Ongoing Projects

AIFORS - ERA Chair in Artificial Intelligence for Robotics

Short description

The six-year AIFORS project will create an ERA Chair in Artificial Intelligence for Robotics at the University of Zagreb Faculty of Electrical Engineering and Computing (UNIZG-FER). This ERA Chair will be an outstanding researcher who will establish and lead a Research Group for Artificial Intelligence for Robotics (AIFORS Research Group) and contribute to implementation of organizational changes at UNIZG-FER. The AIFORS Research Group will be assigned to LAMOR and the ERA Chair holder will report to the Head of the Laboratory. This will open UNIZG-FER to a new research direction with a high potential for research outputs and technology innovation. The project will also allow UNIZG-FER to drive structural changes to increase their capacities for research funding, to encourage researchers’ mobility, to align the human resources and research management policies to the European Research Area principles, and to better disseminate and exploit research results. It is expected that the AIFORS project will significantly step up UNIZG-FER’s research and innovation excellence and build capacities to sustain it beyond the project and across research groups.

Funding H2020 - H2020-WIDESPREAD-2018-2020 ERA Chairs (Total budget:

2.5 million EUR, UNIZG-FER: 2.5 million EUR)

Duration 01.01.2021 - 31.12.2026
Website https://aifors.fer.hr

FITNESS - Flexible IntelligenT NEar-field Sensing Skins

Short description

The main project objective consists in realizing smart flexible surfaces with sparse electronics, using advanced electromagnetic metasurfaces, with sensitivity that decreases with distance from the surface. Short term applications lie in the field of robotics; long-term ones in the field of healthcare.

Funding HORIZON-EIC-2022-PATHFINDEROPEN (Total budget:

3.6 million EUR)

Duration 01.04.2023 - 31.03.2027
Website https://fitness-pathfinder.eu/

DRUMS - Deep Tech & Robotics for Human-Centered Manufacturing Systems

Short description

In the DRUMS project, a learning platform, didactic guidelines and teaching materials for Vocational and Educational Trainings (VETs) and learning materials for their students will be created. The learning plattform, the didactic guidelines and the teaching and learning materials should provide approaches to further automate the manufacturing sector, make it more efficient and, above all, more sustainable. 

The teaching and learning materials will be developed on the following main topics:

  • Manufacturing
  • ICT technologies in manufacturing
  • Robotics (industrial and collaborative)
  • Artificial intelligence in robotics and manufacturing
  • Sustainability
Funding Erasmus+
Duration 01.01.2024 - 31.12.2026
Website https://www.tuwien.at/en/mwbw/ikp/klft-ecodesign/ecodesign/research-projects/awareness-building/drums

DATACROSS - The Centre of Research Excellence for Data Science and Advanced Cooperative Systems

 
Short description

The Centre of Research Excellence for Data Science and Advanced Cooperative Systems is the first centre of excellence in the field of technical sciences in Croatia. The Centre brings together researches from thirteen renowned organizations, including eleven higher education institutions from Zagreb, Split, Rijeka, Osijek and Dubrovnik, as well as the Ruđer Bošković Institute and the company Ericsson Nikola Tesla. The Centre comprises two research units: the Research Unit for Data Science (DATASCIENCE) and the Research Unit for Cooperative Systems (ACROSS). Find out more about the participating organizations here.

The vision of the centre is to establish itself as the leader in research and development of new methods and advanced engineering approaches related to data science and cooperative systems.

The mission of the centre is to advance Croatian science and strengthen its inclusion in the European Research Area, in particular by promoting the participation in EU and other international research programmes. The centre fosters cooperation between the academic community and the public sector in the specific research areas that are in the focus of the Centre.

Principal Investigator Ivan Petrović (coordinator of the Research Unit for Cooperative Systems)
Researchers Marija Seder, Ivan Marković
Partners University of Zagreb Faculty of Mechanical Engineering and Naval Architecture, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Faculty of Science, Faculty of Transport and Traffic Sciences, University of Rijeka Faculty of Engineering and Faculty of Civil Engineering, University of Osijek Faculty of Electrical Engineering, Computer Science and Information Technology, University of Dubrovnik, Ericsson Nikola Tesla, Ruđer Bošković Institute, Catholic University of Croatia, Center for Advanced Computing and Modelling
Website across-datascience.zci.hr

DATACROSS - Advanced methods and technologies in Data Science and Cooperative Systems

Short description

DATACROSS is a project of the Centre of Research Excellence for Data Science and Advanced Cooperative Systems dealing with research problems of developing advanced methods and technologies for heterogeneous data analysis and complex cooperative system shaping.
Considering strategic documents between the European Union and Republic of Croatia, the project DATACROSS is connected to “Partnership Agreement Republic of Croatia 2014HR16M8PA001-1.2” and “Operational Programme Competitiveness and Cohesion 2014-2020”.
DATACROSS represents a milestone because it will strongly strengthen the research capacity of the Centre of Research Excellence by employing and improving more than 40 new young project researchers, which will enable the high intensity of top-level scientific research and the transfer of knowledge and technology to the economy. That will have significant positive effects on the strengthening of the Croatian research sector and the economy, as well as the society in general.

