ARTIFICIAL INTELLIGENCE (AI) APPLICATIONS
At MARIN we explore the pivotal role of artificial intelligence (AI) in the maritime industry. AI stands on the brink of transforming a vast range of maritime activities, offering sophisticated data analytics, machine learning algorithms, and autonomous systems. These technologies bolster safety measures, optimize resource allocation, and foster environmental sustainability.
Our commitment lies in leveraging AI's capabilities to drive safety, innovation and sustainability throughout the maritime industry. Through dedicated research efforts, collaborative initiatives, and strategic partnerships, we pioneer novel solutions to address the multifaceted challenges confronting our oceans.
Below, we showcase a diverse array of AI projects that exemplify our commitment to cutting-edge research and practical solutions. Join us in spearheading the movement towards a more sustainable future for the maritime sector and our planet, fueled by the transformative influence of artificial intelligence.
Our commitment lies in leveraging AI's capabilities to drive safety, innovation and sustainability throughout the maritime industry. Through dedicated research efforts, collaborative initiatives, and strategic partnerships, we pioneer novel solutions to address the multifaceted challenges confronting our oceans.
Below, we showcase a diverse array of AI projects that exemplify our commitment to cutting-edge research and practical solutions. Join us in spearheading the movement towards a more sustainable future for the maritime sector and our planet, fueled by the transformative influence of artificial intelligence.
Contact
Bulent Duz
Senior Reseacher
AI projects
Data-driven Ship trajectory prediction
AI models can predict ship trajectories over longer time periods, providing useful insights for vessel traffic management. For safe and effective application, it is essential to understand these techniques and to know the accuracy of the predictions.
Data-driven Ship trajectory prediction
AI models can predict ship trajectories over longer time periods, providing useful insights for vessel traffic management. For safe and effective application, it is essential to understand these techniques and to know the accuracy of the predictions.
Autonomous sailing against the wind
Reinforcement learning agents learn to make decisions through interactions with an environment. Such techniques can have various applications in maritime domain from design to operation: improving ship operational design, training future pilots or providing advices on board. We trained a Reinforcement Learning agent to sail an Optimist against the wind.
Autonomous sailing against the wind
Reinforcement learning agents learn to make decisions through interactions with an environment. Such techniques can have various applications in maritime domain from design to operation: improving ship operational design, training future pilots or providing advices on board. We trained a Reinforcement Learning agent to sail an Optimist against the wind.
Ship Course-Keeping in Waves using Reinforcement Learning
For a quick and efficient voyage, a ship needs to stay on course. We show how reinforcement learning can be applied as a smart and efficient controller for this task.
Ship Course-Keeping in Waves using Reinforcement Learning
For a quick and efficient voyage, a ship needs to stay on course. We show how reinforcement learning can be applied as a smart and efficient controller for this task.
Improving underwater vehicle manoeuvring and control
MARIN’s research is focussing on enabling wider use of AUVs in the offshore sector by allowing them to safely navigate near large structures, performing docking and conducting visual inspections with minimal collision risk.
Improving underwater vehicle manoeuvring and control
MARIN’s research is focussing on enabling wider use of AUVs in the offshore sector by allowing them to safely navigate near large structures, performing docking and conducting visual inspections with minimal collision risk.
Machine learning without sharing data using Federated Learning
Federated Learning harnesses the collective intelligence of multiple decentralized devices or servers, enabling them to collaboratively train a shared model while keeping data localized. This innovative method, popularized by Google, not only reduces privacy risks but also improves the robustness and accuracy of machine learning models by utilizing diverse data sources.
Machine learning without sharing data using Federated Learning
Federated Learning harnesses the collective intelligence of multiple decentralized devices or servers, enabling them to collaboratively train a shared model while keeping data localized. This innovative method, popularized by Google, not only reduces privacy risks but also improves the robustness and accuracy of machine learning models by utilizing diverse data sources.
