A half-day workshop to be held as part of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)
Place: Abu Dhabi National Exhibition Centre (ADNEC), Abu Dhabi, United Arab Emirates
Date: 14th of October 2024, 14:00-18:00, Room 6
This half day workshop will include invited speaker presentations, poster sessions and panel discussions. Presentations from invited speakers will cover the following themes:
Session 1: Autonomous robotic systems in the aquaculture industry: current status, needs and demands for sustainable food production.
Session 2: Autonomous robotic solutions in academia: novel methods, dedicated robotic concepts, prototypes and lessons learned.
Title: Underwater Robotics Solutions for Autonomous IMR Operations in Fish Farms
Bio: Dr. Eleni Kelasidi is Senior Research Scientist and head of SINTEF ACE-RoboticLab - Autonomous and Robotic Aquaculture systems Lab in SINTEF Ocean leading activities on autonomous systems and robotic solutions applied to the aquaculture industry and targeting interdisciplinary research to link the field of technology and biology. Eleni Kelasidi received a Ph.D degree in Engineering Cybernetics from NTNU in 2015. In 2016, she is honored three-year VISTA (as a collaborative partnership between Statoil and the Norwegian Academy of Science and Letters) fellowship investigating Resident Robot Manipulators for Subsea IMR operations as PostDoc Researcher (VISTA Scholar) at the CoE Centre for Autonomous Marine Operations and Systems, Department of Engineering Cybernetics at NTNU. She has acquired several projects targeting both basic knowledge and applied research and investigated problems towards realization of autonomous robotic concepts in aquaculture domain (e.g. Research Council of Norway: Project leader of 5 IPNs, 1 KSP, 1 FRIPRO-Young Researcher Talent, 3 RACE projects, and WP leader of two EU projects). Her research groups work on robotic applications in fish farming industry in SINTEF Ocean lead to the development of the first robotic lab dedicated to aquaculture domain.
Abstract: Underwater robotic systems have been used and demonstrated for use in the aquaculture industry, and research is targeted to address the required level of autonomy during robotic operations in fish farms. Manually operated ROVs have been used for several monitoring operations such as inspection of nets and mooring lines, as well as monitoring and inspection of water quality, the cage environment, and fish population. This talk will provide an overview of current research and innovative solutions for robust, safe, efficient autonomous monitoring, inspection and repair (IMR) operations in fish farms to reduce costs, and risks, increase objectivity and production, and contribute to better fish welfare. Relevant R&D project results will be presented demonstrating how the adaption of robotic solutions with an increased level of autonomy can contribute to increasing the weather window and support the industry toward increased production, objectivity, and efficiency. The content of the talk will cover areas such as the design of aquaculture-dedicated robotic systems, vehicle interaction with the environment and fish, collision-free motion planning methods and intelligent control approaches able to deal with dynamically changing environments, sensors and tools, underwater localization and communication, and remote operations.
Title: Resilient Exclusively Vision-driven Underwater Autonomy
Bio: Prof. Kostas Alexis conducts research in the domain of resilient robotic autonomy. Through his studies he has examined the potential of autonomous systems to navigate extreme environments by presenting resourcefulness, robustness and redundancy. His research areas include the domains of robot control, path planning, and Simultaneous Localization And Mapping, while across these disciplines a holistic approach is taken to facilitate enhanced resilient as demonstrated through field robotics. He has been the PI in major international grants such as the DARPA Subterranean Challenge and his funding portfolio includes grants from US sources (e.g., DARPA, NSF, DOE, USDA), EU (e.g., Horizon 2020 programs), as well as the Norwegian Research Council.
Abstract: In this talk, we present progress in the domain of exclusively vision-driven underwater autonomy. Specifically, we outline methods for vision-based underwater odometry estimation, autonomous navigation, and operation. Within this framework, we highlight two key directions, namely refractive camera modeling for visual-inertial odometry, and learned models of proprioceptive odometry, alongside their deployment within the framework of autonomous exploration missions with underwater robots.
