Artificial intelligence is accelerating autonomous navigation by turning vessel data into accurate trajectory predictions. Leveraging AIS information and LSTM neural networks, the approach strengthens route forecasting, situational awareness and operational efficiency. The results demonstrate how advanced machine learning can support safer, more reliable decision-making for next-generation autonomous and remotely operated vessels.

Autonomous underwater transport is advancing through coordinated AUV systems capable of carrying payloads with flexible connections. By combining nonlinear dynamic modelling with PID and optimal pole placement control, engineers addressed buoyancy, stability and motion challenges. The findings reveal critical trade-offs between power efficiency and control performance in complex underwater operations.

Advancing navigation in ice-covered waters requires more than a single sensor. By combining diverse sensing technologies into an integrated ice sensor suite, operators and autonomous systems can build real-time ice severity maps, calibrate ship-ice interactions and improve route decisions. The approach addresses a key barrier to safer, more capable autonomous Arctic operations.

A proposed data aggregation framework is strengthening navigation in ice-covered waters by combining forecasts, ice sensing technologies and vessel-specific risk models. By transforming diverse data into regional ice severity maps, the approach supports safer route optimization, informed decision-making and future autonomous operations in challenging polar environments.

Digital twins are emerging as a cornerstone of maritime digital transformation, turning real-time sensor data, models and simulations into actionable operational insight. By clarifying their structure, applications and future evolution, the approach highlights how data-driven learning systems can optimize performance, support decision-making and unlock new opportunities across complex assets.

Artificial intelligence is enabling smarter, energy-efficient ship operations through real-time decision support. Using sea-trial data and optimized neural network models, the system accurately predicts fuel consumption across voyage scenarios, supporting weather routing, trim and ballast optimization. The approach demonstrates how data-driven forecasting can improve operational efficiency, sustainability and voyage planning.

Artificial intelligence is enabling smarter, energy-efficient ship operations through real-time decision support. Using sea-trial data and optimized neural network models, the system accurately predicts fuel consumption across voyage scenarios, supporting weather routing, trim and ballast optimization. The approach demonstrates how data-driven forecasting can improve operational efficiency, sustainability and voyage planning.

The debate over requirements definition and systems engineering continues to shape the procurement of complex naval vessels, where balancing operational needs, affordability, and technical feasibility remains a significant challenge. Growing recognition of the close relationship between requirements and design is driving calls for more integrated and iterative approaches to early-stage ship development.

Hybrid propulsion systems are attracting growing interest as shipowners seek practical pathways to improve energy efficiency and reduce emissions. This study demonstrates that battery-diesel-electric propulsion can be integrated into modern bulk carriers with minimal impact on cargo capacity, while careful system placement may also offer operational benefits through improved weight distribution and trim optimisation.

As environmental, safety, and regulatory expectations increase, ship recycling is under growing pressure to modernise and improve operational standards. The development of knowledge-based expert systems offers a means of supporting decision-making across the recycling process, helping stakeholders enhance safety, environmental performance, and management of increasingly complex ship dismantling activities.

As ship design projects grow in complexity, designers are increasingly seeking methods that can accommodate uncertainty and keep options open for longer. This research demonstrates how set-based design, supported by intelligent decision-support tools, can improve resilience to late-stage design changes, enabling more informed decisions and reducing the risk of costly redesign during development.

Slamming remains one of the most demanding load cases in marine structural design, with significant implications for vessel safety and durability. Improved numerical methods are enhancing the prediction of water-impact pressures and forces, providing deeper insight into the effects of hull geometry and impact conditions while supporting more robust structural assessments.