La rencontre de la robotique sous-marine - 15 au 19 juin 2026
June 19, 2026 – ENSTA, 2 Rue François Verny, Brest, France - Grand Amphi 1 - Norbert Fargère
Price and Access : Free of charge. Registration is mandatory, as access is subject to prior authorization.
Air Sea International WS Program
Guido de Croon (TU Delft)
Title: Neuromorphic AI for small, resource-constrained robots
Abstract: Spurred by the quick progress in artificial intelligence, autonomous robots promise to revolutionize our economy and society. However, current-day AI requires excessive computational effort, leading to extra robot weight, costs, and energy consumption. This makes robots with AI large, heavy, and dangerous, which negatively affects their societal acceptance. To realize a future of competent and safe autonomous robots, AI should become orders-of-magnitude more efficient. Neuromorphic sensing and processing promises substantially faster and more energy efficient robotic AI. In order to show its potential, in my lab we tackle the daunting challenge of developing a neuromorphic AI that provides full autonomy to tiny, severely resource-restricted drones. I will present our ongoing work on realizing capabilities such as attitude and ego-motion estimation and control purely with SNNs, and share our findings on the actual latency and power usage of existing neuromorphic chips. Finally, I will present Bee-Nav, a highly efficient, long-range navigation strategy, inspired by honeybee learning flights.
Guido de Croon is Full Professor at the Micro Air Vehicle lab (MAVLab) of Delft University of Technology, the Netherlands. His research interest lies with computationally efficient, bio-inspired algorithms for autonomous, light-weight flying robots, with an emphasis on computer vision. His work has included fully autonomous flight of the 20-gram flapping wing drone “DelFly Explorer” and a swarm of tiny, 30-gram nano-copters able to explore unknown environments and localize gas leaks. Moreover, his group has made several advances in energy-efficient, low-latency neuromorphic sensing and processing for autonomous drones. Finally, his work has generated various new hypotheses on biological intelligence, including how honeybees actively evaluate distances with optical flow and how flying insects can estimate their flight attitude without using accelerometers.
Marco Tognon (IRISA, INRIA Rennes)
Title: From Flying Sensors to Flying Workers: Aerial Physical Interaction, Manipulation, and Collaboration
Abstract: Aerial robotics is nowadays seeing an exponential growth, both from the academic and industrial points of view. A lot of work has already been done for contact-free motions applied to a wide application domain, e.g., agriculture, archeology, photography, etc. However, if aerial robots were able to also interact with the environment, the application domains could be further extended toward new areas like transportation and manipulation of objects, contact-based inspection and maintenance, assembly and construction, etc. In this talk I will describe my contribution to the field of aerial physical interaction, from showing its feasibility for simple contact tasks, to enhance manipulation capabilities for more and more complex task. I will then present my vision for the future that sees aerial manipulator capable to safely accomplish physical work in real environments, together with other robots and human operators.
Marco Tognon is a tenured researcher at Inria Center of Rennes University, France, in the Rainbow team. Before he was a postdoctoral researcher in the Autonomous System Lab (ASL) at ETH Zurich, Switzerland. He received the Ph.D. degree in Robotics in 2018, from INSA Toulouse, France, developing his thesis at LAAS-CNRS. His thesis has been awarded with three prizes. He received the M.Sc. degree in automation engineering in 2014, from the University of Padua, Italy, with a master thesis carried out at MPI for Biological Cybernetics, Tubingen, Germany. He published more than 36 journal papers, and he is coordinator of the ANR project AirHandyBot. He serves as Associate Editor for IEEE Transaction of Robotics. He is also co-chair for the IEEE TC Aerial Robotics and Unmanned Aerial Vehicles. Recently he received the IROS24 Toshio Fukuda Young Professional Award. His current research interests include robotics, aerial physical interaction, multi-robot systems, and human-robot physical interaction.
Maarja Kruusmaa (TalTech)
Title: Amphibious data: sensing and robotics where land meets water
Abstract: Shallow-water zones and land–water interfaces present unique challenges for sensing and robotics. These environments are far more dynamic, turbulent, and structurally complex than either dry land or deep water, forcing us to rethink how we design systems that must operate, survive, and collect meaningful data there. This talk introduces a set of novel robotic concepts tailored for shallow-water operation and soft, muddy coastlines, highlighting how mobility and robustness can be reimagined for amphibious conditions. It also showcases applications of distributed flow and turbulence sensing—systems capable of capturing fine-scale hydrodynamic patterns around coastal infrastructure and within the surf zone. Together, these developments point toward new ways of observing, understanding, and managing environments where land meets sea.
