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.

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

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.

3.6 million EUR)

In HORACE, we will go beyond Euclidean distances between two points, and instead consider distances between other geometric objects and  account for manifolds that are not Euclidean. We will then exploit these distance measures in the form of kernel functions that can be used in Gaussian processes to account for variations and uncertainty. By leveraging our previous expertise, we will demonstrate the developed approaches in several human-robot collaboration scenarios involving joint physical collaboration, assembly, manipulation of deformable objects, all
with high degree of freedom robots, in particular, the TALOS humanoid. We will investigate how the control of a humanoid robot can be effectively achieved by using the proposed geometric descriptors and how the geodesics in such encoding can be used for effective planning.

HORACE will lead to novel methodological developments yielding more efficient human-robot collaboration and better understanding of its inherent geometrical structure. The three partners each bring knowledge and equipment that complement the others. Idiap brings knowledge on the geometric perspectives, UNIZG-FER on planning and HRC and JSI on humanoid robots and human-robot collaboration. The complementarity of the partners will enable concrete advancements in the field of human-robot collaboration.

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

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.

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.

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.

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

Jelena Gregorić, Karlo Koledić

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.

Ivan Petrović, Ivan Marković, Igor Cvišić

Ivan Bilić

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.

Ivan Petrović, Ivan Marković, Igor Cvišić, Antea Hadviger

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.

Ivan Petrović, Ivan Marković, Igor Cvišić

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.

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

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.

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

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.

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.

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.

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

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.

KTH – Royal Institute of Technology, Innovation Centre Nikola Tesla

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.

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

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.

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.

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.

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.

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).

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.

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. 

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.