Natko Kraševac
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Natko Kraševac has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Fausto Ferreira
University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, City of Zagreb, Croatia
5 shared publications - Nikola Mišković
Faculty of Electrical Engineering and Computing, University of Zagreb, 10000 Zagreb, Croatia
4 shared publications Ivan Lončar
University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, City of Zagreb, Croatia
3 shared publications- Ivan Lončar
University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, City of Zagreb, Croatia
3 shared publications Juraj Obradović
University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, City of Zagreb, Croatia
3 shared publications- Luka Mandić
University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, Croatia
3 shared publications
Latest Publications
- Open Access
- 28 July 2026
- Published by CERN in Open Research Europe
Citizens marine pilots: Increasing autonomous surface vehicles navigation capabilities with and for the public
Most of the world population lives by a water body. Observing, caring and understanding the ocean is vital for all. Among several branches of robotics - marine robotics creates the most interdisciplinary and participatory scientific pool, bringing citizen and scientists close to the use of aquatic robots. International efforts, such as the EU-funded MONUSEN project, are pioneering the technological transfer across borders, disciplines and people, therefore sustaining the United Nations Sustainable Development Goals (Goal 14 Life below Water). In particular, under MONUSEN we carried out two activities involving the general public, demonstrating the use and utility of cost effective technology. The first activity saw the presentation and usage of MARUS - Marine Robotic Unity Simulator - which offers advanced capabilities of generating realistic maritime environments allowing for closer-to-reality V&V – Verification & Validation – of applications developed for maritime vehicles. The second activity shared the functionality of the autonomous surface vehicle (ASV) SWAMP (Shallow Water Autonomous Multipurpose Platform). Participants piloted SWAMP ASV, collecting data along a predetermined path. Through the active involvement in data collection, they gained knowledge of state-of-the-art methods for controlling autonomous surface vehicles and contributed to a learning-by-imitation experiment. Both activities showed that the setting of the experiments and the visual interfaces effectively engaged a wide range of people belonging to different ages, cultures and education. The activities transferred new knowledge to the public, truly bringing them closer to the scientific work carried out in MONUSEN.
- 28 July 2026
- Published by CERN in Open Research Europe
Open AccessCitizens marine pilots: Increasing autonomous surface vehicles navigation capabilities with and for the public
Most of the world population lives by a water body. Observing, caring and understanding the ocean is vital for all. Among several branches of robotics - marine robotics creates the most interdisciplinary and participatory scientific pool, bringing citizen and scientists close to the use of aquatic robots. International efforts, such as the EU-funded MONUSEN project, are pioneering the technological transfer across borders, disciplines and people, therefore sustaining the United Nations Sustainable Development Goals (Goal 14 Life below Water). In particular, under MONUSEN we carried out two activities involving the general public, demonstrating the use and utility of cost effective technology. The first activity saw the presentation and usage of MARUS - Marine Robotic Unity Simulator - which offers advanced capabilities of generating realistic maritime environments allowing for closer-to-reality V&V – Verification & Validation – of applications developed for maritime vehicles. The second activity shared the functionality of the autonomous surface vehicle (ASV) SWAMP (Shallow Water Autonomous Multipurpose Platform). Participants piloted SWAMP ASV, collecting data along a predetermined path. Through the active involvement in data collection, they gained knowledge of state-of-the-art methods for controlling autonomous surface vehicles and contributed to a learning-by-imitation experiment. Both activities showed that the setting of the experiments and the visual interfaces effectively engaged a wide range of people belonging to different ages, cultures and education. The activities transferred new knowledge to the public, truly bringing them closer to the scientific work carried out in MONUSEN.
- Open Access
- 12 January 2026
- Published by CERN in Open Research Europe
- Vol. 6
Citizens marine pilots: Increasing autonomous surface vehicles navigation capabilities with and for the public
Most of the world population lives by a water body. Observing, caring and understanding the ocean is vital for all. Among several branches of robotics - marine robotics creates the most interdisciplinary and participatory scientific pool, bringing citizen and scientists close to the use of aquatic robots. International efforts, such as the EU-funded MONUSEN project, are pioneering the technological transfer across borders, disciplines and people, therefore sustaining the United Nations Sustainable Development Goals (Goal 14 Life below Water). In particular, under MONUSEN we carried out two activities involving the general public, demonstrating the use and utility of cost effective technology. The first activity saw the presentation and usage of MARUS - Marine Robotic Unity Simulator - which offers advanced capabilities of generating realistic maritime environments allowing for closer-to-reality V&V of applications developed for maritime vehicles. The second activity shared the functionality of the autonomous surface vehicle (ASV) SWAMP (Shallow Water Autonomous Multipurpose Platform). Participants piloted SWAMP ASV, collecting data along a predetermined path. Through the active involvement in data collection, they gained knowledge of state-of-the-art methods for controlling autonomous surface vehicles and contributed to a learning-by-imitation experiment. Both activities showed that the setting of the experiments and the visual interfaces effectively engaged a wide range of people belonging to different ages, cultures and education. The activities transferred new knowledge to the public, truly bringing them closer to the scientific work carried out in MONUSEN.
