This paper presents a comprehensive overview of cutting-edge autonomous forklifts, with a strong emphasis on sensors, object detection and system functionality. It aims to explore how this technology is evolving and where it is likely headed in both the near and long-term future, while also highlighting the latest developments in both academic research and industrial applications. Given the critical importance of object detection and recognition in machine vision and autonomous vehicles, this area receives particular attention. The article provides an in-depth summary of both commercial and prototype forklifts, discussing key aspects such as design features, capabilities and benefits, and offers a detailed technical comparison. Specifically, it clarifies that all available data pertains to commercially available forklifts. To obtain a better understanding of the current state-of-the-art and its limitations, the analysis also reviews commercially available autonomous forklifts. Finally, this paper includes a comprehensive bibliography of research findings in this field.

This paper introduces an innovative approach to address the challenges of inspecting offshore wind turbines by presenting a real-time dynamic path-planning system for remotely operated vehicles (ROVs). Focused on floating wind turbine structures, the proposed methodology integrates an Inertial Measurement Unit (IMU) into the structure, allowing dynamic adjustment of the inspection path based on real-time pose data. Utilizing a fault-tolerant control solution, the system enables autonomous flight control of ROVs, maintaining consistent orientation towards the structure and desired inspection distance. The applicability of the approach is validated through simulations in the OceanRINGS+ control suite, emphasizing the importance of dynamic path planning in enhancing efficiency, safety, and cost-effectiveness in offshore wind turbine inspections.

This paper presents a start to finish approach on the inspection and repair of damaged ship hulls in water. The repair of ship hulls in water has been made viable by recent developments in Friction Stir Welding (FSW) of steels. The project is a European Union (EU) funded collaboration involving a variety of academic and industry partners aiming to increase the productivity of small and medium sized EU shipyards. This paper outlines the overall procedure of a repair mission while focusing on the inspection task by use of Remotely Operated Vehicles (ROV), as performed in a variety of environments on a fractured plate made from ship grade steel. The equipment and processing procedures are detailed with discussion demonstrating the capabilities in generating the required quality of 3D models in order for defects to be identified and for a sufficiently sized repair patch to be designed.

In this research, two transfer learning models were trained in order to detect sacrificial anodes on the base of a floating offshore wind turbine with the aim to aid the ROV pilot in navigation. Two models were trained on a dataset of sacrificial anodes collected by our team at WindFloat Atlantic windfarm in collaboration with OceanWinds. This data was then labelled and one model was trained and validated to detect the anodes. This workflow was then further tested in a tank with anodes manufactured from 3D printed materials to test the generalisability of the workflow using the second transfer learning model. The models performed well, one achieving recalls of 85% and the other demonstrating robustness by detecting anodes in the tank despite their vastly different appearance and absence from the training data.

This paper describes an ROV remote presence control exercise conducted over both Geostationary Orbit (GEO) and Low Earth Orbit (LEO) Satellite Communications links. Its purpose was to investigate and compare the reliability, latency and available bandwidth provided by both systems for the chosen application. The ROV used is operated by the Centre for Robotics and Intelligent Systems (CRIS), University of Limerick, Ireland. It was deployed in December 2022 from the Irish Marine Institute’s Research Vessel (RV) 'Tom Crean', off the south coast of Ireland and was controlled by a PC running OceanRINGS smart software control system. The GEO Satellite Communications link used was the vessel’s VSAT system, and the electronic phased array antenna, router and mobile phone hotspot provided the link to the Starlink LEO constellation. A remote operator located in Co. Sligo, Ireland, accessed the OceanRINGS control PC across a TeamViewer link. Upload and Download connection speeds and Latencies between the OceanRINGS PC and onshore servers were recorded. A series of exercises were then performed, remotely altering the heading and depth of the ROV. Wireshark network protocol analyser was used to capture packet data from the network interfaces throughout the exercises. On analysis, it was found that the use of the LEO satellite link significantly reduced latency when compared to the GEO link, while transfer speeds increased by a factor of 13.78 (download) and 7.71 (upload). The exercise demonstrated that both satellite connections could facilitate high-level remote presence control of the ROV.