Prof. Maarja Kruusmaa is a Robotics Professor at Tallinn University of Technology (TalTech). She specializes in underwater robotics and environmental sensing in demanding shallow-water and deep-water environments. Her research integrates bio-inspired design with robotics-based studies of animal locomotion and behaviour.
Pere Ridao RodrĂguez (VICOROB)
Title: TANDEM, a Heterogeneous team of Marine Robots for Offshore IMR Operations
Abstract: The rapid expansion of the blue economy, particularly offshore wind energy, demands scalable, cost-effective, and low-carbon Inspection, Maintenance, and Repair (IMR) solutions. Traditional IMR workflows depend mostly on heavy, manned, fossil-fuel-reliant support vessels and tethered Remotely Operated Vehicles (ROVs)—paradigms that introduce substantial operational carbon footprints and human safety risks. This keynote presents TANDEM, an innovative project developing a heterogeneous, multi-domain team of marine robots designed to achieve fully autonomous, tetherless offshore IMR operations. The TANDEM robotic ecosystem comprises an Autonomous Surface Vehicle (ASV) used to transport, deploy and recover a resident bi-manual I-AUV and a Docking Station, connected to the infrastructure supporting long term deployment. TANDEM is an ongoing project and the keynote will present its current status of development of the different technologies involved.
Pere Ridao RodrĂguez is a Full Professor of Robotics of the Computer Vision and Robotics Research Institute (VICOROB) at the University of Girona, Spain. He is the head of the Underwater Robotics Research Center (CIRS) and a co-founder of Iqua Robotics spin-off company specializing in the development of Autonomous Underwater Vehicles (AUVs). Since 1997, his research has focused on the design of intelligent marine robots, with pioneering contributions to subsea autonomous intervention and Simultaneous Localization and Mapping (SLAM). Prof. Ridao has led numerous European research projects and served as the Chair of the IFAC Technical Committee on Marine Systems. Beyond his research and industrial contributions, Prof. Ridao has been deeply involved in shaping international robotics education. He has been a core academic driver behind a lineage of prestigious Erasmus Mundus Joint Master Degrees hosted at the University of Girona, including VIBOT (Master in Vision and Robotics) and IFROS (Master in Intelligent Field Robotic Systems). Over more than two decades, these international programs have trained top-tier researchers from across the globe in field robotics, computer vision, and autonomous ocean systems.
Adrien Mabire (LS2N, IMT-Atl, Elwave)
Title: Multi-object electrolocalization with near field TR-MUSIC
Abstract: Sensing technologies for underwater robotics are often challenged by turbid environments, where optical and acoustic methods can be unreliable. Electrosensing is an emergent alternative inspired by weakly electric fish. However, estimating the object’s pose and shape is an ill-posed nonlinear inverse problem. We propose a near-field Time-Reversal MUltiple SIgnal Classification (TR-MUSIC) algorithm for localizing multiple extended objects using an arbitrary electrode array. This variant reduces the search to position only ; moreover it shows a 40% improvement in localization accuracy across a broad range of distances and noise levels.
Claire Dune (COSMER)
Title: Challenges of Underwater Robotics in the Arctic
Abstract:
Climate change is driving major transformations in Arctic regions. Melting ice is opening up new shipping routes, both on the surface and underwater, making these areas strategically important at a time when we are only just beginning to grasp the biological richness of these seabeds. In this presentation, I will explain how robotic exploration enables the collection of data essential to understanding these ecosystems. We will also analyze the scientific challenges that these extreme environments present, particularly in the areas of navigation, mapping, and metrology.Claire Dune is an assistant professor at the COSMER laboratory, Université de Toulon. Her research focuses on perception for robotic control, aiming to increase the autonomy of systems in unstructured environments. The application ranges from localization and active positioning for underwater mapping, visual control for docking tasks, to dynamic management of ROV umbilicals. Her research also explores human-robot interactions in underwater environments, where she studies the role of the robot within a mixed diving team. Her work aims to give the machine the ability to understand human behavior and monitor diver behavior in real time, thereby enhancing the safety of collaborative operations. Starting next June, she will join the Norlab at Laval University (Quebec, Canada) to continue her research in Arctic robotics, an extreme environment that poses new challenges in terms of navigation and perception.
