Note: The underwater industry is an important part of European economy, including wind energy, oil&gas, food, pharma, mining, and bio- and geo- science. A responsible and environmentally-friendly growth of this economy calls for automation of monitoring to prevent unexpected energy blackouts, oil&gas spills, and pollution from food, pharma, and mining. This in turn requires development of reliable AI for underwater robotics. The REMARO ETN brings together recognized robotics AI, software reliability, and safety experts. It shall train 15 ESRs able to realize the vision of reliable autonomy for underwater applications.
REMARO attacks one of the most pressing problems of modern computing, the safety of AI, in the well defined context of submarine robotics. The REMARO ESRs will develop the first ever underwater robotics AI methods with quantified reliability, correctness specs, models, tests, and analysis & verification methods. REMARO rests on two founding principles: 1. The submarine robot autonomy requires a comprehensive hybrid deliberative architecture, 2. Safety and reliability must be co-designed simultaneously with cognition, not separately, as an afterthought.
The expertise of the consortium allows to deliver a world-class interdisciplinary training-by-research program in computer vision and machine learning, reasoning and planning, model-driven-engineering, testing, verification, and model-checking. The REMARO program includes almost 40 days of intense activities, 3 cross-sector cross-discipline Challenge Camps, and 37 secondments, including 20 at industrial labs. The network will communicate results to two large research communities and to industry via European platforms and its own Industry Follow Group. The training material will be published in the REMARO book and the REMARO online Learning Hub. The software and data will be licensed for open use to accelerate research and maximize the long-lasting impact on European underwater robotics industry.
http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.pngContribution to a book/Contribution to a conference proceedingsAntal, L.RWTH* ; Link, F.RWTH* ; Ábrahám, E.RWTH* Counterexample-Guided Abstraction Refinement for Star-Based Neural Network Verification 2026Reachability Problems : 19th International Conference, RP 2025, Madrid, Spain, October 1–3, 2025, Proceedings / edited by Pierre Ganty, Alessio Mansutti Reachability Problems : 19. International Conference, RP 2025-, MadridMadrid, Spain, 1 Oct 2025 - 3 Oct 20252025-10-012025-10-03Cham : Springer Nature Switzerland, Lecture Notes in Computer Science16230,202-216(2026)[10.1007/978-3-032-09524-4_14]2026BibTeX |
EndNote:
XML,
Text |
RIS
http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.pngContribution to a book/Contribution to a conference proceedingsAntal, L. (Corresponding author)RWTH* ; Aubard, M. ; Ábrahám, E.RWTH* ; Madureira, A. ; Madureira, L. ; Costa, M. ; Pinto, J. ; Campos, R. A Collision Avoidance Method for Autonomous Underwater Vehicles Based on Long Short-Term Memories 2023Innovations in Bio-Inspired Computing and Applications : Proceedings of the 13th International Conference on Innovations in Bio-Inspired Computing and Applications (IBICA 2022) Held During December 15-17, 2022 / edited by Ajith Abraham, Anu Bajaj, Niketa Gandhi, Ana Maria Madureira, Cengiz Kahraman 13. International Conference on Innovations in Bio-Inspired Computing and Applications, IBICA22, Auburn, WAAuburn, WA, USA, 15 Dec 2022 - 17 Dec 20222022-12-152022-12-17Cham : Springer Nature Switzerland, Lecture Notes in Networks and Systems649,448-457(2023)[10.1007/978-3-031-27499-2_42]2023 FilesBibTeX |
EndNote:
XML,
Text |
RIS