Robotic technologies are increasingly used to perform inspection, maintenance, and intervention tasks in offshore wind farms. However, these tasks can be challenging due to the dynamic and harsh environments in which wind farms are typically located. In this paper, we present a set of developments in underwater robot capabilities for offshore wind applications, including a discussion of control systems, garaged ROVs, auto-docking solutions, necessary intervention capabilities, and inspection equipment. We also present recent results of field trials for real-time underwater imaging and laser scanning. The paper concludes with a discussion of the importance of robust systems and equipment selection and future directions for research in this area.

By creating a dependable, transparent, and cost-effective system for forecasting and ongoing environmental impact monitoring of exploration and exploitation activities in the deep sea, TRIDENT seeks to contribute to the sustainable exploitation of seabed mineral resources. In order to operate autonomously in remote locations under harsh conditions and send real-time data to authorities in charge of granting licenses and providing oversight, this system will create and integrate new technology and innovative solutions. The efficient monitoring and inspection system that will be created will abide by national and international legal frameworks. At the sea surface, mid-water, and the bottom, TRIDENT will identify all pertinent physical, chemical, geological, and biological characteristics that must be monitored. It will also look for data gaps and suggest procedures for addressing them. These are crucial actions to take in order to produce accurate indicators of excellent environmental status, statistically robust environmental baselines, and thresholds for significant impact, allowing for the standardization of methods and tools. In order to monitor environmental parameters on mining and reference areas at representative spatial and temporal scales, the project consortium will thereafter develop and test an integrated system of stationary and mobile observatory platforms outfitted with the most recent automatic sensors and samplers. The system will incorporate high-capacity data processing pipelines able to gather, transmit, process, and display monitoring data in close to real-time to facilitate prompt actions for preventing major harm to the environment. Last but not least, it will offer systemic and technological solutions for predicting probable impacts of applying the developed monitoring and mitigation techniques.

This paper presents a Tether Multipoint Management System (TMMS) for a Resident Remotely Operated Vehicle (ROV) in offshore operations. Operating close to structure or seabed. Boulders etc tether management is critical to ensure the safety and effectiveness of operations without tether entanglement. The proposed TMMS is composed of one or more Independent Tether Management Nodes (ITMN) enabling the ROV to move freely and autonomously around offshore structures while minimizing the risk of tether entanglement. The ITMN can use a combination of active thrusters (axial, lateral, and vertical) and passive (buoyancy and fin) control to achieve the necessary degrees of freedom and an onboard battery for power. The proposed system expands the operational capability of the ROV, allowing it to perform tasks not possible beforehand, saving time and increasing efficiency.

The use of underwater vehicle manipulator systems (UVMS) equipped with cameras has gained significant attention due to their capacity to perform underwater tasks autonomously. However, controlling both the manipulator and the remotely operated vehicle (ROV) based on the vision system information is not an easy task, especially in situations where the vehicle cannot be parked/held stationary. Most of the existing approaches work based on complex matrix calculations for the inverse kinematics (IK), which can lead to high computational costs and the need to deal with singularity problems. A problem arises when the amount of time needed to calculate the UVMS configuration can result in reduced frequency of target pose estimation, beyond the point where the target has moved out of the camera field of view. Therefore, this paper proposes an autonomous visual servoing approach for UVMS, including an extension of a heuristic technique named M-FABRIK (Mobile - Forward and Backward Reaching IK) to calculate the UVMS inverse kinematics in a simple and fast way. This approach aims to control both the configuration of the manipulator and ROV position in order to allow underwater intervention in situations where the ROV cannot be parked/held stationary. This solution allows the vehicle to be positioned according to additional criteria, besides avoiding matrix inversion and being robust to singularities. Trials have been performed with a manipulator mounted on a work-class ROV for an autonomous underwater monitoring task and results demonstrate a simple and fast approach, which is able to set the configuration of the manipulator as well as the ROV for visual servoing applications in real-time, such as for monitoring, tracking and intervention tasks underwater.

