Sort by
Refine Your Search
-
expertise in autonomous marine systems. The research focus will be on development, implementation and verification of novel algorithms for motion planning and control of autonomous underwater vehicles. You
-
degradation modes. Evaluating suitable sensor technologies and data sources for acquiring relevant metrics. Developing tools and algorithms to automatically analyse sensor data, assess asset condition, and
-
achieve automated data driven optimization (in terms of time and quality) of polishing process parameters by application of machine learning algorithms, leading to a robust, repeatable and fast polishing
-
thus including sensing systems, tool condition features selection, algorithms for automated signal preprocessing, feature extraction and decision making based on ML and AI. An integral part of
-
on developing machine learning algorithms to support the use of complex urban simulators in decision-making under uncertainty. This PhD project shifts the focus from optimality to relevance in urban land-use and
-
an optimal molecular representation (including data procurement) and integrating generative model and binding oracles. Propose an algorithm to bias the generative models towards desirable properties, such as
-
. Development of multimodal AI models that fuse data from multiple types of sensors to accurately model and predict wind turbine blade damage. Establish and develop data science pipelines for wind turbine blade
-
of solvers for stochastic optimization problems, and test the methods on real-life data. As part of the PhD you will be following advanced courses to extend your skills, implement and test algorithms, and
-
the molten salt/metal interface at multiple scales, from atomistic to mesoscopic, with the goal of identifying the fundamental mechanisms driving corrosion. Moreover, you will use this knowledge to suggest
-
of Europe’s ‘green transition’ to clean energy. You will work on cutting-edge research tasks, with objectives including • new algorithms and strategies to improve autonomous Airborne Wind Energy (AWE) operation