Funding European Regional Development Fund (Total budget: €5.060.000, UNIZG-FER: €5.060.000)
Principal Investigator Ivan Petrović (coordinator)
Researchers Marija Seder, Ivan Marković
Website across-datascience.zci.hr/en/datacross

Past Projects

A-UNIT - Research and development of an advanced unit for autonomous control of mobile vehicles in logistics

 
Short description

The proposed project effectively addresses the central problem that exists in the market today - the inability to adequately meet the needs for business automation within the logistics and distribution processes. By implementing the project, the company plans to develop an advanced unit for autonomous control of mobile work vehicles (forklifts, towing vehicles, sweepers) that are now man-operated, based on 3D perception technology and artificial intelligence. The project will result in an increase in sales, export revenues, and the creation of 36 new jobs, which will enable the growth of the company's competitiveness in the global market. The target groups of the project are the company itself, the project partners, and their employees.

Funding ESI ERDF - European Regional Development Fund (Total budget: 40.482.556,95 HRK, UNIZG-FER budget: 5.851.334,30 HRK)
Duration 17.08.2020 - 16.08.2023
Project Team

Ivan Petrović, Marija Seder, Ivan Marković, Marta Čolaković-Bencerić,

Jelena Gregorić, Karlo Koledić

Partners Gideon Brothers d.o.o., Mobilisis d.o.o.

EKO-KOMVOZ - Development of environmentally friendly vehicle for cleaning public surfaces with autonomous control system based on artificial intelligence

 
Short description

 

The purpose of the project is to develop an environmentally friendly vehicle for cleaning public surfaces with assistance systems to the vehicle operator and systems of autonomous control of vehicle operation elements based on artificial intelligence, as well as a system for remote monitoring of vehicles and air quality in urban areas that will use three different propulsion systems, including electric propulsion and hydrogen propulsion cells.

By developing and marketing a new product in three versions on the global market, the project will contribute to the achievement of the general goal - Contribution to the growth of innovation competitiveness of the Republic of Croatia in
in the field of environmentally friendly transport solutions and reduction of air pollution in urban areas.

Project activities begin in the phase of industrial research of three key components of an environmentally friendly vehicle for cleaning public surfaces with autonomous control systems based on artificial intelligence:

  • the concept of vehicles for cleaning public surfaces on 3 types of plants, including electric propulsion and hydrogen fuel cells;
  • the concept of a system of assistance to the vehicle operator in operation and a system of autonomous control of the elements of operation of vehicles for cleaning public areas;
  • the concept of a system for remote monitoring of vehicles and air quality in urban areas.
Funding ESI ERDF - European Regional Development Fund (Total budget: 37.310.517,81 HRK, UNIZG-FER budget: 5.392.275,65 HRK)
Duration 17.02.2020 - 16.08.2023
Project Team

Ivan Petrović, Ivan Marković, Igor Cvišić

Ivan Bilić

Partners RASCO d.o.o.

Visual Localization of Sports Cars

 
Short description

The purpose of this project is to develop a visual localization algorithm for sports cars that can accurately and reliably localize high-speed cars in challenging feature-poor environments.

Funding Rimac Automobili d.o.o.
Duration 05.2020 - 05.2023.
Project Team

Ivan Petrović, Ivan Marković, Igor Cvišić, Antea Hadviger

ezDD - Deep Driving

 
Short description

The purpose of this project is to provide a survey of the state-of-the-art of autonomous driving research and devise a concept of the system for multi-sensor environment data collection in Croatia that is aligned with ETRI needs, including an initial example of a dataset recorded in Zagreb.

