Projects
Ongoing projects
Collaboration projects
-
Skipping Boundaries with Internationalization (LoMI)
The project "Skipping Boundaries with Internationalization (LoMI)" is financed by the Operative program „Efficient Human Potentials”, EU Social Fund, Call „Internationalization of Higher Education”. The partners on the project are Faculty of Mechanical Engineering and Naval Architecture, and Faculty of Organization and Informatics from University of Zagreb. The leading institution is the Faculty of Transport and Traffic Sciences. With a budget of 1,800,000.00 HRK (240,000.00 EUR), it has the goal to create a new master study program for logistics, mobility and infrastructure, and to raise the competences of lecturers in the partner institutions related to teaching on the English language. The first enrolment of students into the new master study program is expected in the academic year 2022/2023. Assoc. Prof. Edouard Ivanjko is participating in the project as leader of the subgroup that is creating the courses related to infrastructure.
(2018-2021, project managers: prof. Tomislav Josip Mlinarić and prof. Mario Šafran)
Link to project web page. -
Scientific Centre of Excellence for Data Science and Cooperative Systems
Scientific Centre of Excellence for Data Science and Cooperative Systems is the first centre of excellence in the area of technical sciences in Croatia. It consists of 13 partner institutions and 80 scientists from different areas including computer science, control theory, physics, bioinformatics, traffic sciences, mathematics, civil engineering, ... The centre is divided into two research units: (i) Research unit Data Science with focus on data science, i.e. problems how to extract knowledge and conclusions from various forms of data including big data; and (ii) Research unit Cooperative Systems with focus on cooperative systems, i.e. control of complex nonlinear systems with multiple entities that interchange information. The goal of the centre is to: (i) advance the state of the art in Data Science and Cooperative Systems, and develop new technologies, while increasing the number of research grants at the national and international level; (ii) encourage the transfer of technology from scientific realm to the industry and government, while supporting the growth of SMEs and large enterprises in Croatia; (iii) Provide the government and industry with an access to advanced computing facilities and expertise; and (iv) increase the number of highly skilled scientists/experts to satisfy the needs of the national job market by supporting undergraduate and graduate programs.
(2015-2020, project managers: prof. Sven Lončarić and prof. Ivan Petrović, UNIZG-FTTS representatives: Assoc. prof. Edouard Ivanjko (local leader), prof. Hrvoje Gold and prof. Tonči Carić)
Link to project web page.
Science projects
-
Development of Learning Agent-based Systems for Improved Urban Traffic Control (DLASIUT)
Today’s urban environments are prone to daily congestions due to dense traffic. The development of Machine Learning (ML) based traffic control systems for such environments gathered interest to create intelligent systems with the potential to improve the existing transport network efficiency. Applying ML in control of complex urban environments is prone to the curse of dimensionality. The controller behavior is influenced by the number of observed traffic parameters describing the environment in which it acts. Rising the number of parameters causes an exponential increase of possible state-action space, making it nearly impossible to find an optimal control policy in a reasonable time. The scalability of the same space becomes very important. It is also necessary to gain trust or confidence in the ML control system’s performance in unforeseen situations. Having a control policy that performs well in all relevant traffic states is more important than superior performance in some states. Thus, tuning of such systems for significant transport demand changes is very problematic or even infeasible for operators without computer support. The main benefit of the project DLASIUT is the proposed learning framework and structure of an agent-based traffic controller capable of learning the optimal control policy from microscopic simulations containing realistic models of a real-world urban road network. Additionally, support to Connected and Autonomous Vehicles (CAVs) will be added using them as an extra control output ensuring the applicability in future mixed traffic flows containing classic vehicles and CAVs. In-depth testing using realistic simulation models and Structured Simulation Framework from transport technology point of view to identify possible poor controller behavior will improve the state of the art of ML-based traffic controllers. The benefit for the citizens of urban environments is better traffic management and reduction of congestions and vehicle emissions.
