Basic information

Edouard Ivanjko is an Associate Professor at the Department of Intelligent Transportation Systems (ZITS), Faculty of Traffic and Transport Sciences (UNIZG-FTTS), University of Zagreb (UNIZG) where he teaches courses related to computer science, electrical engineering, artificial intelligence, virtual reality, and traffic control. He is a member of the Transport Optimization Group (TOG) at the Department of Intelligent Transportation Systems (ZITS), Center of Excellence for Computer Vision (CRV), and the Centre of Research Excellence for Data Science and Advanced Cooperative Systems, Research unit Data Science. Personal research interests include intelligent transportation systems, modelling and simulation of road networks, application of computer vision and artificial intelligence in road traffic control. In collaboration with research colleagues, he assists also in research related to the development of algorithms for transport optimization, estimation and prediction of traffic parameters, and navigation of autonomous vehicles.

He is a member of the following professional organizations: IEEE (Institute of Electrical and Electronics Engineers), IEEE Intelligent Transportation Systems Society, ITS Croatia and KoREMA - Croatian Society for Communications, Computing, Electronics, Measurement and Control. Edouard Ivanjko actively participated in organization of several national and international conferences (International Symposium on Industrial Electronics ISIE 2005, European Conference on Mobile Robots 2009, Croatian Computer Vision Workshop in 2013, 2014, 2015, 2016, 2017, 2018 and 2019, First international conference on transportation and logistics ICTL'2015, 9th International Symposium on Image and Signal Processing and Analysis ISPA2015, International Workshop on Data Science (IWDS 2016, 2017, 2018 and 2019), International Conference Science and Traffic Development (ZIRP 2018 and 2019)), 11th Int'l Symposium on Image and Signal Processing and Analysis (ISPA 2019) and Informative workshops about the results of the finished PROM-PRO projects from the respective grant period (2016 and 2017). He participated in four scientific projects sponsored by the Croatian Ministry of Science, several EU funded projects (financed by the ESF, FP7 and the IPA program), in several professional projects in cooperation with industry and public institutions, obtained one PROM-PRO grant for young researchers from Faculty of Traffic and Transport Sciences (UNIZG-FTTS), and one short term support from the University of Zagreb (UNIZG) publishing more then 64 papers in international journals and conferences, chapters in scientific books, extended abstracts and technical reports.

Obavijesti / News

New journal paper accepted and published

Publication date: 2021-12-02

Our newest paper under the title “Spatial-Temporal Traffic Flow Control on Motorways Using Distributed Multi-Agent Reinforcement Learning” has been accepted for publication and published in the international scientific journal Mathematics, Special Issue "Advances in Artificial Intelligence: Models, Optimization, and Machine Learning". The paper is freely available in Open Access with DOI: 10.3390/math9233081. This paper was written in the co-authorship of Assoc. Prof. Edouard Ivanjko with his Ph.D. students Krešimir Kušić, mag.ing.traff. and Filip Vrbanić, mag. ing. traff., and postdoc Martin Gregurić, Ph.D., and Prof. Ivana Dusparic from TCD, Dublin, Ireland. The paper presents the results of applying distributed W-learning for variable speed limit control on urban motorways, including spatial-temporal control of the placement of speed limit zones and setting appropriate speed limits according to the current traffic situation. The research findings results from a yearlong work of the authors and common research goal to implement a multi-agent learning based traffic control system for urban motorways to improve the Level of Service and reduce the environmental impact of road traffic. We all congratulate on the accepted and published journal paper.