Funding Electronics and Telecommunications Research Institute (ETRI), Republic of Korea
Duration 2020.
Project Team

Ivan Petrović, Ivan Marković, Igor Cvišić

SafeLog - Safe human-robot interaction in logistic applications for highly flexible warehouses

Short description The European market for e-commerce is growing rapidly, with more than 16% just in the year 2014. With the internationalization of distribution chains, the key for success lies within efficient logistics. In such facilities,
goods for the end-user or products in the B2B sector are stored, commissioned and shipped. To manage the supply chains, many new warehouses have been erected and more will follow. With the growing markets, the need for larger warehouses and their automation increases. To advance the position of the European trade sector, technical restrictions on the size of warehouses should be avoided and new automation paradigm should be implemented to ensure their efficient operation. Therefore the European robotic and automation companies should be able to provide appropriate solutions, making scalable systems and scalable software mandatory. Current automation solutions based on strict separation of humans and robots cannot provide such efficient operation of large warehouses. SafeLog aims to overcome this issue by enabling much more efficient warehouse concepts joining human and robot workforce. Given that, the overall objective of SafeLog is the conception and implementation of a large-scale flexible warehouse system which enables safe and efficient collaboration of humans and robots in the same area and at the same time. On the way to reach this objective SafeLog will develop, integrate and test: (1) a holistic and certifiable safety concept based on the safety vest, which allows the collaboration of robots and humans in a flexible warehouse system, (2) planning and scheduling algorithms for a heterogeneous fleet manager, which allow the adhoc reactive planning and scheduling for human and robot workforce in a flexible warehouse system,
and (3) augmented reality based interaction strategies to support workers in a robotized warehouse system with information about their current task and environment.
Funding EU H2020-ICT-2015 (Total budget: €4.618.462, UNIZG-FER: €698.405)
Principal investigator Ivan Petrović, Ivan Marković
Researchers Marija Seder, Igor Cvišić, Goran Popović, Tomislav Petković
Partners Karlsruhe Institute of Technology (coordinator Björn Hein), Swisslog,  Czech Technical University in Prague, Fraunhofer Institute for Material Flow and Logistics, Končar Electrical Engineering Institute
Website safelog-project.eu

L4MS - Logistics for Manufacturing SMEs

Short description

The project will establish a Pan-European ecosystem of Competence Centres (CCs) supported by Logistics for Manufacturing SMEs (L4MS) marketplace. The objective is to facilitate the take up of logistics automation by manufacturing SMEs across Europe by acting as a broker between SMEs who seek solutions and financing and the CCs and their ecosystem who are interested to provide consulting, solutions, best practices and areas for demonstration and experimentation. Central to the ecosystem is a marketplace which provides access to support services with tools and online helpdesk thus providing a single point of access to the SMEs. Six strategically located CCs and several regional associations, Digital Innovation Hubs and consulting agencies will establish the ecosystem.  An Open Platform for Innovations in Logistics (OPIL) will be developed to provide latest navigation, localization, mapping and traffic management services and IOT infrastructure for logistics automation. Cross border Application Experiments (AE) will be used to deploy OPIL for small and flexible logistics solutions requiring no infrastructure change, no production downtime and no in-house expertise, making investment in logistics automation attractive for manufacturing SMEs. AEs will be developed with the infrastructure of already participating and new CCs. Results from AEs will be used to advance the OPIL and enrich L4MS marketplace with business success stories. The business sustainability of the L4MS marketplace as a potential start-up and its ecosystem comprising of CCs, regional DIHs, industry associations and technology suppliers will be the focus of the work, adopting the already developed best practice in I4MS phase 2.

Funding H2020-FOF-2017, (Total budget: €8,709,130, ICENT: €276,625)
Principal Investigator Ivan Petrović
Researchers Marija Seder, Ivan Marković, Davorka Moslavac Forjan
Partners

Teknologian tutkimuskeskus VTT Oy (coordinator), Asociatia Producatorilor De Mobila Din Romania, Automatismos Y Sistemas De Transporte Interno, S.A.U., Chemi-Pharm AS, Technologiko Panepistimio Kyprou, European Dynamics Advanced Systems of Telecommunications Informatics and
Telematics Sa, Engino.net Ltd., Fundingbox Accelerator Sp Zoo, Hermia Yrityskehitys Oy, IMECC OÜ, Fraunhofer Gesellschaft Zur Foerderung Der Angewandten Forschung E.V., Kine Robot Solutions Oy, Lithuanian robotics association, MURAPLAST d.o.o., Fundacio Barcelona Mobile World Capital Foundation, Odense Robotics, Pannon Gazdasagi Halozat Egyesulet, Politecnico di Milano, Visual Components Oy

Website http://www.l4ms.eu/

DIH2- A Network of Robotics DIHs for Agile Production

Short description

DIH² is a network of 26 DIHs, with a target to reach over 170 DIHs. The sole aim of the network is to spark incremental (cut 50% cost of advance robotics solutions, double the growth of robotics market) and disruptive (maximum productivity & optimum agility) innovations in over 300,000 Manufacturing SMEs and Mid-Caps. It will support SMEs in their Agile Production challenge (50% increase in productivity) and unleash their digitalization potential by enabling robot solutions that are more cost effective at lower lot sizes.

