Description du projet
Une nouvelle technologie permet aux navires de «voir» dans les océans
Le transport maritime demeure l’épine dorsale du commerce mondial. Alors qu’il en est ainsi depuis des milliers d’années, le transport maritime s’engage sur une nouvelle voie sans pilote. Les constructeurs automobiles rivalisant pour construire des voitures autonomes, les navires commerciaux télécommandés ne sont peut-être pas une idée si farfelue. Le projet MARINA, financé par l’UE, ouvrira la voie en répondant à un besoin du marché d’accroître la sécurité de l’industrie mondiale du transport maritime, de réduire son impact environnemental lié aux collisions et de préparer l’avenir de la navigation autonome. Plus précisément, il développera une solution innovante faisant appel à un système LADAR unique et novateur. Pour réduire le risque de collision avec d’autres navires, des mammifères ou même du bois flotté, le projet combinera un traitement en temps réel de pointe avec un algorithme avancé de détection et de classification des objets basé sur des techniques d’apprentissage automatique.
Objectif
Shipping is a key driver of the EU economy, but dense traffic lanes, tighter schedules, high cost of trained staff and
increasingly difficult weather patterns have put serious pressures on sustainability and environmental safety of commercial
shipping. Contact and collision incidences are now the most frequent and overall the costliest type of accidents in the
maritime transport sector. Accidents force 1 out of 10 ships to an unplanned dry dock stay every year, costing on average
€400,000 per incident, and have detrimental impact on the environment due to the release of pollutants into the water. Semi
and fully submerged objects cause concern for shipping because they go undetected by state-of-the-art sensors, presenting
an acute need for improved observation capability of the ocean surface layer. Aware of this clear market need to increase
the global maritime transport industry’s safety, to decrease its environmental impact through collisions and to prepare for a
future of autonomous shipping, the present consortium has developed an innovative solution using a unique and novel
LADAR system. Our new sensor combines state-of-the-art real-time processing with an advanced object detection and
classification algorithm based on machine learning techniques, to detect and classify objects in the ocean surface layer in a
range of up to 2nm ahead of the ship. LADAR’s ability for obstacle detection will allow ship operators to operate their vessels
efficiently and safely, reducing the risk of collision with other ships, driftwood, mammals or submerged containers. MARINA
is a strong and complimentary consortium, where all partners have collaborated together extensively in preceding R&D&I
projects. The aim of the project is to advance the system to TRL8, then to qualify the product in real-life operations to reach
TRL9 and finally to support the commercial viability. Commercialization is expected to lead to an accumulated revenue of
€786m 5 years post-project.
Champ scientifique
- natural sciencescomputer and information sciencesartificial intelligencecomputer visionobject detection
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsensors
- social sciencessocial geographytransport
- natural sciencesbiological scienceszoologymammalogy
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
Mots‑clés
Programme(s)
Régime de financement
IA - Innovation actionCoordinateur
3071 Limassol
Chypre
L’entreprise s’est définie comme une PME (petite et moyenne entreprise) au moment de la signature de la convention de subvention.