- 12 January 2026
- Published by CERN in Open Research Europe
- Vol. 6
Open AccessCitizens marine pilots: Increasing autonomous surface vehicles navigation capabilities with and for the public
Most of the world population lives by a water body. Observing, caring and understanding the ocean is vital for all. Among several branches of robotics - marine robotics creates the most interdisciplinary and participatory scientific pool, bringing citizen and scientists close to the use of aquatic robots. International efforts, such as the EU-funded MONUSEN project, are pioneering the technological transfer across borders, disciplines and people, therefore sustaining the United Nations Sustainable Development Goals (Goal 14 Life below Water). In particular, under MONUSEN we carried out two activities involving the general public, demonstrating the use and utility of cost effective technology. The first activity saw the presentation and usage of MARUS - Marine Robotic Unity Simulator - which offers advanced capabilities of generating realistic maritime environments allowing for closer-to-reality V&V of applications developed for maritime vehicles. The second activity shared the functionality of the autonomous surface vehicle (ASV) SWAMP (Shallow Water Autonomous Multipurpose Platform). Participants piloted SWAMP ASV, collecting data along a predetermined path. Through the active involvement in data collection, they gained knowledge of state-of-the-art methods for controlling autonomous surface vehicles and contributed to a learning-by-imitation experiment. Both activities showed that the setting of the experiments and the visual interfaces effectively engaged a wide range of people belonging to different ages, cultures and education. The activities transferred new knowledge to the public, truly bringing them closer to the scientific work carried out in MONUSEN.
- 24 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. PP (10709932) , 2-19
Heterogeneous Multirobot Team: Maritime Inspection and Intervention in Global Navigation Satellite System-Denied Scenarios
Autonomous robotic systems play an increasingly important role in overcoming complex maritime challenges, where the environment requires high adaptability, robustness, and precision. Marsupial robotic systems, combining aerial systems and surface vessels, offer a powerful solution for coordinated missions in Global Navigation Satellite System (GNSS)-denied scenarios, leveraging the unique capabilities of each robot to form a versatile team. This article presents a system integrating advanced sensor fusion, localization, mission planning, and communication to enable seamless collaboration between unmanned aerial vehicles (UAVs) and autonomous surface vehicles (ASVs). The focus is on optimizing the vehicles’ interaction to efficiently locate, retrieve, and transport objects from a target vessel in an adverse sea environment. This article provides a complete system overview, including the hardware setup, algorithms used, implementation details, and field trial results. The results analysis demonstrates the advanced capabilities of the developed ASV‒UAV system in complex real-world maritime operations, underscoring its potential for coordinated multirobot tasks in environments where traditional navigation systems are unavailable. Notably, this system was developed by the team that secured first place in the Mohamed Bin Zayed International Robotic Challenge (MBZIRC), proving its excellence in challenging conditions.
- 24 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. PP (10709932) , 2-19
Heterogeneous Multirobot Team: Maritime Inspection and Intervention in Global Navigation Satellite System-Denied Scenarios
Autonomous robotic systems play an increasingly important role in overcoming complex maritime challenges, where the environment requires high adaptability, robustness, and precision. Marsupial robotic systems, combining aerial systems and surface vessels, offer a powerful solution for coordinated missions in Global Navigation Satellite System (GNSS)-denied scenarios, leveraging the unique capabilities of each robot to form a versatile team. This article presents a system integrating advanced sensor fusion, localization, mission planning, and communication to enable seamless collaboration between unmanned aerial vehicles (UAVs) and autonomous surface vehicles (ASVs). The focus is on optimizing the vehicles’ interaction to efficiently locate, retrieve, and transport objects from a target vessel in an adverse sea environment. This article provides a complete system overview, including the hardware setup, algorithms used, implementation details, and field trial results. The results analysis demonstrates the advanced capabilities of the developed ASV‒UAV system in complex real-world maritime operations, underscoring its potential for coordinated multirobot tasks in environments where traditional navigation systems are unavailable. Notably, this system was developed by the team that secured first place in the Mohamed Bin Zayed International Robotic Challenge (MBZIRC), proving its excellence in challenging conditions.