This article presents a simulated and experimental analysis of the effects of the evaporation duct on microwave propagation in the Irish Sea. The evaporation duct is a phenomenon that occurs almost permanently over all the world’s oceans and allows electromagnetic waves to travel beyond the horizon. Weather data logged over several years from four buoys off the east coast of Ireland has been analyzed to find the probability and strength of the evaporation duct. Signal propagation in the evaporation duct has been simulated using the parabolic equation model and compared to results obtained from an experimental setup in the Irish Sea. The best antenna heights and frequencies to maximize signal propagation at this location are also found. Results show that the evaporation duct can be used to provide high bandwidth communications beyond the horizon with an uptime of approximately 40%, and that weather data from buoys can be used to predict the performance of the communications link. While this method of communication is not one that can be relied on all the time, it could be useful to reduce dependency on expensive satellite links or provide nontime critical communications.

An investigation of the effects of wind gusts on the directly interconnected wind generators is reported, and techniques toward the mitigation of the wind gust negative influences have been proposed. Using a directly interconnected system approach, wind turbine generators are connected to a single synchronous bus or collection grid without the use of power converters on each turbine. This bus can then be transformed for transmission onshore using High Voltage Alternating Current, Low-Frequency Alternating Current or High Voltage Direct Current techniques with shared power conversion resources onshore connecting the farm to the grid. Analysis of the potential for instability in transient conditions on the wind farm, for example, caused by wind gusts is the subject of this paper. Gust magnitude and rise time/fall time are investigated. Using pitch control and the natural damping of the high inertial offshore system, satisfactory overall system performance and stability can be achieved during these periods of transience.

In this paper, we investigate the methods to be used in the inspection of damaged ship hulls in water at sea, as part of the European Union (EU) Robotic Survey, Repair and Agile Manufacture (RESURGAM) Project. Employing underwater robotics equipped with camera or laser sensors, along with robust control and positioning systems, 3D models of the damaged section(s) can be produced with a goal of providing sufficient information for the subsequent design of repair patch(es), and ultimately the application of this repair to the ship. This work will allow damaged ships at sea to seek repair without the need for access to a dry dock. Preliminary results from recent field operations are included in this paper, with further field research to be carried out later this year.

Although underwater manipulators are considered the most suitable tools for executing many subsea intervention operations, they are an example of robots not designed for autonomous tasks. The subsea manipulator Schilling Titan 2, for instance, is composed of a sequence of constrained joints that makes impossible finding a closed-form analytical solution for its inverse kinematics. For this reason, numerical methods have normally been used. Nevertheless, these methods typically result in high computational load and may need many iterations to find a solution. FABRIK is an inverse kinematics approach which has as main advantages a fast convergence and a low computational cost, avoiding matrix inversion and being robust to singularities. However, the constraints imposed by the joints of the Titan 2 manipulator also makes impossible solving its inverse kinematics using FABRIK. A recent extension of FABRIK, named FABRIK-R, presents a solution for this problem. Therefore, this paper proposes to overcome the mentioned issues by solving the inverse kinematics of a high constrained subsea manipulator based on FABRIK-R and presents a comparison between this solution and a classical approach based on a second-order pseudo-inverse Jacobian. The advantages of the proposed approach are demonstrated in simulation experiments, and its feasibility is demonstrated in real experiments in manipulation tasks performed in dry lab conditions.

This paper is an overview to Visual Simultaneous Localization and Mapping (V-SLAM). We discuss the basic definitions in the SLAM and vision system fields and provide a review of the state-of-the-art methods utilized for mobile robot's vision and SLAM. This paper covers topics from the basic SLAM methods, vision sensors, machine vision algorithms for feature extraction and matching, Deep Learning (DL) methods and datasets for Visual Odometry (VO) and Loop Closure (LC) in V-SLAM applications. Several feature extraction and matching algorithms are simulated to show a better vision of feature-based techniques.

This paper presents research and development for autonomous ROV manipulation systems with vision servoing in dynamic underwater conditions. Underwater inspection operations are performed by work-class ROVs equipped with robotic manipulators. The ROV generally travel at pre-planned paths extracting features from the environment, usually detected by a visual sensor. A monocular hybrid position based visual servoing (PBVS) system for underwater inspection on Work-class ROVs with a camera mounted on the manipulator and other on the top of the ROV is proposed. The effectiveness of the proposed system is verified through experiments carried out on real-world environmental tests consisting on using a work-class ROV to autonomously inspect a wall with 10 fiducial markers.