Attending the Sixth International Workshop on Data Science (IWDS 2021)

Publication date: 2021-11-26

On the 24th November, 2021 the Sixth International Workshop on Data Science (IWDS 2021) was held in Zagreb, Croatia. It was organized by the Centre of Research Excellence for Data Science and Advanced Cooperative Systems, Research unit Data Science and the project Advanced methods and technologies in Data Science and Cooperative Systems (DATACROSS). The workshop aimed to foster the interaction of researchers and exchange new ideas in the diverse area of data science and encourage interaction and networking between data science researchers and practitioners from both industry and government organizations. Assoc. prof. Edouard Ivanjko participated with the poster titled "Agent-based Urban Traffic Control" presenting the work done in cooperation with young researchers postdoc Martin Gregurić, Ph.D., Dino Čakija, Krešimir Kušić, Mladen Miletić and Filip Vrbanić related to applying reinforcement learning to control traffic flows in urban environments. He also contributed to the poster presentation "Motorway Bottleneck Detection Using Speed Transition Matrices" given by young researcher Leo Tišljarić to present the results achieved by researchers Leo Tišljarić, Filip Vrbanić, Edouard Ivanjko, and Tonči Carić. We all congratulate on the successful presentation.

Students Patrik Hršak and Josip Miloš win the Rector reward

Publication date: 2021-09-28

The bachelor and master students Patrik Hršak and Josip Miloš received the Rector award of the University of Zagreb for their work under the title “Impact of Speed Limit Zone Collocation on Variable Speed Limit Control on Urban Motorways”. The list of awarded students is available here. They worked under the supervision of Assoc. Prof. Edouard Ivanjko, assistant Krešimir Kušić and assistant Filip Vrbanić as part of student participation on the project "Control system of the spatial-temporal variable speed limit in the environment of connected vehicles" financed by Scientific Foundation of the Faculty of Transport and Traffic Sciences, and the project "Development of Learning Agent-based Systems for Improved Urban Traffic Control (DLASIUT)" financed by Croatian Science Foundation. In the scope of their research, the students implemented a realistic model of an urban motorway, a simple variable speed limit controller and evaluated it with different spatial configurations of speed limit zones using the microscopic traffic simulator SUMO and MATLAB to obtain the optimal placement of speed limit zones. We all congratulate them for their success and wish a fruitful continuation of their research efforts.

HRZZ Research Project DLASIUT First Workshop

Publication date: 2021-08-31

On the 6th of September, the HRZZ research project DLASIUT first workshop will be held in the amphitheater of object 69 at the Scientific Campus Borongaj starting at 8:30. The workshop is open for public using on-line participation and all interested persons can use this MS Teams link to participate. The workshop aims to disseminate the research goals of the project DLASIUT, to foster discussion between the research team and other interested members from academia and industry, and provide knowledge transfer between the foreign and domestic scientists. To track the number of possible online attendees, please register using the e-mail address filip.vrbanic@fpz.unizg.hr until Friday, the 3rd September noon. The workshop official language is English due to participation of foreign researchers and the agenda is available here .

We all wish a successful workshop.

Four new conference papers accepted

Publication date: 2021-08-26

Our newest research results have been accepted for publication in four conference papers. The first paper titled "Proposal for Fuzzy based Adaptive Traffic Signal Control for Reducing Vehicle Emissions" is accepted for the conference "3rd International Scientific Conference "TRANSPORT FOR TODAY'S SOCIETY"" which will be held on October 14-16, 2021 in Bitola, North Macedonia. This paper was made in the co-authorship of Daniela Koltovska Nechoska, Roberto Pashic, Robert Šimić, and Edouard Ivanjko. It presents a proposal on improving adaptive traffic signal control with emphasis on reducing road vehicle emissions using fuzzy logic reasoning and a newly developed traffic and emissions sensor.

The second paper titled "Influence of Spatial Placement of Variable Speed Limit Zones on Urban Motorway Traffic Control" is accepted for the "International Scientific Conference The Science and Development of Transport ZIRP2021" which will be held from September 30 until October 1, 2021, in Šibenik, Croatia. This paper was made in the co-authorship of Miloš Josip, Hršak Patrik, Topić Nikola, Jakšić Leon, Kušić Krešimir, Vrbanić Filip, and Ivanjko, Edouard. It presents the results of an analysis regarding the placement of speed limit zone for variable speed limit control systems. Emphasis is on traffic parameters and emission parameters. This paper god also recommended for the scientific journal "PROMET - Traffic&Transportation" due to its high quality.