- Open Access
- 12 February 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (2) , 317
Remote-Access Marine Robotics Infrastructure and Experiments at LABUST
Marine robotics is a complex field with a potentially high demanding logistics and high deployment cost. This is a barrier to many research groups. On the other hand, some research groups have substantial equipment and infrastructure that are typically underutilized. The push for sharing infrastructures was recently accentuated due to the COVID-19 pandemic. In particular, remote access experiments became the norm during the lockdown periods. LABUST completed new infrastructure during the COVID-19 pandemic and prepared it for state-of-the-art remote access from anywhere in the globe. This is important both for research and educational purposes. This article describes the infrastructure, equipment, and methods used for implementing the remote access including the calibration procedures. It also reports on real remote access trials for different applications such as Autonomous ships, diver–robot interaction, and Remotely Operated Vehicle (ROV) pilots. These examples include both pool and at-sea remote trials, proving the capabilities of the infrastructure.
- 12 February 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (2) , 317
Open AccessRemote-Access Marine Robotics Infrastructure and Experiments at LABUST
Marine robotics is a complex field with a potentially high demanding logistics and high deployment cost. This is a barrier to many research groups. On the other hand, some research groups have substantial equipment and infrastructure that are typically underutilized. The push for sharing infrastructures was recently accentuated due to the COVID-19 pandemic. In particular, remote access experiments became the norm during the lockdown periods. LABUST completed new infrastructure during the COVID-19 pandemic and prepared it for state-of-the-art remote access from anywhere in the globe. This is important both for research and educational purposes. This article describes the infrastructure, equipment, and methods used for implementing the remote access including the calibration procedures. It also reports on real remote access trials for different applications such as Autonomous ships, diver–robot interaction, and Remotely Operated Vehicle (ROV) pilots. These examples include both pool and at-sea remote trials, proving the capabilities of the infrastructure.
- Open Access
A Search Strategy and Vessel Detection in Maritime Environment Using Fixed-Wing UAVs
In this paper, we address the problem of autonomous search and vessel detection in an unknown GNSS-denied maritime environment with fixed-wing UAVs. The main challenge in such environments with limited localization, communication range, and the total number of UAVs and sensors is to implement an appropriate search strategy so that a target vessel can be detected as soon as possible. Thus we present informed and non-informed methods used to search the environment. The informed method relies on an obtained probabilistic map, while the non-informed method navigates the UAVs along predefined paths computed with respect to the environment. The vessel detection method is trained on synthetic data collected in the simulator with data annotation tools. Comparative experiments in simulation have shown that our combination of sensors, search methods and a vessel detection algorithm leads to a successful search for the target vessel in such challenging environments.
Open AccessA Search Strategy and Vessel Detection in Maritime Environment Using Fixed-Wing UAVs
In this paper, we address the problem of autonomous search and vessel detection in an unknown GNSS-denied maritime environment with fixed-wing UAVs. The main challenge in such environments with limited localization, communication range, and the total number of UAVs and sensors is to implement an appropriate search strategy so that a target vessel can be detected as soon as possible. Thus we present informed and non-informed methods used to search the environment. The informed method relies on an obtained probabilistic map, while the non-informed method navigates the UAVs along predefined paths computed with respect to the environment. The vessel detection method is trained on synthetic data collected in the simulator with data annotation tools. Comparative experiments in simulation have shown that our combination of sensors, search methods and a vessel detection algorithm leads to a successful search for the target vessel in such challenging environments.
- 17 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
MARUS - A Marine Robotics Simulator
Marine robotics requires high quality simulators due to complexity and availability of trials at sea. While there are several simulators in the literature, these have gaps in applications requiring high visual fidelity and human-robot interaction. This paper describes Marine Robotics Unity Simulator (MARUS), an open-source simulator for marine robotics based on Unity3D software that aims to close those gaps. It can simulate multi-robot systems in a marine environment offering water physics and a wide array of sensors commonly used in underwater and maritime domain. An interface allowing inter-connectivity with the simulator was developed where the focus was put on ROS 1/2 integration preferred in robotics community. Due to growing requirements on high-fidelity visual simulation required for machine learning, tools were developed for enabling dataset generation with automatic annotations. Examples of simulator application demonstrate the capabilities of the simulator for real world problems encountered during research project development.
- 17 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
MARUS - A Marine Robotics Simulator
Marine robotics requires high quality simulators due to complexity and availability of trials at sea. While there are several simulators in the literature, these have gaps in applications requiring high visual fidelity and human-robot interaction. This paper describes Marine Robotics Unity Simulator (MARUS), an open-source simulator for marine robotics based on Unity3D software that aims to close those gaps. It can simulate multi-robot systems in a marine environment offering water physics and a wide array of sensors commonly used in underwater and maritime domain. An interface allowing inter-connectivity with the simulator was developed where the focus was put on ROS 1/2 integration preferred in robotics community. Due to growing requirements on high-fidelity visual simulation required for machine learning, tools were developed for enabling dataset generation with automatic annotations. Examples of simulator application demonstrate the capabilities of the simulator for real world problems encountered during research project development.