Operators of offshore production units (OPUs) employ risk-based assessment (RBA) techniques in order to minimise inspection expenses while maintaining risks at an acceptable level. However, when human divers and workers are involved in inspections conducted at high heights, the operational risks can be significant. Recently, there has been a growing trend towards the use of unmanned aerial vehicles (UAVs), autonomous surface vehicles (ASVs), remotely operated vehicles (ROVs), and autonomous underwater vehicles (AUVs) for inspections of offshore structures as a means to reduce exposure to human risk. This article provides an analysis of these vehicle inspection capabilities and their potential to enhance robustness and safety within the oil and gas industry. The review assesses both the advantages and the drawbacks associated with these innovative systems, providing valuable comparisons and assessments on their potential use as viable alternatives to conventional inspection methods.

This paper describes the use of navigation data to generate a model in order to answer to the following questions. What is the ship with less efficiency in my fleet? What is the best strategy to improve the overall efficiency of my fleet? What is the ship that I should sell in priority? What is the influence of this maintenance policy on the performance of my fleet? The application case of this paper is based on one fleet of 13 ships containing 223 trips that gather approximately 6844 traveling days. The developed mathematical model is using Key Performance Indicators (KPIs) based on Fuel consumption performance, Aging, Work performance, Sea condition, Steaming Time, Emissions, and Port Logistic. Afterwards a Data Envelopment Analysis (DEA) model is discussed. Both laden and ballast conditions are considered. Afterwards, a Multi Criterion Decision Analysis (MCDA) is proposed in order to assist the ship-owner in the improvement of the performance of their fleet. A methodology to compare the efficiency of various ships in a fleet has been introduced in this paper and it provides a way to compare similar or different ship types and sizes during their operation. This study offers a method to exclude the engineer subjectivity by assessing the ship efficiency from different aspects using Data Envelopment Analysis. The results suggest that this new methodology can efficiently provide a multi-criteria decision framework to improve maintenance and fleet management strategies. The outcomes show a performance classification of the ships inside a fleet in a way that best and worst ships are identified at any moment. These findings provide a new way to address efficiency and performance in ship fleet management. Developed methodology allows to minimize operational resources hence reduce costs.