Search Results (125)

Inspection, maintenance, and repair (IMR) operations on underwater infrastructure remain costly and time-intensive because fully teleoperated remote operated vehicle s(ROVs) lack the range and dexterity necessary for precise cooperative underwater manipulation, and the alternative of using professional divers is ruled out due to the risk involved. This work presents and experimentally validates an autonomous, dual-I-AUV (Intervention–Autonomous Underwater Vehicle) system capable of assembling rigid pipeline segments through coordinated actions in a confined underwater workspace. The first I-AUV is a Girona 500 (4-DoF vehicle motion, pitch and roll stable) fitted with multiple payload cameras and a 6-DoF Reach Bravo 7 arm, giving the vehicle 10 total DoF. The second I-AUV is a BlueROV2 Heavy equipped with a Reach Alpha 5 arm, likewise yielding 10 DoF. The workflow comprises (i) detection and grasping of a coupler pipe section, (ii) synchronized teleoperation to an assembly start pose, and (iii) assembly using a kinematic controller that exploits the Girona 500’s full 10 DoF, while the BlueROV2 holds position and orientation to stabilize the workspace. Validation took place in a 12 m × 8 m × 5 m water tank. Results show that the paired I-AUVs can autonomously perform precision pipeline assembly in real water conditions, representing a significant step toward fully automated subsea construction and maintenance. Full article

The ocean encompasses the majority of the Earth’s surface and harbors substantial energy resources. Nevertheless, the intricate and asymmetrically distributed underwater environment renders existing target detection performance inadequate. This paper presents an enhanced YOLOv8s approach for underwater robot object detection to address issues of subpar image quality and low recognition accuracy. The precise measures are enumerated as follows: initially, to address the issue of model parameters, we optimized the ninth convolutional layer by substituting certain conventional convolutions with adaptive deformable convolution DCN v4. This modification aims to more effectively capture the deformation and intricate features of underwater targets, while simultaneously decreasing the parameter count and enhancing the model’s ability to manage the deformation challenges presented by underwater images. Furthermore, the Triplet Attention module is implemented to augment the model’s capacity for detecting multi-scale targets. The integration of low-level superficial features with high-level semantic features enhances the feature expression capability. The original CIoU loss function was ultimately substituted with Shape IoU, enhancing the model’s performance. In the underwater robot grasping experiment, the system shows particular robustness in handling radial symmetry in marine organisms and reflection symmetry in artificial structures. The enhanced algorithm attained a mean Average Precision (mAP) of 87.6%, surpassing the original YOLOv8s model by 3.4%, resulting in a marked enhancement of the object detection model’s performance and fulfilling the real-time detection criteria for underwater robots. Full article

Hydrodynamic coefficients determine the behavior of all simulated underwater vehicles. Therefore, it is essential to precisely define their values when aiming to replicate a real vehicle. Generally established procedures for obtaining them tend to have limitations, especially in transient responses. To address these issues, this paper proposes a comprehensive methodology for obtaining the hydrodynamic coefficients of an underwater vehicle. The main novelty is the combination of empirical measurements as a first step and evolutionary algorithms as a final step for optimizing the coefficients. The proposed methodology is described and applied to a commercially available remotely operated vehicle (ROV) BlueROV2, followed by analyzing the results in detail and including several tests that compare it to the real vehicle to validate its adequacy. Full article

This study focuses on the remotely operated underwater vehicle (ROV) and addresses key issues in existing simulation systems, such as neglecting the influence of ocean currents on the ROV’s trajectory or only simulating the impact of ocean currents instead of combining wake flow and ocean currents. Additionally, the visualization capabilities of current simulation systems still have room for improvement. This paper develops a three-dimensional path simulation system for ocean inspection robots to tackle these challenges based on MATLAB and Simulink. The system optimizes the drag matrix of the original simulation model by decomposing the sea current into three directional components in three-dimensional space and simulating the relative velocity in each direction separately; it introduces the influence of the current wake, thus more accurately realizing the trajectory simulation of the ROV under the current perturbation. Experimental results demonstrate high consistency between the optimized model’s simulation outcomes and theoretical expectations. The proposed system significantly improves trajectory evolution stability and consistency, compared to traditional models. The findings of this study indicate that the proposed optimized simulation system not only effectively verifies the applicability of control algorithms but also provides reliable data support for ROV design and optimization. Additionally, it lays a solid foundation for further developing intelligent underwater robots based on Internet of Things (IoT) technology. Full article