(15th January 2021 - 14th January 2025, project manager: Assoc. Prof. Edouard Ivanjko)
Link to project web page. -
Control system of the spatial-temporal variable speed limit in the environment of connected vehicles
This project deals with traffic control on urban motorways with flows containing new vehicles having communication capabilities. The analyzed traffic control method is Variable Speed Limit (VSL) in traffic scenarios with severe congestions creating shockwaves that propagate upstream. A multi-agent control structure will be applied to solve such a congestion scenario capable of learning optimal speed limit control law and placement of the VSL and acceleration areas. Thus, project goals can be listed as: (i) Determination the impact of the spatial location of the VSL zone on traffic flow optimization in congested areas of an urban motorway; (ii) Developing an adaptable spatial-temporal VSL system using multi-policy optimization techniques in multi-agent environments, emphasizing collaboration between VSL agents for better flow optimization using Multi-Agent Reinforcement Learning-based techniques; and (iii) Testing the developed system on various traffic scenarios with varying flow homogeneity containing simulations of vehicles with certain autonomous levels concerning speed control (e.g., Intelligent Speed Adaptation system). The contract’s total value is 49,989.84 kn. The project is financed by the Science Foundation of the Faculty of Transport and Traffic Sciences call “Smart Traffic Solution,” program financing research of Ph.D. students.
(September, 2020 - September, 2021, project manager: Krešimir Kušić, mag. ing. traff.) -
Software Sensor Augmentation at Environmental Data Analysis Laboratory (SSA@EDAL)
The project entitled "Software Sensor Augmentation at Environmental Data Analysis Laboratory (SSA@EDAL)" is an Installation Research Project funded by the Croatian Science Foundation. Partners on the project are the University of Split - Faculty of Science, University of Zagreb - Faculty of Transport and Traffic Sciences, St. Kliment Ohridski University - Faculty of Technical Sciences, company Ericsson Nikola Tesla – R&D, and Institute of Oceanography and Fisheries. The scientific goals of the project assume machine learning models investigation for Software Sensor Augmentation (SSA). SSA denotes estimation of measurements in points where (or when) data has not been acquired and assumes that it is possible to find knowledge representation which describes the problem well. By learning representation from the data, the knowledge can be stored or transferred to another system (or problem domain). This can result in better initialization and faster convergence rate of such systems. The learned representation can be applied for data reconstruction and thus augment the sensor capabilities, which can result in more efficient resource utilization with positive effects on industry and environment. Potential applications are in classical monitoring systems such as meteorology, transport, or EU monitoring (e.g., of fish stock). In the Internet of Things (IoT) world, the exchange of information between sensors and inferring from data based on data from different domains is becoming a rule rather than the exception – and this research follows this direction.
(15th February 2020 - 14th February 2025, project manager: Assoc. Prof. Hrvoje Kalinić)
Link to project web page. -
Advanced methods and methodologies in data science and cooperative systems (DATACROSS)
The project Advanced methods and methodologies in data science and cooperative systems (DATACROSS) is financed as part of the Scientific Centre of Excellence for Data Science and Cooperative Systems from the program Superior Research of Science Centers of Excellence, European fund for regional development. It will explore advanced methods and technologies in data science and cooperative systems within the horizontal theme ICT of the Croatian S3 strategy with the aim of supporting innovation development and competitiveness of the Croatian economy in all five thematic priority areas of the Croatian S3 strategy. By employing more than 40 new researchers, buying new research equipment, invting relevant world class scientists, and by organizing summer schools and yearly workshop the project will enable the implementation of world-relevant scientific research and the transfer of knowledge and technology with a long-term contribution to the Croatian research sector, the economy and society as a whole.
(2017-2022, project manager: Prof. Ivan Petrović, UNIZG-FTTS representatives: Assoc. Prof. Edouard Ivanjko (local leader), Prof. Hrvoje Gold and Prof. Tonči Carić)
Link to project web page.
Project ideas & Collaboration opportunities
"Intelligent control of urban road traffic networks“
Today’s road traffic systems are prone to heavy daily congestions due to dense road traffic. This phenomenon is especially present in urban areas. According to studies, traffic congestion cost in the EU reaches up to 100 billion EUR yearly or about 1% of the annual EU’s GDP. Road traffic congestion mostly appears in densely populated urban areas where mostly no space for the further build-up of road infrastructure exists. To tackle this problem, new advanced road traffic management and control approaches are being intensively developed in the domain of Intelligent Transportation Systems (ITS). The goal of this project idea is to develop new control algorithms based on learning that improve their effectiveness during operation based on the autonomicity concept. Testing of the developed control algorithms will be done using calibrated simulation models of an urban network with near crossroads and a network of urban motorways. First results are already obtained using an ANFIS based control framework and reinforcement learning on an urban motorway network for the control cases of ramp metering and variable speed limit control. Additional results regarding traffic light control include full adaptive control (phase length and sequence) of a single intersection using fuzzy logic, genetic algorithm for fuzzy rules optimization and self-organizing maps for the improvement of Q-learning convergence.
