The ability to observe the world has seen significant developments in the last few decades, alongside the techniques and methodologies to derive accurate digital replicas of observed environments. Underwater ecosystems present greater challenges and remain largely unexplored, but the need for reliable and up-to-date information motivated the birth of the Interreg Italy–Croatia SUSHI DROP Project (SUstainable fiSHeries wIth DROnes data Processing). The aim of the project is to map ecosystems for sustainable fishing and to achieve this goal a prototype of an Unmanned Underwater Vehicle (UUV), named Blucy, has been designed and developed. Blucy was deployed during project missions for surveying the benthic zone in deep waters of the Adriatic Sea with non-invasive techniques compared to the use of trawl nets. This article describes the strategies followed, the instruments applied and the challenges to be overcome to obtain an accurately georeferenced underwater survey with the goal of creating a marine digital twin.

This work proposes the development of a scheme for the fault diagnosis of the actuators of a simulated model accurately representing the behaviour of an autonomous under-water vehicle. The Fossen model usually adopted to describe the dynamics of the underwater vehicle has been generalised in this paper to take into account time–varying sea currents. The proposed fault detection and isolation strategy uses a data–driven approach relying on multi–layer perceptron neural networks that include auto–regressive exogenous prototypes. These tools are thus exploited to design a bank of dynamic neural networks for residual generation that are trained on the basis of the input and output measurements acquired from the simulator. The neural network bank is able to provide the detection of the faults affecting the actuators jointly with their isolation in case of simultaneous and concurrent faults The paper firstly describes the steps performed for deriving the proposed fault diagnosis solution. Secondly, the effectiveness of the scheme is demonstrated by means of high–fidelity simulations, in presence of faults and marine current.

The availability of accurate, reliable and up-to-date information concerning the state of marine resources is essential to create a decision support system for sustainable fishing to protect ecosystems. Within the Interreg Italy-Croatia SUSHI DROP Project (SUstainable fiSHeries wIth DROnes data Processing) a prototype of an Unmanned Underwater Vehicle (UUV) was developed as a detection system capable of surveying the benthic zone in deep waters of the Adriatic Sea. Traditional survey methods based on the capture of living organisms, for example through the use of trawl nets, are invasive, extremely expensive and at the same time prohibited in protected marine areas. The need to develop accurate and non-invasive methods to map and study marine ecosystems is highlighted in the EU Strategy for the Adriatic-Ionian Region (EUSAIR) action plan. To meet these objectives, a UUV system equipped with various scientific instruments has been implemented and in this work we present the first surveys carried out.

The study of underwater environments has been revolutionized by the use of autonomous underwater vehicles. However, effective guidance and control of these vehicles face challenges such as modeling errors, environmental disturbances, and the inherent under-actuation of many designs. To address these challenges, we propose a Neuro-Adaptive Fixed-Time Sliding Mode Control framework for under-actuated underwater vehicles. The issue of under-actuation is resolved using a line-of-sight guidance system based on look-ahead distance, enabling accurate trajectory tracking. A Fixed-Time Sliding Mode Controller is employed to guarantee faster convergence. To handle modeling uncertainties, the controller is augmented with a neural network (NN) trained using a composite error learning, which incorporates prediction errors from a state observer into the NN weight update law, enhancing learning performance. Additionally, a Disturbance Observer (DOB) is integrated to estimate and counteract environmental disturbances. The stability of the proposed control system is proven using Lyapunov theory. To validate its effectiveness, the control framework is tested in a high-fidelity simulation under scenarios involving significant uncertainties, external disturbances, and actuator faults.