Massimo Caccia (CNR)
Title: Marine robotics @ CNR: an historical perspective and new trends
Abstract:
The author provides an overview of research in marine robotics carried out at CNR in the last 35 years, discussing its relationship with worldwide technological evolution until current new trends related to the availability of light and relatively cheap COTS robots and AI developments.Massimo Caccia , graduated in Electronic Engineering at the University of Genova joined CNR in 1993. His theoretical and applied research activities focused on marine robotics, mainly addressing the topics of modelling and identification, cooperative guidance and control, vision-based motion estimation and control, and embedded real-time platforms and architectures for Unmanned Marine Vehicles. He is among the European pioneer researchers in the field of uncrewed surface vehicles and, with his research group, he developed pioneer research projects on the application of robotic technology to maritime safety. Research results, certified by more than 200 publications in international books, journals and conferences, led to the partnership in a number of EC, national and regional projects. Recently he coordinated the projects Blue RoSES (EMFF), ARES (PON Blue Growth), and MODA (PNRM), that represent state-of-the-art R&D in the definition of guidelines and codes of practice for the operation of robotic vehicles in harbour waters and coastal water, and in the integration of shipbuilding and robotics according to the vision identified by Blue Italian Growth National Technology Cluster.
Maria Méndez Real (Lab-STICC)
Title: Security Challenges of Multi-environment unmanned systems – what can go wrong?
Abstract: The use of drones across a wide range of sectors is expanding rapidly to encompass all kinds of critical and strategic missions, which involves the handling of private, confidential and strategic data. With the trend towards the integration and coexistence of commercial, specialised and military-modified systems, security and reliability are becoming key concerns. This talk will highlight the current challenges posed by the protection of these complex, autonomous and distributed systems, and will offer some insights into the collaborative detection of anomalous behaviour.
Maria Méndez Real is Professor Chair at Université de Bretagne Sud at Lorient, within Lab-STICC laboratory. She has been working on hardware and embedded security for more than ten years. She currently holds a Junior Professor Chair on Security and Trust of Autonomous Swarm of Maritime Drones at Université de Bretagne Sud from the French National Agency of Research. Her current research interest includes security of complex, autonomous systems with a special focus on system collaboration, security of embedded artificial intelligence, and embedded detection of deviant behavior applied to unmanned systems.
David Cabecinhas (ISR-Lisboa)
Title: Cooperative Marine Robotics – Towards autonomomy and endurance
Abstract: This talk presents advances in cooperative marine robotics at ISR/IST, showing how teams of ASVs and AUVs can enable persistent and adaptive ocean operations. We discuss coordination strategies, autonomy architectures, and field results demonstrating how heterogeneous robotic systems overcome endurance and sensing limitations of single vehicles, moving towards sustained ocean presence with minimal human intervention.
David Cabecinhas received the Licenciatura and Ph.D. degrees in electrical and computer engineering from the Instituto Superior Técnico, Universidade de Lisboa, Portugal, in 2006 and 2014, respectively. He was the ISR responsible for BlueRoSES and RAMONES, two European Union funded projects, and is currently responsible for a nationally funded Portugal-India cooperation project. He participated on multiple national and international research projects leveraging his experience on systems integration and guidance, navigation and control of unmanned aerial, surface and underwater robotic vehicles. His current research interests include nonlinear cooperative control and navigation, sensor-based and vision-based control, modeling and identification, systems integration, and fault detection and mitigation with applications to underwater, surface, aerial, and space autonomous robotic vehicles.
Nadir Kapetanović (MARBLE)
Title: Building the Infrastructure for Maritime Robotics Research: Experiences of the Centre of Excellence MARBLE
Abstract: The Centre of Excellence MARBLE is establishing a unique research and innovation ecosystem for maritime robotics, autonomous systems, and digital maritime technologies. This presentation provides an overview of MARBLE's research areas and the development of its core infrastructure, including the renovation of the headquarters and the deployment of three pilot sites designed to support experimentation, validation, and technology transfer. The talk will highlight the planned laboratories, testing facilities, specialized equipment, and digital infrastructure that will enable multidisciplinary research in autonomous surface and underwater systems, maritime sensing, artificial intelligence, and sustainable blue economy applications. Particular emphasis will be placed on the role of research infrastructure in bridging fundamental research, industrial collaboration, and real-world deployment, creating a long-term platform for innovation in the maritime domain.
Nadir Kapetanović is the Head of Engineering and Research Infrastructure at the Centre of Excellence MARBLE, Zagreb, Croatia. With a PhD in robotics and extensive experience in marine and field robotics, he leads the planning, development, and operation of MARBLE's research infrastructure, including laboratories, experimental facilities, and pilot sites. His work spans research project management, engineering leadership, infrastructure strategy, and international collaboration, supporting the advancement of autonomous maritime systems and blue economy technologies.