(proposed project manager: Assoc. prof. Edouard Ivanjko)."Traffic control in a connected vehicle environment“
Autonomous and connected vehicles are being extensively researched and tested today. Their inclusion in today's traffic network will significantly change the user behavior and the corresponding traffic situation. In order to tackle this problem, simulation environments capable of simulating autonomous and connected vehicles will be developed, the influence of autonomous and connected vehicles on the traffic flow will be analyzed, and new advanced traffic control approaches will be developed capable of tacking mixed traffic flows (conventional and connected or autonomous vehicles) into account when creating the control output. Two phases of research are planned with the first phase of research dealing with the simpler traffic environment of urban motorways and the second dealing with an urban network of signalized intersections.
(proposed project manager: Assoc. prof. Edouard Ivanjko).
Past projects
Collaboration projects
ICT COST Action IC1406 “High-Performance Modelling and Simulation for Big Data Applications (cHiPSet)”
The Big Data era poses a critically difficult challenge and striking development opportunities in High-Performance Computing (HPC): how to efficiently turn massively large data into valuable information and meaningful knowledge. Computationally effective HPC is required in a rapidly-increasing number of data-intensive domains, such as Life and Physical Sciences, and Socioeconomic Systems.
Modelling and Simulation (MS) offer suitable abstractions to manage the complexity of analysing Big Data in various scientific and engineering domains. Unfortunately, Big Data problems are not always easily amenable to efficient MS over HPC. Also, MS communities may lack the detailed expertise required to exploit the full potential of HPC solutions, and HPC architects may not be fully aware of specific MS requirements.
Therefore, there is an urgent need for European co-ordination to facilitate interactions among data-intensive MS and HPC experts, ensuring that the field, which is strategic and of long-standing interest in Europe, develops efficiently – from academic research to industrial practice. This Action will provide the integration to foster a novel, coordinated Big Data endeavour supported by HPC. It will strongly support information exchange, synergy and coordination of activities among leading European research groups and top global partner institutions, and will promote European software industry competitiveness.
(2014.-2019., project manager: Prof. Joanna Kolodziej, Croatia MC members: prof. Tonči Carić and Assoc. prof. Edouard Ivanjko)
Link to COST web page, Link to Action web page.TUD COST Action TU1102 "Towards Autonomic Road Transport Support Systems"
A current, well recognised societal problem is the frequent failure of road transportation networks, resulting from traffic incidents, system overloading and lack of optimised support systems. The aim of this Action is to unite and align groups across Europe from computer science, engineering and transport studies into a world leading research community that will develop new ways of designing Road Transportation Support (RTS) systems based on the ideas of autonomic systems. If used as a platform on which to implement leading edge RTS technologies, such systems have the potential to deliver savings in the cost of system configuration, maintenance, and infrastructure, while potentially improving network efficiency and reducing the chances of human error. Using an autonomic approach to RTS is a novel and very ambitious idea requiring interdisciplinary community building, hence the need for COST, and a European dimension. This Action will bring together disparate strands of research into an integrated discipline, putting Europe at the leading edge of autonomic transportation system development. Additionally it will have the wider benefit of producing a transformative change within the field of autonomic systems itself that will translate to other application areas such as energy management.
(2011.-2015., project manager: prof. Thomas Leo McCluskey, Croatia MC members: prof. Edouard Ivanjko, prof. Sadko Mandžuka)
Link to COST web page, Link to Action web page.
