• Nie Znaleziono Wyników

35 years of excellence in computational methods for transportation science and technology

N/A
N/A
Protected

Academic year: 2021

Share "35 years of excellence in computational methods for transportation science and technology"

Copied!
4
0
0

Pełen tekst

(1)

Delft University of Technology

35 years of excellence in computational methods for transportation science and

technology

van Arem, Bart DOI

10.1111/mice.12610

Publication date 2020

Document Version Final published version Published in

Computer-Aided Civil and Infrastructure Engineering

Citation (APA)

van Arem, B. (2020). 35 years of excellence in computational methods for transportation science and technology. Computer-Aided Civil and Infrastructure Engineering, 35(9), 921-922.

https://doi.org/10.1111/mice.12610 Important note

To cite this publication, please use the final published version (if applicable). Please check the document version above.

Copyright

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons. Takedown policy

Please contact us and provide details if you believe this document breaches copyrights. We will remove access to the work immediately and investigate your claim.

This work is downloaded from Delft University of Technology.

(2)

Green Open Access added to TU Delft Institutional Repository

‘You share, we take care!’ – Taverne project

https://www.openaccess.nl/en/you-share-we-take-care

Otherwise as indicated in the copyright section: the publisher

is the copyright holder of this work and the author uses the

Dutch legislation to make this work public.

(3)

DOI: 10.1111/mice.12610

E D I T O R I A L

35 years of excellence in computational methods for

transportation science and technology

I completed my MSc degree in Mathematics in June 1986 on the Stochastic Modeling of Delays at Unsignalized Intersections. In July 1986, one month later, the first issue of Computer-Aided Civil and Infrastructure Engineering (CACAIE) was published by Prof. Hojjat Adeli. It was inevitable but it would take 30 years before our paths would cross.

Transportation engineering studies the planning, design, operation, and management of the demand and supply of transportation systems. It is rooted in civil and infrastructure engineering, by supporting planning, geo-metric design, and maintenance of civil and infrastructure assets. With growing demand of transport demand and limitations in space and funding, the intelligent utilization of physical transportation infrastructure has developed as an important field of scientific research. Already in 1986, CACAIE featured important work on transportation, for instance on computational equilibrium models for demand and supply in transport (Taylor,1986).

The advent of Information and Communication Tech-nologies opened new research avenues in which roads and vehicles could be studied as an integral system: Intel-ligent Vehicle Highway Systems, which developed more generally into Intelligent Transport Systems. Research challenges were multifold, integrating sensing, state estimation, systems and control, network modeling, and in particular data-driven methods.

Automated Driving is a field of research that has long captured the imaginations of researchers since the 1930s. Its recent history of research was marked by world-wide technology showcases Prometheus in Europe (Glathe,

1994) and National Automated Highway Systems Con-sortium demonstrations in the United States (Ioannou,

1997). They marked the successful combination of auto-motive engineering, electrical engineering, and roadway engineering.

The advent of data science and artificial intelligence methods such as machine learning and the entrance of new players such as Waymo and Tesla spurred a

world-© 2020 Computer-Aided Civil and Infrastructure Engineering

wide increase into research on automated driving. Com-puter vision and cognition based on images from laser scanner, video, and radar systems pose extremely high demands on hardware and software. The advent of high-definition digital maps and 5G (and further) communica-tion leaves no doubt that the vehicles of the future will be supported by a high-tech data and communication infras-tructure (Townsend,2014).

In order to accommodate high performance traffic in terms of efficiency, safety, and energy use, the roads of the future will also need to be high tech, with exten-sive monitoring, communication, and management sys-tems. Especially in the case of (highly) automated driv-ing capabilities, drivdriv-ing safely in dense traffic at high speed will require careful monitoring of the prevailing operational design domain traffic and roadway conditions requiring substantial investments in roadway infrastruc-ture (Shladover,2018).

In 2018, the paths of Prof. Hojjat Adeli and me finally crossed when I teamed up with Xiaobo Qu and Satish V. Ukkusuri to develop a special issue on novel compu-tational modeling of connected and automated transport systems. It was not only out of interest in contributing to a high-impact journal, CACAIE, but also I was inter-ested to learn how he runs the journal. I learned that first and foremost, running a journal is about personal commitment and passion to advance the field. This per-sonal commitment of Prof. Hojjat Adeli is the key to also establish a motivated and active editorial board. Equally important is his focus on original, high-quality scientific contributions.

The year 2020 marks the 35th Anniversary of

Computer-Aided Civil and Infrastructure Engineeringunder the lead-ership Prof. Hojjat Adeli. Having started with an initial focus on Civil and Infrastructure Engineering, CACAIE now also ranks number 1 in Transportation Science & Technology. I congratulate Prof. Hojjat Adeli with his accomplishment and thank him for his leadership and contribution to the field.

(4)

922 EDITORIAL

Bart van Arem

Faculty of Civil Engineering and Geosciences, Department of Transport & Planning, Delft University of Technology, Delft, The Netherlands

Correspondence

Bart van Arem, Faculty of Civil Engineering and Gesociences, Department of Transport & Planning, Delft University of Technology, Stevinweg 1, 2628 CN Delft, P.O. Box 5048, Delft, GA 2600, The Netherlands. Email:B.vanArem@tudelft.nl R E F E R E N C E S

Glathe, H. (1994). Prometheus - A cooperative effort of the European automotive manufacturers. SAE Technical Paper 942430.https:// doi.org/10.4271/942430

Ioannou, P. A. (Ed.). (1997). Automated highway systems. New York, NY: Plenum Press.

Shladover, S. E. (2018). Connected and automated vehicle sys-tems: Introduction and overview. Journal of Intelligent Transporta-tion Systems, 22(3), 190–200. https://doi.org/10.1080/15472450. 2017.1336053

Taylor, M. A. P. (1986). Interactive graphics and microcomputer mod-eling of traffic flows in dense road networks. Computer-Aided Civil and Infrastructure Engineering, 1(3), 197–208.https://doi.org/10. 1111/j.1467-8667.1986.tb00129.x

Townsend, A. (2014). Re-programming, mobility: The digital trans-formation of transportation in the United States. Retrieved from https://www.starcitygroup.us/2014/12/re-programming-mobility/

Cytaty

Powiązane dokumenty

The realization of cooperation between the Dutch technical universities took more time than expected; that is why for the time being only a local content organization will

of my PhD thesis: Computational analysis of fracture and healing in thermal barrier coatings on Wednesday, Dec 16, 2020, at 5:30 pm in the Aula (Senaatszaal) of the

Zelfs als micromechanische modellen bedoeld zijn om voorspellend te zijn, dan nog kun- nen ze het gedrag op systeem niveau pas voorspellen als ze voorzien zijn van de juiste

Based on the results presented in Volatile fatty acids production during mixed culture fermentation – The impact of substrate complexity and pH (Jankowska E.,

Convolutional weights are parameters of the model, so they are adjusted during the training process to filter out the most frequent features found in the data..

We stimulate neural networks with input data (usually affecting neurons in the input layer), for which neurons in subsequent layers make calculations until we obtain results (in

Train, dev (validation), and test sets should be set up in such a way that they share data of all distributions in the same way (be representative for the solved problem) to

a subset of training examples consisting of a defined number of training examples. In this case, training process is a compromise between the stability and speed, much better