Funding H2020-DT-2018-1, (Total budget: €16,834,085, ICENT: €152,820)
Principal Investigator Ivan Petrović
Researchers Marija Seder, Ivan Marković, Davorka Moslavac Forjan
Partners

Teknologian tutkimuskeskus VTT Oy (coordinator), Aries Transilvania, BrainsBusiness, Information Technologies Institute, CyRIC, European Dynamics, Digital.Hub Logistics, EProsima, FundingBox, International Data Spaces Association, Fraunhofer IML, Irish Manufacturing Research, ISDI, iTechnic GmbH, Linz Center of Mechatronics, Blumorpho, Intemac, Lithuanian Robotics Association, Loupe 16, NCR, sirris, VATP, Pannon Businees Network, Produtech, Proxinnov, Pomurski tehnološki park

Website http://dih-squared.eu/

SafeTRAM - System for Increased driving safety in public urban rail traffic

 

The goal of the SafeTRAM project is to develop an innovative system which would increase  traffic safety by implementing safety functions for urban rail traffic, thus lowering the number of accidents causing great material damage and human casualties. Electric trams use up to five times less energy than an automobile, do not pollute the environment and have a number of ecological advantages with respect to road traffic, which is responsible for 95% of traffic gas emissions. In the near future, systems like  SafeTRAM will be a key element of autonomous vehicles which is one of the final goals of the modern society.

Funding European Regional Development Fund (Total budget: €2.460.000, UNIZG-FER: €751.500)
Principal Investigators Ivan Petrović, Marija Seder, Ivan Marković,
Researchers Igor Cvišić, Juraj Peršić, Josip Ćesić, Kruno Lenac
Partners Končar Electrical Engineering Institute (coordinator)

MAS - Development of a multi-functional anti-terrorism system 

 

The analysis of states in counterterrorism and anti-terrorism forces (military units conducted by counterterrorism and anti-terrorist police forces) undoubtedly points to the very serious lack of adequate remotely-controlled vehicles and systems that can respond to the challenges of contemporary terrorism. The same situation exists in the market of remotely-controlled systems for other purposes in the security and defence sector (military, police and civil). This project develops a multi-functional anti-terrorism system (MAS), consisting of a remotely-controlled anti-terrorism attack vehicle and a transport-logistic and commanding operating module on an on-road vehicle (commuter vehicle) that will find its applications in these market sectors.

Funding European Regional Development Fund (Total budget: €3.670.000, UNIZG-FER: €380.000)
Principal Investigator Ivan Petrović
Researchers Marija Seder, Ivan Marković, Filip Marić, Ana Šelek, Demijan Jurić, Anđela Čirjak
Partners DOK-ING (coordinator)

DUV-NRKBE - Development of a remotely controlled vehicle for operation in extreme CBRNe conditions 

 

The goal of the DUV-NRKBE project is to develop a remotely controlled vehicle for acting in extreme Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNe) conditions. It will be a unique system on continuous tracks which will give the end user a capability to work in extreme heat zones - in conditions where a human could not survive, along with an array of tools and sensors with which it will perform various missions and drastically shorten the time and intensity of accidents. Furthermore, besides remote control one of the goals of the project is to enhance the vehicle with autonomous capabilities such as autonomous patrolling, laser cartography etc.

Funding European Regional Development Fund (Total budget: €2.440.000, UNIZG-FER: €260.190)
Principal Investigator Ivan Petrović
Researchers

Marija Seder, Ivan Marković, Filip Marić, Ana Šelek, Demijan Jurić, Anđela Čirjak, Marta Čolaković-Bencerić, Juraj Peršić, Tomislav Petković  

Partners DOK-ING (coordinator)