The third and fourth papers are accepted for presentation at the scientific conference"63rd International Symposium ELMAR-2021, Special session Intelligent Transport Systems" which will be held on September 12-15 in Zadar, Croatia. The third paper titled "Creating Representative Urban Motorway Traffic Scenarios: Initial Observations" was made in the co-authorship of Filip Vrbanić, Mladen Miletić, Edouard Ivanjko, and Zeljko Majstorović. It presents the first results of traffic data analysis regarding Slovenian motorways in order to obtain realistic simulation scenarios for testing learning-based traffic controllers. The fourth paper, titled "Combining Neural Gas and Reinforcement Learning for Adaptive Traffic Signal Control," was made in the co-authorship of Mladen Miletić, Edouard Ivanjko, Sadko Mandžuka, and Daniela Koltovska Nečoska. It presents the results of the development of a reinforcement learning-based adaptive traffic signal controller with fast convergence and good control quality. Its results are an improvement of the ELMAR-2020 paper titled "State Complexity Reduction in Reinforcement Learning-based Adaptive Traffic Signal Control" published last year.

We all congratulate on the accepted papers and wish a successful presentation.

New project grant received

Publication date: 2021-06-01

On the 28th May 2021, financing for one Ph.D. student in the scope of the call DOK-2021-02 of the Croatian Science Foundation was granted to Assoc. Prof. Edouard Ivanjko. The new Ph.D. student will work on the HRZZ project DLASIUT and will receive financing for four years. Joint supervision of the Ph.D. student with Prof. Tonči Carić is envisaged. A public call for hiring the Ph.D. student will be announced in 2 months' time. We all congratulate on this success.

ERASMUSplus remote visit to the Faculty of Technical Sciences – Bitola, Macedonia

Publication date: 2021-06-01

From the 24 to the 31st May Assoc. Prof. Edouard Ivanjko remotely visited the Department for traffic and transport, Faculty of Technical Sciences – Bitola, St. Kliment Ohridski University, Bitola, North Macedonia as a guest lecturer. He presented his research results and held 10 hours of lectures to bachelor and master students from the area of Artificial intelligence and Virtual reality in transport and traffic. This visit was also used for planning of future cooperation of topics related to intelligent transport systems and joint research on the HRZZ project DLASIUT with project team member Assoc. Prof. Daniela Koltovska Nechoska.

ERASMUSplus visit of Assoc. Prof. Daniela Koltovska Nechoska

Publication date: 2021-05-31

From the 25 to the 28th May Assoc. Prof. Daniela Koltovska Nechoska from the Department for traffic and transport, Faculty of Technical Sciences – Bitola, St. Kliment Ohridski University, Bitola, North Macedonia, visited the Department of Intelligent Transportation Systems as a guest lecturer. She presented her research results and held 8 hours of lectures to bachelor and master students from the area of Adaptive Traffic Control in urban areas and the application of Artificial Intelligence in transport and traffic. The host was Assoc. Prof. Edouard Ivanjko. This visit was also used for planning of future cooperation of topics related to intelligent transport systems and joint research on the HRZZ project DLASIUT with the project team from the Faculty of Transport and Traffic Sciences.

ZIRP2020 conference papers published

Publication date: 2021-03-22

Three conference papers coauthored by Assoc. Prof. Edouard Ivanjko presented on the last year conference ZIRP2020 have been published in the book Transformation of Transportation issued by Springer. All the papers present the results of the joint work between Assoc. Prof. Edouard Ivanjko and his young researchers and national and international associates. The titles of the papers are Traffic Flow Simulators with Connected and Autonomous Vehicles: A Short Review, In-Depth Evaluation of Reinforcement Learning Based Adaptive Traffic Signal Control Using TSCLAB, and Airline Fleet Rotables Staggered Replacement Scheduling Using Dynamic Approach covering the topics of traffic control simulation of new mixed traffic flows, evaluation of learning based adaptive traffic signal control systems and approaches to airplane part replacement scheduling. We all congratulate on the published papers and wish for a successful continuation of the existing cooperation.

