Autonomous Underwater Vehicles (AUVs) do need to be equipped with highly-accurate and robust navigation systems in order to perform challenging operations and complex missions. Nevertheless, since the Global Positioning System (GPS) is not a feasible, functional solution in the underwater scenario, the localization task is fulfilled by employing filtering techniques - as Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) - or Dead Reckoning (DR) strategies. Even though the specific algorithm architecture may vary, such methodologies usually rely on the direct linear speed measurements provided by specialized and expensive sensors, such as the Doppler Velocity Log (DVL). Thus, DVL failures or fallacies alongside DVL-denied environments may arise as unexpected causes for a severe malfunction of the whole navigation system. Motivated by the aforementioned considerations and the outstanding performance of Long Short-Term Memory (LSTM) neural networks in time-series regression problems, an LSTM-based DR approach has been developed to estimate the surge and sway body-fixed frame velocities, without canonically employing the DVL sensor.

In recent years, seabed inspection has become one of the most sought-after tasks for Autonomous Underwater Vehicles (AUVs) in various applications. Forward-Looking Sonars (FLS) are commonly favored over optical cameras, which are not-negligibly affected by environmental conditions, to carry out inspection and exploration tasks. Indeed, sonars are not influenced by illumination conditions and can provide high-range data at the cost of lower-resolution images compared to optical sensors. However, due to the lack of features, sonar images are often hard to interpret by using conventional image processing techniques, leading to the necessity of human operators analyzing thousands of images acquired during the AUV mission to identify the potential targets of interest. This paper reports the development of an Automatic Target Recognition (ATR) methodology to identify and localize potential targets in FLS imagery, which could help human operators in this challenging, demanding task. The Mask R-CNN (Region-based Convolutional Neural Network), which constitutes the core of the proposed solution, has been trained with a dataset acquired in May 2019 at the Naval Support and Experimentation Centre (Centro di Supporto e Sperimentazione Navale - CSSN) basin, in La Spezia (Italy). The ATR strategy was then successfully validated online in the same site in October 2019, where the targets were replaced and relocated on the seabed.

In the early 2000s, data from the latest World Health Organization estimates paint a picture where one-seventh of the world population needs at least one assistive device. Fortunately, these years are also characterized by a marked technological drive which takes the name of the Fourth Industrial Revolution. In this terrain, robotics is making its way through more and more aspects of everyday life, and robotics-based assistance/rehabilitation is considered one of the most encouraging applications. Providing high-intensity rehabilitation sessions or home assistance through low-cost robotic devices can be indeed an effective solution to democratize services otherwise not accessible to everyone. However, the identification of an intuitive and reliable real-time control system does arise as one of the critical issues to unravel for this technology in order to land in homes or clinics. Intention recognition techniques from surface ElectroMyoGraphic (sEMG) signals are referred to as one of the main ways-to-go in literature. Nevertheless, even if widely studied, the implementation of such procedures to real-case scenarios is still rarely addressed. In a previous work, the development and implementation of a novel sEMG-based classification strategy to control a fully-wearable Hand Exoskeleton System (HES) have been qualitatively assessed by the authors. This paper aims to furtherly demonstrate the validity of such a classification strategy by giving quantitative evidence about the favourable comparison to some of the standard machine-learning-based methods. Real-time action, computational lightness, and suitability to embedded electronics will emerge as the major characteristics of all the investigated techniques.

Seabed inspection is one of the most sought-after applications for autonomous underwater vehicles (AUVs). Acoustical sensors, such as side-scan sonars and forward-looking sonars (FLSs), are commonly favored over optical cameras to carry out such a task. Indeed, sonars are not influenced by illumination conditions and can provide high-range data. However, due to the lack of features and low resolution, acoustical images are often hard to interpret with conventional automatic techniques, forcing human operators to analyze thousands of collected images to identify the so-called objects of potential interest (OPIs). In this article, we report the development of an automatic target recognition (ATR) methodology to identify and localize OPIs in FLS imagery. Such detections have been then exploited to realize a virtual world model with the probabilistic multiple hypothesis anchoring data association and model tracking algorithm. Distinct models of convolutional neural networks have been trained with a data set acquired in May 2019 at the Naval Support and Experimentation Centre (Centro di Supporto e Sperimentazione Navale—CSSN) basin in La Spezia, Italy. The ATR strategy has been successfully validated offline with the data gathered in October 2019 in the same site where the seabed targets were replaced and relocated. As regards the world modeling technique, it has been preliminarily tested on a simulated scenario built upon unmanned underwater vehicle Simulator. Finally, both the ATR and world modeling systems were on-field tested in October 2020 at the CSSN basin in a multivehicle architecture by employing an acoustical channel between FeelHippo AUV and an autonomous moving buoy.

The underwater industry and scientific community are actively researching the development of vehicles that combine the functionalities of autonomous underwater vehicles and remotely operated vehicles. An innovative approach to address the challenges posed by underwater exploration is the development of autonomous underwater reconfigurable vehicles (AURVs). These vehicles are designed to adapt their configuration to suit the requirements of the task at hand. The flexibility of AURVs enables them to undertake a variety of underwater missions, ranging from scientific research to deep-sea exploration. The Department of Industrial Engineering at the University of Florence, Italy, has developed and patented an innovative AURV that is able to quickly change its shape to suit different tasks. The reconfigurable underwater vehicle for inspection, free-floating intervention and survey tasks (RUVIFIST) have been equipped with two extreme configurations. The first configuration is a slender one meant for long navigation tasks, while the second configuration is a stocky one designed for tackling complex objectives such as inspection or intervention operations. With the ability to adapt its form to suit the task at hand, the RUVIFIST vehicle represents a significant advancement in underwater vehicle technology. This work provides an overview of the challenges faced and the solutions adopted during the development of this new vehicle. This article presents the results of experimental campaigns to test the reconfigurable system of the vehicle and the strategies developed for the guidance, navigation, and control system of AURVs. Finally, preliminary tests were conducted to explore the integration of machine learning and deep learning algorithms that are compatible with the purpose of automatic target recognition.