ACROSS - Centre of Excellence for Autonomous and Cooperative Robotic Systems

Short description

The overall objective of the project is to create a Centre of Excellence for Autonomous and Cooperative Robotic Systems in Croatia (ACROSS CoE), which will be at the forefront of research and innovation of novel methodologies and advanced engineering approaches in the targeted domains. ACROSS CoE will be created and run as a long-term joint venture between the UNIZG-FER  ̵ University of Zagreb Faculty of Electrical Engineering and Computing, the KTH  ̵ Royal Institute of Technology, and the ICENT  ̵ Innovation Centre Nikola Tesla. To achieve the overall objective, the proposal focuses on long-term objectives for Teaming Phase 2 and on one-year objective for Teaming Phase 1. Long-term objectives of the Phase 2 and beyond are: (i) Reinforcing scientific capacity and innovation performances in autonomous and cooperative robotic systems, (ii) Increasing scientific visibility and reputation at international level, and (iii) Improving responses to socioeconomic needs of Croatia. ACROSS CoE will achieve these objectives by striving for high quality research, in line with international standards of excellence, and by directing its research towards areas serving the technological needs identified by the Croatian Smart Specialisation Strategy. The ultimate objective of the Phase 1 is to produce an extensive, detailed, and robust Business Plan for ACROSS CoE; and to achieve this, the plan will be built upon (i) Assessment of the existing ACROSS ecosystem and (ii) Development of roadmaps for achieving ACROSS CoE excellence. The ACROSS project is relevant to the work programme since the main goal is to create a new Centre of Excellence in Croatia, a low R&I performing country, by building upon partnership with KTH, a world leading scientific and innovation institution. Creation of the ACROSS CoE will help Croatia in attaining a competitive position in the global value chains, thus also contributing to Europe’s competitiveness and its ability to address future societal challenges.

Funding H2020-WIDESPREAD-2016-2017 Teaming, (Total budget: €400.000, UNIZG-FER: €185.000)
Principal Investigator Ivan Petrović
Researchers Zoran Vukić, Zdenko Kovačić, Stjepan Bogdan, Mato Baotić, Jadranko Matuško, Mario Vašak, Nikola Mišković, Marija Seder, Ivan Marković, Matko Orsag
Partners

KTH – Royal Institute of Technology, Innovation Centre Nikola Tesla

RoboCom++ -  Rethinking Robotics for the Robot Companion of the future

Short description

The main objective of the RoboCom++ project is to lay the foundation for a future global interdisciplinary research programme (e.g., a FET-Flagship project) on a new science-based transformative robotics. RoboCom++ will gather the community and organise the knowledge necessary to rethink the design principles and fabrication technologies of future robots. RoboCom++ will aim at developing the cooperative robots (or Companion Robots) of the year 2030, by fostering a deeply multidisciplinary, transnational and federated effort. The RoboCom++ community will pursue these ambitious objectives by cooperating along three main lines of action: 1) building the community and the tools for research reproducibility (benchmarks, metrics, data sharing protocols, test platforms, standards); 2) proof-of-concept research pilots; and 3) defining the long-term S&T roadmap, competitiveness strategy, governing and financing structure, and the ethical, legal, economic and social framework of a future FET Flagship.

Funding FLAG-ERA JTC 2016 (Total budget: €4.216.718, UNIZG-FER: €125.000)
Principal Investigator Ivan Petrović
Researchers Marija Seder, Ivan Marković
Partners

University of Zagreb Faculty of Electrical Engineering and Computing (LARICS, LABUST), Scuola Superiore Sant’Anna/The BioRobotics Institute (coordinator Paolo Dario), Université Libre de Bruxelles, Tallinn University of Technology, Centre National de la Recherche Scientifique, Laboratoire National de Métrologie et d’Essais, Istituto Italiano di Tecnologia, Riga Technical University, National Institute for R&D in Microtechnologies, Universitatea Transilvania Brasov, Ecole Polytechnique Fédérale de Lausanne, Middle East Technical University, University Carlos III of Madrid, Weizmann Institute of Science, Czech Technical University, Czech Institute of Informatics, Robotics and Cybernetic, Vrije Universiteit Brussel, National Technical University of Athens,Universitat Politecinca de Catalunya, Cognitive Systems Research Institute, Technical University of Kosice, University of Plymouth, University of Twente, Consorzio Nazionale delle Ricerche/ Istituto di Studi sui Sistemi Intelligenti per l'Automazione

Website http://robocomplusplus.eu/

Human localization and intention recognition based on wearable sensors

Short descrption

According to the recent report by the International Robotics Federation (IFR, www.ifr.org/industrial-robots/statistics) linking the real-life factory with virtual reality will play an increasingly important role in global manufacturing. Furthermore, it is also stated that global competition requires continued modernization of production facilities and that growing consumer markets require expansion of production capacities. For example, the European market for e-commerce is growing rapidly, with more than 18,6% just in the year 2015. With the growing markets, the need for larger warehouses and their automation will only increase. To advance the position of the European manufacturing and trade sector, a new automation paradigm should be implemented to ensure their efficient operation. According to the same IFR report, robots and human-robot collaboration will play an important role in the upcoming years. And indeed, robots are nowadays able to successfully solve complicated tasks like autonomous transport and autonomous manipulation. Yet, when it comes to human-robot collaboration, cooperation, or generally speaking coexistence, the main barrier is safety as it typically affects performance and costs of the robot system. Current automation solutions in manufacturing and logistics is based on strict separation of humans and robots. In order to enable coexistence of humans and robots in the same environment, one of the prerequisites is to know the location of the humans in the warehouse and predict their intentions. This project aims to overcome this issue by developing methods for human indoor localization and intention prediction based on wearable sensors. This approach also enables solving the project problem with minimal changes to the environment. Furthermore, wearable sensors can also be used to provide online information to workers, e.g., via an augmented reality (AR) device, thus even further increasing the working efficiency and link the real-life factory with virtual reality.