Konstantinos Alexis
WebsiteGoogle ScholarLinkedIn
Title: Bioinspired robotic systems - UCAT for operations in Atlantic fish farms
Bio: Maarja Kruusmaa is an Estonian computer scientist, professor at Tallinn University of Technology, vice-rector for research and head of the biorobotics center. At Tallinn University of Technology, she has served as head of the biorobotics center 2008–2016 and professor 2008–2016; research vice-dean of the Faculty of Information Technology 2015–2019; Head of the Biorobotics Center of the Institute of Computer Systems; Professor of the Institute of Computer Systems since 2017; and research vice-rector from 2020. She was elected a member of the Estonian Academy of Sciences in 2016 in the field of technical sciences. She belongs to the department of informatics and technical sciences at the academy and is a member of the board of the academy (since 2019). She is a member of the Estonian Polar Research Commission of the Academy of Sciences and the Council of Estonian Centers of Excellence in Science. In 2020, she was elected as the chief scientific adviser of the European Commission. Her main research area is bio-inspired underwater robotics to imitate the movements of fish and turtles, electroactive materials and devices and their control, underwater robotics and learning algorithms for intelligent robots.
Abstract: Animal–robot studies can inform us about animal behaviour and inspire advances in agriculture, environmental monitoring and animal health and welfare. Currently, experimental results on how fish are affected by the presence of underwater robots are largely limited to laboratory environments with few individuals and a focus on model species. Laboratory studies provide valuable insight, but their results are not necessarily generalizable to larger scales such as marine aquaculture. This talk will discuss the effects of underwater robots and a human diver in a large fish aggregation within a Norwegian aquaculture facility, with the explicit purpose to improve the use of underwater robots for fish observations. We observed aquaculture salmon's reaction to the flipper-propelled robot U-CAT in a sea cage with 188 000 individuals. A significant difference in fish behaviour was found using U-CAT when compared to a thruster-driven underwater robot, Argus Mini and a human diver. Specifically, salmon were more likely to swim closer to U-CAT at a lower tailbeat frequency. Fish reactions were not significantly different when considering motor noise or when U-CAT's colour was changed from yellow to silver. No difference was observed in the distance or tailbeat frequency as a response to thruster or flipper motion, when actuated and passively floating robots were compared. These results offer insight into how large aggregations of aquaculture salmon respond to underwater robots. Furthermore, the proposed underwater video processing workflow to assess fish's response to underwater robots is simple and reproducible. This work provides a practical method to study fish–robot interactions, which can lead to improved underwater robot designs to provide more affordable, scalable and effective solutions.
Maarja Kruusmaa
maarja.kruusmaa@taltech.ee
WebsiteGoogle ScholarLinkedIn
Title: Multi-Robot System for operations in Aquaculture
Bio: Dr. Nadir Kapetanović is a Leading Researcher at the Laboratory for Underwater Systems and Technologies (LABUST) at University of Zagreb Faculty of Electrical Engineering and Computing. In the scope of ESI ERDF-funded project HEKTOR project (Heterogeneous autonomous robotic system in viticulture and mariculture) he led activities related to the development of an autonomous catamaran and subsystems enabling control and cooperation between the catamaran, a commercial ROV, and a UAV in mariculture scenarios. He had a close collaboration with a Croatian mariculture company for collecting datasets used for development of fish cage net visual biofouling estimation algorithms.
Abstract: For millennia, mariculture has been a component of human society. It is still heavily reliant on human labor, with workers generally doing arduous, repetitive, sometimes even dangerous tasks for long periods of time. HEKTOR (Heterogeneous Autonomous Robotic System in Viticulture and Mariculture) project looked for solutions to these issues. The main objective of the HEKTOR project was to realize a systematic solution for the coordination/cooperation of autonomous heterogeneous robots/vehicles (marine and aerial) that can cooperate autonomously and assign tasks to each other in an open unstructured space. HEKTOR is designed as a modular and autonomous system, adapted for various missions in mariculture with the foreseen possibility of human intervention during the performance of various inspection and intervention tasks. The lecture will cover the development and integration of various robotic platforms (autonomous catamaran, aerial drone, and remotely operated vehicle) and their cooperation-enabling subsystems (landing platform, tether management system, and underwater acoustic localization). Furthermore, results of autonomous inspection and fish cage net biofouling estimation will be presented.