Science projects
-
Innovative models and control strategies for intelligent mobility
This small project investigates new approaches to establish intelligent mobility for all traffic entities in urban environments. Emphasis will be set on creating realistic scenarios of urban traffic containing connected and autonomous vehicles (urban motorways and small networks of intersections), developing a simulation platform for testing of control approaches of urban traffic flows with connected and autonomous vehicles with different penetration rates based on learning agents, and developing new route optimization algorithms for electric vehicles. Additionally, bachelor and master students working in the scope of their theses will investigate the possibility of applying machine learning for traffic control of urban environments. All of this to improve the existing traffic control algorithms and the throughput of the already built urban road network that will have to more and more serve traffic flows with vehicles that contain a certain level of autonomous capabilities. This short-term support budget will be used to upgrade the existing high-end server and mobile work stations, graphic tablets to improve the remote teaching processes, and finance mobilities of young researchers to summer schools and international scientific conferences. In this small project's scope, existing cooperation with foreign researchers from Brazil, North Macedonia, Romania, and Switzerland will be continued and extended. The project is financed in the scope of the University of Zagreb short-term support program and partly by the Faculty of Transport and Traffic Sciences.
(May - December, 2020, project manager: Prof. Sadko Mandžuka) -
Investigation of the impact of autonomous vehicles on urban traffic flow characteristics
This small project aims to investigate the impact of autonomous vehicles on traffic flows in urban environments. Emphasis will be set on creating realistic scenarios of urban traffic that contain autonomous vehicles, developing a simulation platform for testing of control approaches of urban traffic flows with autonomous vehicles and developing new route optimization algorithms for electric autonomous vehicles. Additionally, bachelor and master students working in the scope of their theses will investigate the possibility of applying machine learning for traffic control of urban environments. All of this to improve the existing traffic control algorithms and the throughput of the existing urban road network that will have to more and more serve traffic flows with vehicles that contain a certain level of autonomous capabilities. The budget of this short-term support will be used to obtain one new high-end server, OBD sensors for tracking vehicle data, and finance mobilities of young researchers to summer schools and international scientific conferences. In scope of this small project, existing cooperation with foreign researchers from Brazil, North Macedonia, Romania and Switzerland will be continued and extended. The project is financed in the scope of the University of Zagreb short-term support program and partly by the Faculty of Transport and Traffic Sciences.
(September - December, 2019, project manager: Prof. Sadko Mandžuka) -
Application of deep learning in intelligent traffic control
The aim of this small project is to investigate the possibility of applying the paradigms of deep and reinforcement learning for traffic control on urban motorways. Emphasis will be set on variable speed limit control applied on a representative simulation model of an urban motorway. Additionally, bachelor and master students working in the scope of their theses will investigate the possibility of applying fuzzy logic for traffic light control of signalized urban intersections. All of this with the goal to improve the existing traffic control algorithms and the throughput of the existing urban road network. The budget of this short-term support will be used to obtain one new high-end server and desktop computer, finance mobilities of young researchers to summer schools and international scientific conferences, and for an advanced grammar checking software. In scope of this small project, existing cooperation with foreign researchers from Brazil, Bosnia and Herzegowina, Macedonia, and Romania will be continued and extended. The project is financed in the scope of the University of Zagreb short-term support program.
(May - December, 2018, project manager: Assoc. Prof. Edouard Ivanjko) -
Extraction of knowledge from big traffic databases based on methods for machine learning
The aim of this PROM-PRO support is to develop algorithms that can find relevant knowledge from big traffic databases that are publicly available or created by companies collaborating with the Faculty of traffic and transport sciences. Relevant knowledge is related to the estimation of the location of intersections in urban environments, vehicle movement patterns, queue lengths on intersections, and waiting times on intersections. This knowledge will be used to improve route optimization of road vehicles and traffic light control. The project is financed from the Faculty of transport and traffic sciences University of Zagreb in the scope of its PROM-PRO program for young prospective scientists.
(2017.-2019., project manager Juraj Fosin, Ph.D.) -
Methods for machine learning and knowledge extraction from big data set of vehicle tracks
The aim of this project is to use the existing Floating Car Data (FCD) archived in big data sets to extract hidden knowledge related to detection of the traffic state on a particular road segment, estimation of speed profiles on a road segment and extraction of vehicle movement patterns. All of this with the goal to improve the existing digital road maps, better forecast of speed profiles on urban roads, classification of drive patters for delivery vehicles and computation of optimal routes for delivery vehicles. The project is financed in the scope of the University of Zagreb short-term support program.