Funding German Academic Exchange Service and Croatian Ministry of Science and Education (Total budget: €17.000, UNIZG-FER: €6.000)
Principal investigator Ivan Marković
Researchers Josip Ćesić, Kruno Lenac, Tomislav Petković, Juraj Peršić
Partner Björn Hein, Karlsruhe Institute of Technology

cloudSLAM - Cooperative cloud based simultaneous localization and mapping in dynamic environments

Short description

Over the last several decades, robotics has been a key technology for achieving high productivity and industrial competitiveness. Recently, robotics has begun expanding intensively outside of industrial settings, thus bringing robots closer and closer to humans. The main robotics challenges in the coming decade will be to develop robotic systems that can safely cooperate with humans in arbitrary settings and that are capable of autonomously performing complex tasks in human environments.

One of the main prerequisites for robot autonomous operation in unknown environments populated by humans or other robots is to perform simultaneous localization and mapping (SLAM) so that the robot can infer its position and relate it to other objects of interest. The main focus of the cloudSLAM project is to develop algorithms for solving the SLAM problem such that robots can operate reliably even in highly dynamic environments. This will be achieved through a mathematical framework accurately describing the non-Euclidean geometry of objects moving in space and through robot cooperation via a cloud based service.

The methodology of the proposed project will be grounded in a novel estimation approach based on the recently developed Kalman filter on Lie groups. We will estimate the state of the robot and the tracked objects in six degrees of freedom by representing the state with the special Euclidean group (SE3) and performing filtering directly on the introduced group. This way, the non-Euclidean nature of the orientation components will be intrinsically respected, while their uncertainty will be correctly coupled with the uncertainty of the Euclidean members of the SE3 group through the joint covariance matrix.Since the idea of cloudSLAM is to exploit the moving objects for enhancing the SLAM performance, we will develop algorithms for multiple object detection and tracking using Lie groups and random finite sets theory. This result will then serve as an input to a dynamic SLAM algorithm. The dynamic SLAM will also be based on Lie groups, where we will develop an algorithm based on the exactly sparse delayed state filter so as to keep the computational complexity reasonable. Finally, all the information will be shared by multiple agents through a common cloud-based service, thus enabling robots which have just started operating to immediately exploit the experience of veteran team members. The proposed framework will be tested in coordinated exploration scenarios involving heterogeneous teams moving in dynamic environments, including aerial and ground vehicles and human operators.

Funding Unity Through Knowledge Fund (Total budget: €244.470, UNIZG-FER: 244.470)
Principal investigator Ivan Petrović, Ivan Marković
Researchers Kruno Lenac, Josip Ćesić
Partners University of Waterloo (principal investigator Dana Kulić)
Website cloudslam.fer.hr

EuRoC - European Robotics Challenges

Short descrption

The European manufacturing industry needs competitive solutions to keep global leadership in products and services. Exploiting synergies across application experts, technology suppliers, system integrators and service providers will speed up the process of bringing innovative technologies from research labs to industrial end-users. As an enabler in this context, the EuRoC initiative proposes to launch three industry-relevant challenges:

  • Reconfigurable Interactive Manufacturing Cell (RIMC),
  • Shop Floor Logistics and Manipulation (SFLM),
  • Plant Servicing and Inspection (PSI).    

It aims at sharpening the focus of European manufacturing through a number of application experiments, while adopting an innovative approach which ensures comparative performance evaluation. Each challenge is launched via an open call and is structured in 3 stages.

45 Contestants are selected using a challenge in a simulation environment: the low barrier of entry allows new players to compete with established robotics teams. Matching up the best Contestants with industrial end users, 15 Challenger teams are admitted to the second stage, where the typical team is formed by research experts, technology suppliers, system integrators, plus end users.

Teams are required to benchmark use cases on standard robotic platforms empowered by this consortium. After a mid-term evaluation with public competition, the teams advance to showcasing the use case in a realistic environment. After an open judging process, 6 Challenge Finalists are admitted to run pilot experiments in a real environment at end-user sites to determine the final EuRoC Winner.

