cooperative transportation;
  • efficient, sustainable and reliable organization of city logistics services;
  • adapting current methodologies in planning and
  • control of urban transport systems to cooperative intelligent transportation.