(June - December, 2017, project manager: prof. Tonči Carić) -
Navigation of electric vehicles with the criteria of minimal energy consumption
Electric road vehicles are more and more being included in today’s traffic. To ensure they optimal usage new routing algorithms are needed that take into account the road elevation in order to minimize the energy consumption. Additionally, the charging process has to be optimized so that the grid isn’t overloaded and the electric vehicle can be used as a short term energy source in times of increased electric energy consumption. In the same time, the charging costs have to be kept on a minimum. Goal of this project is to build a small scale electric vehicle using the Pioneer 3AT mobile robot, develop a simulation model for the built small scale electric vehicle and to develop new routing algorithms suitable for electric vehicles in urban environments. The project is financed from the Faculty of transport and traffic sciences University of Zagreb in scope of its PROM-PRO program for young perspective scientists.
(2015.-2017., project manager Assoc. Prof. Edouard Ivanjko) -
Simulator of a distributed control system for aircraft stabilization
Today’s passenger aircrafts are being constructed with the goal to maximally reduce their weight in order to maximize their payload. One way to reduce the weight is to apply a distributed wireless control system with intelligent sensors and actuators that contain processing power positioned near the actual measurement or acting place. The goal of this project is to build a hardware in the loop based simulator of distributed control system for aircrafts, develop a control algorithm for aircraft auto-stabilization, and check the suitability of the control system for different aircraft types. The project is financed from the Faculty of transport and traffic sciences University of Zagreb in scope of its PROM-PRO program for young perspective scientists.
(2015.-2017., project manager Karolina Krajček Nikolić, Ph.D.) -
Upgrade of a radar system for continuous measurement of traffic parameters
This short term support is intended for the continuation of the research started in the project "System for route optimization in a dynamic transport environment SORDITO". Research topics are related to detection of congestion areas and computation of speed profiles in urban environments, and to finish the build up of a system for traffic data collection. Existing four FMCW radars will be equipped with solar panels and a communication systems to establish a connection with a server for traffic data collection. With this upgrade continuous measurement of traffic data and creation of a larger data set will be enabled. Data about average daily traffic, average speed and queue length would be collected daily without the trouble of manually changing accumulators or manually collecting traffic data.
(June - December, 2016, project manager: prof. Tonči Carić) EU Structural fund project SORDITO "System for route optimization in a dynamic transport environment"
Projekt će razviti algoritam za optimiranje plana ruta distribucije koji će uvažavanjem vremenske komponente biti precizniji i izbjegavati zagušenja u prometu i riješiti realan gospodarstveni problem: kašnjenje u dostavama kao usluzi koja utječe na poslovanje i stabilnost tvrtke. Procjena je da će distributerske tvrtke/korisnici algoritma smanjiti troškove transporta do 30%. Dodatne koristi: manje opterećenje prometnog sustava, veća sigurnost sudionika u prometu, ušteda energenata, manja emisija ispušnih plinova. Ciljna skupina: zaposlenici Prijavitelja i Partnera, logističke tvrtke te sudionici u prometu.
Project partner is the Croatian company Mireo, Ltd.
(2014.-2016., project manager: prof. Tonči Carić)
Link Project web page.- Short term grant of University of Zagreb TP1.44
„Optimal navigation of small electric vehicles in indoor environments“
Aim of this short grant is to start a new research area in the field of navigation of small electric vehicles. In scope of this project a Hokuyo outdoor laser range finder will be purchased. Partner institution is the Faculty of mechanical engineering and naval architecture, University of Zagreb.
(2013.- 2014., project manager: prof. Tonči Carić). FP7 project ICSI "Intelligent Cooperative Sensing for improved traffic Efficiency"
Cooperative Intelligent Transport Systems is the future direction of mobility. Transportation assets will be increasingly integrated and will communicate through a wireless communications system. Travellers and goods carriers will have full knowledge of system performance and will be able to plan their journeys accordingly. The goal of the project is to define a new architecture to enable cooperative sensing in intelligent transportation systems and to develop a reference end-to-end implementation. The project results will enable advanced traffic and travel management strategies, based on reliable and real-time input data. The effectiveness of such new strategies, together with the proposed system, will be assessed in two field trials.