A number of challenge advisors and independent experts decide about access to the subsequent stages. A challenge-based approach with multiple stages of increasing complexity and financial support for competing teams will level the playing field for new contestants, attract new developers and new end users toward customisable robot applications, and provide sustainable solutions to carry out future challenges.

Funding EU FP7
Principal investigators Ivan Petrović, Stjepan Bogdan
Researchers Igor Cvišić, Andrej Kitanov
Partners University of Zagreb Faculty of Electrical Engineering and Computing (LARICS), University of Dubrovnik, Diagnostiqa Consultoria Tecnica S.L.
Website http://www.euroc-project.eu/index.php?id=bladehunters

Creating thermal information models of existing buildings by active exploration

Short descrption

Europeans need to save energy. Mayor energy savings can be achieved by preventing heating and air conditioning losses due to thermal bridging, air leakage, discontinuous insulation, air infiltration, and structural defects in buildings, as much as 39 % and 32 % of the energy used is required for heating, cooling and ventilation in residential and commercial buildings, respectively. To create a methodology for cost effective renovation of existing buildings it is essential to have detailed semantic thermal 3D models thereof.

The focus of this project is to extract precise digital models from existing buildings. To ensure that data acquisition is carried out in a complete, accurate and efficient way, novel methods are developed within this project to explore the environment autonomously with mobile robots through active exploration. The robotic platforms are equipped with non-destructive sensors such as 3D laser scanners and thermal cameras for data acquisition. The resulting information is put into a building information model (BIM), i.e., digital representations of physical and functional characteristics of the building. The BIM forms the basis for guiding the user for maintenance and renovation actions.

Funding German Academic Exchange Service and Croatian Ministry of Science and Education (Total budget: €17.000,00, UNIZG-FER: €6.000)
Principal investigator Marija Seder
Researchers Ivan Petrović, Ivan Marković, Ivan Maurović, Juraj Peršić
Partner M.Sc. Dorit Borrmann, Julius-Maximilians-University Würzburg, Germany

FER-KIET - Advanced Technologies in Power Systems and Railway Vehicles

Short description

Advanced technologies in power systems and railway vehicles (FER-KIET) project has the main goal of creation of new knowledge and technologies with commercial application to power systems and railway vehicles. Project is performed as collaboration between Faculty of Electrical Engineering and Computing and industrial partner Končar - Electrical Engineering Institute (KIET).

Funding European Regional Development Fund (Total budget: €1.131.034, UNIZG-FER: €807.945)
Principal investigator Ivan Petrović (coordinator)
Partner Končar Electrical Engineering Institute
Website fer-kiet.fer.hr

ACROSS - Centre of Research Excellence for Advanced Cooperative Systems

Short description The project Centre of Research Excellence for Advanced Cooperative Systems (ACROSS) aims at unlocking and strengthening the research potential of the Faculty of Electrical Engineering and Computing of the University of Zagreb (UNIZG-FER) in the area of cooperative systems related to robotics, networked embedded systems and renewable energy systems. Possible applications of such cooperative systems are numerous: advanced flexible manufacturing, renewable and sustainable energy generation, home and office automation, transport, logistics, environmental monitoring, healthcare, security and surveillance, human augmentation, etc. The ultimate goal of ACROSS is to create a Centre of Research Excellence for Advanced Cooperative Systems within UNIZG-FER, which will be at the forefront of research and development of novel methodologies and advanced engineering approaches for cooperative systems with the following objectives: • Strengthening the Research Management Potential; • Increasing the Human Potential; • Increasing the Technology Potential; • Increasing Scientific Visibility and International Reputation; • Developing the Strategic Partnerships with Outstanding Research Centres in EU and leading Croatian industrial partners; • Improving responses to socio-economic needs of Croatia; • Earning a certified recognition “EU Centre of Research Excellence”. The ACROSS Project implements a coherent set of measures for execution of these objectives: • Recruitment of experienced researchers and a project manager; • Upgrading research equipment and establishing three new laboratories; • Exchange of know-how and experience with leading EU centres; • Organisation of workshops and conferences, dissemination and promotional activities; • Ex-post evaluation of research potential by independent experts chosen by the EC. 
Funding FP7 (Total budget: €3.755.660, UNIZG-FER: €3.755.660)
Principal investigator Ivan Petrović (coordinator)
Website across.fer.hr

VISTA - Computer Vision Innovations for Safe Traffic

Short description

The VISTA project employs a group of researchers from the University of Zagreb Faculty of Electrical Engineering and Computing and from the Faculty of Transport and Traffic Sciences. As part of this project the researchers will conduct research followed by the development of computer vision-based methods with intended use in road traffic. Vision is the most important sense used for driving and therefore computer vision algorithms are the most critical for Advanced Driver Assistance System (ADAS).