One of the most important key points in the intelligent transportation systems is scene understanding of the known and unknown surrounding environment to achieve a safe driving for smart mobile robots and cars. Semantic segmentation can address most of the perception needs of mobile robots and Intelligent Vehicles (IV). There are several deep learning approaches based on Convolutional Neural Network (CNN) for semantic segmentation. Most of these techniques have been designed on a pretrained network base and loading a specific weight file is necessary for them. In this paper, we propose a deep architecture for semantic segmentation from scratch based on an asymmetry encoder- decoder architecture using Ghost-Net and U-Net which we have called it Ghost-UNet. This model can be used for precise segmentation using a combination of low-level spatial information and high-level feature maps. We focus our work on outdoor datasets to evaluate the proposed model which is tested on the Cityscapes dataset. The proposed model has good pixel accuracy and mean Intersection over Union (mIoU) compared with other valid literature.

The conventional fuzzy c-spherical shells (FCSS) clustering model is extended to cluster shells involving non-crisp numbers, in this paper. This is achieved by a vectorized representation of distance, between two non-crisp numbers like the crisp numbers case. Using the proposed clustering method, named vector fuzzy c-spherical shells (VFCSS), all crisp and non-crisp numbers can be clustered by the FCSS algorithm in a unique structure. Therefore, we can implement FCSS clustering over various types of numbers in a unique structure with only a few alterations in the details used in implementing each case. The relations of VFCSS applied to crisp and non-crisp (containing symbolic-interval, LR-type, TFN-type and TAN-type fuzzy) numbers are presented in this paper. Finally, simulation results are reported for VFCSS applied to synthetic LR-type fuzzy numbers; where the application of the proposed method in real life and in geomorphology science is illustrated by extracting the radii of circular agricultural fields using remotely sensed images and the results show better performance and lower cost computational complexity of the proposed method in comparison to conventional FCSS.

This paper presents an autonomous tracking system of a moving target Underwater Operations of Work-class ROVs using a single camera. A computer vision system is developed to detect fiducial markers attached to the target and estimate its position in the global frame, representing it in the latitude and longitude coordinates for the global positioning controller of the ROV. Real-world environmental tests consisting of using a workclass ROV to autonomously tracking a smaller ROV is presented and results demonstrate the feasibility of the developed system.

The overall control system for an open-frame Remotely Operated Vehicle (ROV) is typically built from three subsystems: guidance, navigation and control (GNC). The control allocation plays a vital role in the control subsystem. Typically, open-frame underwater vehicles have p actuators (thrusters) for the motion in the horizontal plane, and the control allocation problem, in this case, is very complex and hard to visualise, because the normalised constrained control subset is a p-dimensional unit cube. The aim of this paper is to give a clear picture and a geometric interpretation of the problem and to introduce a hybrid method, based on the integration of a weighted pseudoinverse and the fixed-point method. The main idea of the hybrid method is visualised, and the deep geometric insight is provided using a “virtual” ROV in low-dimensional control spaces, including visualisation of the attainable command set, solution lines, control energy spheres and the role of pseudoinverse and fixed-point iterations. The same concepts are then extended to higher-dimensional cases, for open-frame ROV with four X-shaped (vectored) horizontal thrusters, which is one of the most common thruster configurations for commercial ROVs. The proposed hybrid method has been developed, integrated into a generic fault-tolerant ROV control system and evaluated in virtual and real-world environments off the west coast of Ireland using observation-class ROV Latis and work-class ROV Étaín.

Feature extraction and matching is a key component in image stitching and a critical step in advancing image reconstructions, machine vision and robotic perception algorithms. This paper presents a fast and robust underwater image mosaicking system based on (2D)(2)PCA and A-KAZE key-points extraction and optimal seam-line methods. The system utilizes image enhancement as a preprocessing step to improve quality and allow for greater keyframe extraction and matching performance, leading to better quality mosaicking. The application focus of this paper is underwater imaging and it demonstrates the suitability of the developed system in advanced underwater reconstructions. The results show that the proposed method can address the problems of noise, mismatching and quality issues which are typically found in underwater image datasets. The results demonstrate the proposed method as scale-invariant and show improvements in terms of processing speed and system robustness over other methods found in the literature.