(2012.-2015., project manager: Cordiviola Elena, local project leader: prof. Sadko Mandžuka)
Link Project web page, Link local FPZ Project web page.IPA IIIc project VISTA "Computer Vision Innovations for Safe Traffic"
The overall objectives of the action are strengthening of technology transfer and commercialization capacities of partner HEIs, transfer of existing computer vision applications from HEIs to SMEs, and developing new traffic- and transportation-related computer vision applications with commercial potential in collaboration with SMEs in the automotive industry sector. The overall objectives will be achieved through two specific objectives. The first specific objective is conducting R&D activities towards commercialization of specific innovative computer vision applications. Implementation of R&D activities requires purchase of research equipment and employment of R&D engineers, which will represent enhancement of the R&D capacity. R&D results on seven computer vision applications will enhance amount of intellectual property that will be available for commercialization.
(2013.-2015., project manager: prof. Sven Lončarić, local project leader: prof. Hrvoje Gold)
Link Project web page, Link local FPZ web page.- Short term grant of University of Zagreb 2013-ZUID-21,5.4.1.2 –
„Vehicle fleet route optimization using multi-agent optimization algorithms and real time traffic data“
Aim of this project was to develop algorithms for vehicle fleet route optimization using real time traffic data and not a static road traffic network model. In scope of this grant a Pioneer 3AT mobile robot was purchased. Partner institutions were the Ruđer Bošković Institute and the Faculty of Technical Sciences, Sv. Kliment Ohridski University, Republic of Macedonia.
(2013.- 2014., project manager: prof. dr. sc. Tonči Carić). - Project of the Croatian Ministry of science, education and sports 135-1352598-2581 –
„Development Methodology of Integrated Adaptive Transport-logistic Systems“
Efficient and effective development of integrated intelligent transport-logistics systems (ITLS) require coupling of different domains of knowledge, methods and tools which can operate with smart ITLS strucutres and processes in real-time. The main problem in end-to-end transport service and transport chains realisation is on the interface between separated and different physical, logical and organisation systems i.e. when the transport modes or the network operator is changed. Classical analytical and numerical methods of "hard" optimization are not suitable for transport-logistics problem with real-time data collecting. Methodological experiences from development of air traffic control, traffic and travel management, emergency management, demonstrate need for upgrading methodological approach and tools for intelligent adaptive transport-logistics networks development. Basic change is shift away from fragmented and static observing to higher levels of cooperation and service coordination with elimination of mode changing barriers., change of operators, crossboarders etc. In the first phase of the ITS development the focus is on the ITS technology development and preliminary architecture design focused on road traffic and transport but in the future it is necessary to generate ITS knowledge and adapted methods oriented to end user service, safety and security. Explanatory multilayer model and adapted multiagent methods will be tested on the prototip of mobile warehouse and in simulation laboratory of logistic-distribution centre with ITS functionalities.
(2006.-2013, project manager: prof. dr. sc. Sadko Mandžuka).
Link MZOS web page, Link Institution web page - Project of the Croatian Ministry of science, education and sports 036-0363078-3018 –
„Control of mobile robots and vehicles in unknown and dynamic environments“
Mobile robotics is an interdisciplinary scientific discipline, which has been evolving very intensively for the last twenty years. Various mechanical constructions of a mobile robot and its drive mechanism, as well as electrical and electronic implementation of drives, sensors, power supplies and control systems, are being researched. While a selection of mechanical construction, drive mechanism, sensors and power supplies dominantly depends on the robot application, the control system is mostly generic so it can be developed application-independent. A number of research groups of reputable universities around the world have developed their own mobile robot control systems (among them is this project proposer’s group), but a number of open-end research problems still remains. Particularly, the most control systems are tested in laboratory environments, which are assumed to be structured and stationary, but the direct, specific goal of the proposed project is to develop mobile robots and vehicles control system, which will enable fully autonomous navigation in unknown, unstructured and dynamic environments. In order to systematically solve this complex problem, probabilistic multisensor fusion methods, optimal state estimation of nonlinear stochastic systems with multimodal measurement uncertainties, advanced automatic control methods, artificial intelligence and decision-making methods will be applied. The most important expected result of the proposed research is a generic library of advanced mobile robot control functions, which can be easily applied to different designs of autonomous mobile robots and vehicles as well as to different applications in unknown and dynamic environments. Every developed algorithm will be experimentally tested in computer simulations and on available mobile platforms. Also, it is expected that some of them will find particular industrial application even before the project ends. Proposed research could be very valuable to the Republic of Croatia, having in mind expected large expansion of autonomous mobile robots and vehicles applications in the world and the possibility for small high-tech companies to participate on that market. In that sense, this project could be stimulation for forming such high-tech companies, so that this opportunity wouldn’t be missed, as was the case with the automotive industry.