Research and development activities constitute one component of VISTA project in which the focus will be on industrial research and development, feasibility check and prototype development and testing of advanced computer vision systems for safe traffic. The second component of the project consists of networking activities with companies in the Croatian automotive sector through which new possibilities and potentials will be presented, and the process of defining new challenging application of computer vision in traffic will be started.

Funding EuropeAid/131920/M/ACT/HR (Total budget: €685.265)
Principal investigator Ivan Petrović
Researchers Josip Ćesić
Partners University of Zagreb Faculty of Electrical Engineering and Computing (coordinator Sven Lončarić), University of Zagreb Faculty of Transport and Traffic Sciences
Website vista.fer.hr

Thermal Perception, Mapping and Exploration of Environments for Energy Efficiency

Short descrption

More than 40% of Europe’s energy consumption is related to buildings, as
estimated by the Commission of the European Communities. Technology will help to exploit a huge saving potential, by automatically generating compact, three-dimensional, and annotated representation of indoor and urban environments. Regular, automatic surveying and monitoring provides the basis for reducing energy losses. By combining the emerging technologies of thermal imaging and terrestrial 3D laser scanning, the prototype system records as-built data of buildings related to energy
issues. Clever exploration and next-best-view-planning strategies with advanced sensors are needed to acquire snapshots of temperature distributions. Regular smart metering combined with advanced visualizations will enable end-users to carry out appropriate measures for saving energy.

The focus of this project is to combine several technologies, namely state of the art thermography, 3D laser scanning, computer vision and mobile robotics. Novel algorithms are used to tie these technologies together and to create 3D computer models containing multi-modal data. These
can be used to inform the user or customer about the temperature distribution and the heat flow in environments and to automate the detection of energy losses. 

Funding German Academic Exchange Service and Croatian Ministry of Science and Education (Total budget: €17.000, UNIZG-FER: €6.000)
Principal investigator Ivan Petrović
Researchers Marija Seder, Ivan Maurović
Partner Andreas Nüchter, Jacobs University Bremen GmbH, Germany

ThermalMapper - Thermal 3D Modeling of Indoor Environments for Saving Energy

Short description Heat and air conditioning losses in buildings and factories lead to a large amount of wasted energy. To prevent such losses, a precise digital model of heat distribution and heat flow is needed. Imagine a technology that enables one to gage the environmental structure in three dimensions and thermal information at the same time. Further imagine clever visualization software that presents the thermal 3D models to a computer screen, lets the user rotate the model for inspection and runs simulations of heat and air flow. The project ThermalMapper aims at constructing precise thermal 3D models of indoor environments. Technology that has been developed in the last years by robotic researchers is now available to be adapted to solve these real world issues. "The Action Plan for Energy Efficiency estimates that the largest cost-effective energy savings potential lies in the residential (around 27%) and commercial buildings (around 30%)". The availability of precise thermal 3D models will enable architects and construction engineers to modify existing buildings to reach these savings. The central point of the project ThermalMapper is to create 3D models that include thermal information as additional modality. In the course of the project ThermalMapper, 3D mapping methods will be enriched with thermal information, visualizations and simulations are developed to continuously gather and present data on what is taking place inside a building. Applications range from thermal 3D modelling of houses to factories. For example, service providers such as data processing centres are highly interested in constant and concurrent data acquisition techniques to optimize load control while providing high availability. Since thermal issues are very important for operators of data centres, we have chosen this scenario for additional demonstrations.  
Funding FP7 SEE-ERA.NET Plus (Total budget: €150.000, UNIZG-FER: €38.760)
Principal investigator Ivan Petrović
Researchers Marija Seder, Ivan Maurović
Partners Jacobs University Bremen GmbH, Germany (coordinator Andreas Nüchter), University of Sarajevo Faculty of Electrical Engineering

IntRobSAV - Intelligent robotic systems and autonomous vehicles

Short description

The main and general goal of this project is to create scientifically grounded fundamentals for starting development, design, production and application of autonomous mobile robots and vehicles in Croatia. Given that, it would also include Croatia in the most perspective industrial branch of the 21th century. Specific goal of suggested research is the development of general functional system library for control which could be easily applied during the development of autonomous mobile robots and vehicles of different constructions and applications in unknown and dynamic environments.

Funding Ministry of Science, Education and Sports of the Republic of Croatia
Principal investigator Ivan Petrović
Researchers Eduard Ivanjko, Mišel Brezak, Marija Seder, Andrej Kitanov, Srećko Jurić-Kavelj, Ivan Marković


Current Projects

 

 

External sites