Home      Log In      Contacts      FAQs      INSTICC Portal

Keynote Lectures

Data Stream Mining Applied to Intelligent Transportation Systems
Javier Sánchez-Medina, University of Las Palmas de Gran Canaria, Spain

Cooperative Automated Driving: From Platooning To Maneuvering
Jeroen Ploeg, 2getthere B.V., Utrecht, The Netherlands and Eindhoven University of Technology, Eindhoven, Netherlands


Data Stream Mining Applied to Intelligent Transportation Systems

Javier Sánchez-Medina
University of Las Palmas de Gran Canaria

Brief Bio

Dr. Sanchez-Medina earned his Engineering Master Degree at the Telecommunications Faculty on 2002, and his PhD at the Computer Science Department on 2008. His PhD dissertation versed on the use of Genetic Algorithms, Parallel Computing and Cellular Automata based Traffic Microsimulation to optimize the Traffic Lights Programming within an Urban Traffic Network.

His research interests include mainly the application of Evolutionary Computation, Data mining and Parallel Computing to Intelligent Transportation Systems. He has a wide experience on the development of traffic models and simulation platforms.

Javier Sanchez-Medina has been volunteering for several years at many international conferences related to Intelligent Transportation, Computer Science, Evolutionary Computation, etc. He is reviewer for some Transportation related journals.

He is also very active as a volunteer of the IEEE ITS Society. Since 2010, we has served for the IEEE ITS Society organizing the TBMO 2010 Workshop at ITSC2010, co-organizing the “Travel Behavior Research: Bounded Rationality and Behavioral Response” Special Session at ITSC2011, being Publications Chair at the IEEE FISTS2011, Registration Chair at the IEEE ITSC2012, Workshops and Tutorials Chair for IEEE ITSC 2013, Panels Chair at IEEE VTC2013-Fall, Program co-Chair at IEEE ITSC2014, program co-Chair at IEEE ITSC2016, publicity chair at IEEE IV2016, program chair at IEEE ICVES 2017, program chair at IEEE ITSC2018 and General Chair at IEEE ITSC2015. Currently he also is EiC of the ITS Podcast, the ITS Newsletter and Vice-president of the IEEE ITSS’s Spanish chapter.

He has widely published his research with more than 25 international conference articles and more than 15 international journal articles.




These days we are living an all-out revolution in Intelligent Transportation Systems (ITS) and Smart Mobility these days. It is not just how we are going to move from A to B. Instead, it is more how we are going to develop our lives both professionally and personally. The ongoing dramatic technological, economic and cultural change has a central driving force, a backbone that articulates it all, and that is Data. Data flow will shape our future and the future of our cities. That is especially true of ITS and Smart Mobility, a central part of Smart Cities.

However, this is not an easy step forward to humanity. This revolution, as any other in history, will take suffering. The overabundance of data poses a real challenge. The Internet of Things, the sensor networks and the data coming from apps running on our personal computing devices together are generating what could be described as a tsunami of data. We can either fight against this wave or take advantage of it!

When it comes to the so called Big Data, there are mainly two major challenges to face. Storage and efficient analytics. One recent approach to those two facets is that of Data Stream Mining. Put simply, it consists of not storing any more data, but creating the knowledge, updating the models, detecting anomalies, etc. as we go. It is easier said than done. This implies a denial of most of the classic methodologies on Machine Learning and Artificial Intelligence. It is a brand new way of understanding Machine Learning. A quantum leap in research development will be necessary. It must include a theoretical and practical change of perspective.

ITS is an engineering field where we can find plenty of Data based systems that need to operate in real time, through incremental learning and change adaptation. In most of them we have serious restrictions regarding the available computational performance and storage capacity, for instance at embarked systems. That is why ITS is the ideal test field to unfold the current Data Stream Mining methodologies and to push forward new knowledge too. This will be discussed in this keynote.



Cooperative Automated Driving: From Platooning To Maneuvering

Jeroen Ploeg
2getthere B.V., Utrecht, The Netherlands and Eindhoven University of Technology, Eindhoven

Brief Bio

Jeroen Ploeg received the M.Sc. degree in mechanical engineering from Delft University of Technology, Delft, The Netherlands, in 1988 and the Ph.D. degree in mechanical engineering on the control of vehicle platoons from Eindhoven University of Technology, Eindhoven, The Netherlands, in 2014.

He is currently with 2getthere, Utrecht, The Netherlands, were he leads the research and development activities in the field of cooperative automated driving for automated transit systems, in particular platooning. Since 2017, he also holds the position of part-time Associate Professor with the Mechanical Engineering Department, Eindhoven University of Technology, Eindhoven, The Netherlands. From 1989 to 1999, he was with Tata Steel, IJmuiden, The Netherlands, where his interest was in the development and implementation of dynamic process control systems for large-scale industrial plants. He was with TNO, Helmond, The Netherlands, from 1999 until 2017, ultimately as a Principal Scientist in the field of vehicle automation and road safety assessment.

His research interests include control system design for cooperative and automated vehicles, in particular string stability of vehicle platoons, the design of interaction protocols for complex driving scenarios, and motion control of wheeled mobile robots.


Autonomous vehicles do not intrinsically improve traffic since they optimize towards reaching their own goals. Cooperative driving, on the other hand, aims for optimizing the collective behavior, thus having the potential to improve the traffic system. Connectivity is instrumental for cooperative driving because traffic participants can express and share their intention more easily and precisely. When combined with vehicle automation, a powerful approach arises for improving traffic efficiency and safety.

A well-known application of cooperative automated driving (CAD) is cooperative adaptive cruise control (CACC) or platooning, which improves traffic throughput by adopting very short intervehicle distances. This is particularly of interest in automated transit systems (people movers) which, when used for first-/last-mile transportation, must have a high transport capacity. Also truck platooning is a promising application because fuel consumption decreases due to reduced aerodynamic drag at short distances. To fully exploit these potential benefits, a platoon needs to be string stable, which refers to attenuation of the effects of disturbances in upstream direction along the platoon. String stability contributes to safety, but it is only a necessary condition, not a sufficient one. To also guarantee safety in the presence of failing communication or common threats such as cutting in of other vehicles, additional measures are required which are only addressed in literature to a limited extent.

Next to ongoing developments in the field of platooning, cooperative automated maneuvering attracts attention to an increasing extent, acknowledging the fact that traffic is not a one-dimensional string of vehicles. Many approaches are still investigated in this field. One such approach relies on explicit decision making, employing so-called interaction protocols; This approach was illustrated by i-GAME, a European-funded project, whereas other projects, such as Autonet2030, adopt an optimization-based approach for path planning.

In summary, CACC and platooning are promising first applications of CAD, but further research and development in the field of safety is required, especially when considering the current world-wide standardization and road approval activities. At the same time, the application domain is extended towards cooperative automated maneuvering, ultimately leading to a truly ‘automated intelligent transportation system’.