Nadir Kapetanović
nadir.kapetanovic@fer.hr
WebsiteGoogle ScholarLinkedIn
Title: Current and New Farming Concepts: Relevance of robotic solutions to manage risk and ensure safe aquaculture operations
Bio: Dr. Kristine Vedal Størkersen is Senior Research Scientist at the research institute SINTEF Ocean in Norway with a PhD in Sociology from the Norwegian University of Science and Technology (NTNU). She is currently leading several research activities within biosafety and occupational safety in aquaculture. Over two decades, Størkersen has studied how organizations create safe working conditions for the personnel. In aquaculture, this could include how technology, regulations and resources influence the personnel’s ability to achieve objectives like efficiency, occupational safety, or fish welfare. In 2021-2023, Størkersen was the coordinator of SFI Exposed – Center for research-based innovation about exposed aquaculture operations (2015-2023). A research area in the Center was about autonomous operations and robotics. Here, innovative developments were made, and further research challenges and industry needs were identified. All research led by Dr. Størkersen include dialogue with actors from the industry, regulators, and other stakeholders.
Abstract: Technology that reduces manual operations at fish farms can reduce risk of injuries, but also introduce new risks to the personnel. In Norway, fish farmers have the second most hazardous occupation, and salmon farming is one of the largest industries. Currently, the industry is undergoing major changes. The production technology is developed from mostly open netpens along the coast, to also new production concepts: semi-closed and submerged units offshore and on land. The new concepts include robotics and technology that remove humans from the forces. This talk will be about how the technologies influence the occupational safety and health (OSH) in the various salmon farming concepts: Along with the technology, the workplaces have transformed. Implementation of technology and robotics have made routine operations semi-autonomous or remotely controlled. This removes personnel from the hazard, but increases other risks related to monitoring tasks. Also, larger operations still require personnel, and involve hazards, forces and increased uncertainty. At the new fish farm concepts, risks of injuries, fatalities and illness may be higher, despite more thorough operational planning and safety management. At this point in development, technology and remote operations introduce new risks at the same time as it reduces some hazards for the personnel.
Kristine Vedal Størkersen
WebsiteGoogle ScholarLinkedIn
Title: Towards Autonomous Underwater Robotic System for Aquaculture Applications
Bio: Dr. Irfan Hussain an Assistant Professor in Robotics and Mechanical Engineering at Khalifa University, Abu Dhabi, UAE. He is Associate Editor of proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science. Research Topic Editor on "Wearable Robots and Sensorimotor Interfaces: Augmentation, Rehabilitation, Assistance or substitution of human sensorimotor function" (ID 21096), frontiers in Neurorobotics. He is an Associate Editor of IEEE/ RAS ICRA-23, ICRA-22, ICRA-21, RAS/EMBS BioRob-18 and. He received his PhD degree in robotics from University of Siena, Italy. He was a post doctorate researcher at Robotics Institute at Khalifa University of Science and Technology, Abu Dhabi, UAE. He also worked as a post doctorate at Siena robotics and system lab (SIRSLab), Italy. His research interests include embodied and cognitive intelligence in robots with applications in marine, healthcare and industrial robotics.
Abstract: Aquafarms consist of special enclosures named fish cages/net pens to culture fish in the open sea while protecting them from predators. For the well-being of the fish, it is essential to monitor their feed and condition while ensuring the cleanliness and integrity of the fish net. Currently, divers and multiple remotely operated vehicles (ROVs) are deployed for inspecting and maintaining aquafarms; this approach is expensive and requires highly skilled human operators. In this talk, I will discuss our ongoing development of the autonomous underwater robotic system to inspect and monitor aquafarm cages, reduce cost, and improve quality and ease of operation. In particular, I will discuss the use of advanced computer vision techniques coupled with ROV to regularly detect fish net defects, including biofouling, plants, and holes. In addition, this talk will cover ROV control and navigation to perform the aquaculture inspection tasks autonomously. Such innovative robotics-applied solutions will help the sustainability and profitability of the aquaculture industry.
Irfan Hussain
WebsiteGoogle Scholar
Title: Robotic Vision for Autonomous Operations in Aquaculture
Bio: Annette Stahl is a Professor at the Department of Engineering Cybernetics at the Norwegian University of Science and Technology – NTNU, Norway. She is Head of the Robotic Vision Group and Researcher at the Centre for Research-based Innovation Autonomous Ships - SFI AutoShip. She received her PhD degree from the University of Heidelberg, Germany in applied mathematics with the main focus on computer vision. She spent two years as a postdoc at the School of Computing, Dublin City University – DCU, Ireland and three years at the Department of Mathematical Sciences, NTNU, Norway, where she worked on isogeometric analysis-based methods for structural mechanics. After this period, she worked as a researcher at the High-Performance Computing Group at NTNU and at SINTEF Ocean, Norway, on computer vision-based techniques towards automation of aquaculture operations. In 2016, her was awarded an Onsager Fellowship from NTNU's Research Excellence. She is presently immersed in the realm of robotic vision and visual perception, focused on enabling autonomous robotic operations across diverse and adverse environments—spanning underwater, sea surfaces, land, air, space, as well as indoor and industrial applications.