New journal paper accepted

Publication date: 2021-03-22

Our newest journal paper under the title “Variable Speed Limit and Ramp Metering for Mixed Traffic Flows: A Review and Open Questions” has been accepted for publication in the international scientific journal Applied Sciences, Special Issue "Artificial Intelligence for Connected and Automated Vehicles". The paper is available at Open Access with DOI: 10.3390/app11062574. This paper was written in the co-authorship of Assoc. Prof. Edouard Ivanjko with his Ph.D. students Filip Vrbanić, mag.ing.traff. and Krešimir Kušić, mag. ing. traff., and lecturer Dino Čakija, B.Sc., and presents the results of a detailed review analysis of a comprehensive survey of Variable Speed Limit and Ramp Metering control algorithms, including the most recent reinforcement learning-based approaches. Best practices for mixed traffic flow control are summarized, and new viewpoints and future research directions are presented, including an overview of the currently open research questions. The paper results from the authors' year-long work on the common research goal to implement a traffic control system for urban motorways to improve the Level of Service and reduce the environmental impact of road traffic. It is also related to the recently granted HRZZ project DLASUT We all congratulate on the accepted journal paper.

New master themes accepted

Publication date: 2021-03-22

On the 9h of February, the Committee for baccalaureus and master theses approved/prolonged three new topics for the students Filip Strikinac, Vjeko Glibota, and Marko Slavulj. All students will work on their thesis under the supervision of Assoc. prof. Edouard Ivanjko with the help of his young researchers. Approved theses are related to genetic algorithm-based calibration of microscopic traffic simulation models, variable speed limit control in the environment of connected autonomous vehicles, and traffic data analysis using neural networks in the ITS-related research scope done by Assoc. prof. Edouard Ivanjko and his young researchers and Ph.D. students. We all welcome the mentioned students in our small research group and wish them much success working on their theses.

New project grant received

Publication date: 2021-01-12

On Tuesday, December 22, 2021, at the Faculty of Transport and Traffic Sciences, the agreement for the assigning of funds from the Croatian Science Foundation under the tender "Research project, deadline 2020-02" for the research project IP-2020-02-5042 "Development of Learning Agent-based Systems for Improved Urban Traffic Control (DLASIUT)" led by Assoc. Prof. Edouard Ivanjko was signed. The signing of the contract was attended by the dean Prof. Tomislav Josip Mlinarić, Vice Dean for Science and External Cooperation Assist. Prof. Marko Šoštarić and secretary Romina Jovančević.

The project's total value is HRK 1,088,840.00, with the first installment of HRK 599,130.00. The project will last for four years from January 15, 2021, to January 14, 2025, and is implemented in collaboration with foreign researchers Prof. Ivana Dusparic from TCD, Dublin, Ireland, Prof. Daniela Koltovska Nečoska from the Faculty of Technical Sciences, St. Kliment Ohridski University - Bitola, Northern Macedonia and Prof. René Schumann from the Institute of Information Systems, HES-SO Valais, Switzerland. In the project, local researchers Prof. Sadko Mandžuka, postdoc Martin Gregurić, Ph.D., Dino Čakija, B.Sc., Krešimir Kušić, mag. ing. traff., Mladen Miletić, mag. ing. traff. and Filip Vrbanić, mag. ing. traff. will also participate with the plan for the employment of one doctoral student.

The goals and expected results of the project are:

• 1. Identified most representative classes of traffic scenarios with which the traffic controller must cope.
• 2. Developed reinforcement learning multi-agent-based traffic controller for urban traffic environments.
• 3. Developed framework for structured learning/testing of learning multi-agent-based traffic controller.
• 4. The developed traffic controller augmented for the management of traffic flows containing connected and autonomous vehicles.
• 5. The impact of the developed learning multi-agent-based controller on the improvement of urban traffic control analyzed.