Andrzej Wasowski, ITU, DK
(REMARO Coordinator)

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.

The REMARO project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement N°956200.