Abstract: Advanced vision and perception technologies for underwater robotic systems play an important role in today's aquaculture facilities. The integration of such systems enables real-time monitoring and assessment of fish health, behavior, welfare, and infrastructure integrity. In this talk, we present vision and perception advancements which include work towards salmon re-identification systems that accurately detect body parts and melanin spots, quantify scale loss, estimate swimming speed and breathing rates, crucial for robust salmon welfare monitoring. Additionally, we address the use of vision-based systems in the routine inspection of aquaculture infrastructure, including the integrity of fish nets and cages, which are critical to ensuring both the safety of aquatic life and the economic viability of aquaculture operations. Through a series of field tests and case studies, our findings demonstrate that robotic vision systems provide more consistent and accurate data for decision-making processes in aquaculture management.
Annette Stahl
annette.stahl@ntnu.no
WebsiteGoogle Scholar
Title: Advanced technological solutions in Mediterranean marine fish farms: Current applications and future needs
Bio: Dr. Nikos Papandroulakis is Research Director at the Institute of Aquaculture of the HCMR and head of the Aquaculture Production Technologies Lab at the Institute of Marine Biology Biotechnology and Aquaculture. He was involved in the development of offshore aquaculture concepts for multipurpose oceanic platforms, developing the aquaculture module with emphasis on the synergies with other activities, modelling technologies and analyzing the economic characteristics of the activity. The work on farming technologies has recently been directed towards developing tools for new monitoring, operation and decision-making systems towards precision aquaculture. His research is focused on developing appropriate rearing technologies and he is particularly interested in applications of precision fish farming concepts and novel technologies in aquaculture industry. Dr Papandroulakis has initiated the pilot scale net pen cage farm of the Institute at Souda bay (west Crete) in 2000 and is the scientific responsible for its operation since then. Among his interests are also issues related to technology transfer and the application of research results in the industry. He has been involved as coordinator or partner in 43 National and EU projects (such as. AquaExcel2020, TROPOS, COPEWELL, DIVERSIFY, TAPAS, CLIMEFISH, BlueMed SCA, PERFORMFISH, iFishENCi AquaExcel 3.0, SusinChain, Cure4Aqua).
Abstract: Mediterranean marine fish aquaculture primarily focuses on rearing European seabass (308.4K MT; 48%) and gilthead seabream (330.2K MT; 52%), achieving a total production of 640K MT in 2022, a marginal increase of 1.2% from 2021. However, Mediterranean aquaculture production has stagnated since the turn of the century due to a combination of ecological, economic, regulatory, social, and technological factors. These technological challenges are multifaceted and significantly impact the sector's growth and sustainability.
Industrial operations in aquaculture are complex, involving biological and technological elements, often conducted on structures exposed to the marine environment. Conventional aquaculture practices rely heavily on manual labor, leading to inaccuracies in activities such as water management and posing risks to both personnel and fish well-being. This results in subjective assessments during daily operations in both sea-based and land-based facilities. Increasingly, automation and robotics are becoming essential in Mediterranean marine aquaculture, allowing the digitization of the industry (an EU strategic approach) and a shift towards precision farming, thus enhancing efficiency, sustainability, and productivity.
Applying the precision farming concept and new intelligent tools to quantify various properties related to the farm environment and the fish is increasingly necessary for the advancement of Mediterranean marine aquaculture. Several groups are active in this direction. Examples of already applied tools include machine vision to recognize individual fish, identify size and external morphometric characteristics, and describe individual or group fish behavior. For a more holistic picture of the farm, combinations of sensors are used together with mathematical models in an Internet of Things (IoT) platform, which also utilizes satellite data to provide predictions for major environmental parameters (e.g., temperature, dissolved oxygen). The combination of these data allows for better management, particularly in feeding, and helps mitigate future threats such as climate change.