(2006.-2011., project manager: prof. dr. sc. Ivan Petrović).
Link MZOS web page, Link Institution web page - Project of the Croatian Ministry of science, education and sports 003618 –
„Intelligent Control of Mobile Robots“
In this project, methods, algorithms and structures for control of mobile robots are being investigated, which should ensure full autonomy of motion of mobile robots based on sensor measurements and without prior preparation of the environment. In order for the control system to fulfil this complex task, it must have the capabilities of estimating the mobile robot's current position and orientation, map building and path planning in the environment. When investigating solutions to these problems, core implementation is expected in intelligent methods, especially concerning neural networks and fuzzy logic, methods of stochastic reasoning and fusion methods of several sensors. Based on knowledge acquired so far and investigations planned, it is expected that further insight in the possibilities and constraints of intelligent methods for mobile robots will be gained with an appropriate contribution to their further development. Moreover, it is expected that a thorough and scientific base for development, design and implementation of control system will be developed, which will ensure quality, safety and energy efficiency of various applications of autonomous mobile robots. The overall result is to be a generic library of programming functions of an intelligent control system applicable to a large class of various mobile robots, ranging from cheap domestic and leisure robots to expensive robots for complex applications in industry, construction, agriculture, etc. The whole set of programming functions will be implemented on the experimental mobile robot already available, anticipating possible implementations on other types of robots.
(2003.-2006., project manager: prof. dr. sc. Ivan Petrović).
Link MZOS web page, Link Institution web page - Project of the Croatian Ministry of science, education and sports 036006 –
„Process automation - new control approaches“
The most important particular aims of research in the project are:
Intense scrutiny of dynamics of wide class of technical processes and the development of suitable mathematical models. Equipping Laboratory for automation of plants and processes with physical models of the typical industrial processes and with evaluation tools for algorithms development and implementation. Concentrated study of new process identification methods, with special interest in application of artificial neural nets. Integral research of modern methods and structures (neural, fuzzy and predictive) used in control of nonlinear time variable processes. Research of control algorithms used in position tracking systems with complex kinematic structure. Comparative analysis of modern and conventional identification methods and control algorithms considering possible applicability in industry. Forwarding of new results in control theory from academic level to the level of application in industry; implementing control solutions on plants and processes in industry. Modernization of undergraduate and graduate education with modern notions learned during work on this project.
(2001.-2003., project manager: prof. dr. sc. Nedjeljko Perić).
Link MZOS web page, Link Institution web page
Application projects
- Petrović, Ivan; Ivanjko, Edouard; Seder, Marija; Kitanov, Andreja.
Program system for autonomous navigation of indoor mobile robots
University of Zagreb Faculty of Electrical Engineering and Computing, 2004.-2006.
- Petrović, Ivan; Ivanjko, Edouard; Petrinić, Toni.
AMORsim – mobile robot simulator for MATLAB
University of Zagreb Faculty of Electrical Engineering and Computing, 2004.-2006.
- Ivan Petrović, Mišel Brezak, Edouard Ivanjko, Marija Đakulović, Andreja Kitanov, Damir Josić,
Host Mobile Robot at the Croatian Booth at the 10th International Architecture Exhibition in Venice
This project is a funny application of our research results in the mobile robots control and navigation. The task of our robot was to amuse the visitors of the Croatian Booth at the 10th International Architecture Exhibition in Venice from September 10 to November 19, 2006, eight hours a day.
10th International Architecture Exhibition in Venice with sponsorship of Croatian Ministry of Culture, Venice, Italy, 10.09. – 19.11. 2006. Project documentation of the Ethernet installation in Clinical Hospital Center „Sestre milosrdnice“ Zagreb
in collaboration with company Infosistem d.d. during civil military service, 2004. (project associate)
Collaboration with industry
Education of industry participants in Siemens Step7 PLC technologies
University of Zagreb Faculty of Electrical Engineering and Computing, Siemens AG Croatia, 2001.-2009.