Nikos Papandroulakis
WebsiteGoogle ScholarLinkedIn
Title: MIT Sea Grant Strategy for Offshore Aquaculture
Bio: Andrew Bennett has nearly 40 years of R&D experience developing novel robotic systems for land, water and air use in both academic and industrial situations. His projects have included a variety of autonomous maritime vehicles at MIT, including the Sea Squirt, the Odyssey series of AUVs, the Oystermaran aquaculture ASV and Zippy, a coastal monitoring robot. He also worked for Walt Disney Imagineering Research & Development where he helped create walking quadruped robot technology demonstrators and several ride effects currently installed in Disney’s Animal Kingdom. He is the former Director of Research at iRobot Corporation and the project manager for the PackBot mobile robot system; one of which is in the Smithsonian American History Museum and several thousand more are in active service. In 2011 Dr. Bennett became a Professor and Director of the SCOPE program at the Franklin W. Olin College of Engineering where he taught Systems Engineering and Robotics. He founded his own startup, Point Road Solutions, which is dedicated to creating engineering solutions for the ocean research community. Currently he works for MIT Sea Grant on a variety of ocean research projects and teaches a capstone ocean engineering class each spring. Dr. Bennett currently has 4 patents issued and 5 more pending.
Abstract: Coastal aquaculture in Massachusetts is structured with leased farms that are often small in size and located in or near densely populated, heavily used areas of coastline. One unintended consequence of this is that farms often must function with relatively small economic returns, making equipment investments difficult. Adding to this is the relative lack of suitable labor; current farms often employ equipment and practices first created decades ago and are often ergonomically dangerous for the worker, requiring significant strength to perform. This physical requirement has the effect of restricting the available pool of prospective employees due to the demanding physical requirements as well as the capacity for aging aquaculturists to continue to farm as they once did.
MIT Sea Grant is working to introduce robotics to the Massachusetts aquaculture industry along several fronts: to improve yield and minimize losses, mitigate the risk of injury to employees and reduce the necessary headcount to operate a farm and to expand the viable workforce by changing the physicality required to operate aquaculture facilities. In this presentation we will provide an overview of three ongoing projects: “Zippy,” a payload-carrying coastal monitoring robot designed to survey both in and out of water, regardless of local weather conditions or sea state; Oystermaran, an oyster-bag-handling robot designed to replace manual bag flipping, thereby preventing shoulder and back injuries; and an autonomous docking system for offshore aquaculture finfish operations. Finally, we will discuss current investigations into the economic and policy drivers that affect aquaculture facility viability.
Andrew Bennett
WebsiteResearch GateLinkedIn
Title: Breaking Barriers: Affordable IoT, Biomimicry, and 3D Printing for Sustainable Global Aquaculture
Bio: Liane Thompson is founder and CEO of Aquaai, a USA B2B hardware-enabled software company, which addresses critical issues in water bodies by providing advanced monitoring and affordable data analytics solutions. Through the use of AI, the cloud (a web dashboard), and 3D printed fishlike autonomous underwater vehicles (fAUVs), Aquaai delivers data insights on water quality, subsurface infrastructure and ecosystem health, enabling better management for customers from numerous Blue industries, including aquaculture. FaaS - Fish as a Service®
Prior to founding Aquaai, Liane was a global journalist, received 3-time PrimeTime Emmy nominations and co-created the premier television series of acclaimed late chef Anthony Bourdain. Liane has been named in 50 Most Powerful Women in Technology 2023, World's Top 50 Innovators 2022, 20 Women Driving the Future of ClimateTech 2021, 30 Women in Robotics to Know 2020, and Innovative Women in AI / Blockchain to Follow (2019). Liane is a speaker at numerous events, including TEDx, Our Ocean and COP28, and is most passionate about addressing food and water scarcity in order to provide her children a better future.
Abstract: Aquaai CEO Liane Thompson will address why high-cost AI software solutions are unlikely to achieve widespread adoption in global aquaculture. Most aquaculture farmers, especially in emerging markets, face significant financial limitations, making such technology impractical. Liane will argue that to achieve real impact, the industry needs affordable hardware that leverages biomimicry and 3D printing for IoT-driven insights. Aquaai’s 3D printed, fishlike autonomous vehicles (fAUVs) mimic marine life, offer a cost-effective and sustainable alternative for monitoring water quality, improving operational efficiency, and protecting ecosystems. This affordability is crucial for driving real, large-scale impact and sustainability across the aquaculture industry globally.
Liane Thompson
WebsiteLinkedInThe workshop has been endorsed by
Participants are required to abide by the IEEE RAS Code of Conduct
Contact information: Eleni.kelasidi@sintef.no