Traditional track-driven deep-sea nodule mining solutions significantly disrupt seabed ecosystems, making them unsuitable for commercial application. In contrast, ROV-like alternatives, such as the hovering mining vehicle, or HMV, offer substantial improvement in this regard and are deemed to be a viable way forward. This paper proposes an adaptive neural network fuzzy sliding mode controller architecture for the underwater trajectory tracking of HMV. The algorithm, named the Adaptive Radial Basis Function Neural Network Fuzzy Sliding Mode Controller (ARFSMC), replaces modeled vehicle dynamics with a radial basis function neural network (RBFNN). To enhance disturbance rejection, an adaptive mechanism is applied to the RBFNN output weighting matrix. Additionally, a fuzzy inference system (FIS) is implemented as the switching term, replacing the traditional signum function, to reduce high-frequency oscillations in the control signal. The stability of the algorithm under unknown external disturbance was confirmed via Lyapunov stability analysis. To validate the ARFSMC’s performance, three numerical simulation cases were conducted, each designed to reflect an expected operation scenario of the HMV, through which the tracking performance of the ARFSMC under time-varying system inertia is validated and benchmarked against conventional sliding mode control (CSMC) and double-loop sliding mode control (DSMC). The simulation results confirm that comparing the above two controllers, the root mean square error (RMSE) of the ARFSMC is reduced by 15.0% and 11.4%, respectively. And when comparing the CSMC, the chattering is reduced by 97.8%. Both indicate their high robustness and superior performance in tracking control. The controller development and numerical validation in this work are aimed at the trajectory tracking challenge of the HMV in deep-sea mining operation. The dynamical modeling of the vehicle is based on parameters of the HaiMa ROV. External disturbance from currents were considered as sinusoidal functions modified with random noise. Full article

Remotely operated vehicles (ROVs) face challenges in achieving optimal trajectory tracking performance during underwater movement due to external disturbances and parameter uncertainties. To address this issue, this paper proposes a position and attitude control strategy for underwater robots based on a reinforcement learning active disturbance rejection controller. The linear active disturbance rejection controller has achieved satisfactory results in the field of underwater robot control. However, fixed-parameter controllers cannot achieve optimal control performance for the controlled object. Therefore, further exploration of the adaptive capability of control parameters based on the linear active disturbance rejection controller was conducted. The deep deterministic policy gradient (DDPG) algorithm was used to optimize the linear extended state observer (LESO). This strategy employs deep neural networks to adjust the LESO parameters online based on measured states, allowing for more accurate estimation of model uncertainties and environmental disturbances, and compensating the total disturbance into the control input online, resulting in better disturbance estimation and control performance. Simulation results show that the proposed control scheme, compared to PID and fixed parameter LADRC, as well as the double closed-loop sliding mode control method based on nonlinear observers (NESO-DSMC), significantly improves the disturbance estimation accuracy of the linear active disturbance rejection controller, leading to higher control precision and stronger robustness, thus demonstrating the effectiveness of the proposed control strategy. Full article

In order to realize the detection of marine engineering facilities, the hardware system of a new type of remotely operated vehicle (ROV) is designed independently, and the control system, including the lower computer program and the upper computer software, is developed. At the same time, in order to explore the thrust distribution of the thruster and realize the optimization of the thrust distribution under the installation position and installation angle of the designed thruster, the mathematical model of the ROV propulsion system is established. The simulation models of ROV motion control and thrust distribution are established in MATLAB R2022a and Unity 3D, respectively. Given the thrust input of the compound motion, the sequential quadratic programming (SQP) method and the direct logic method are used to compare the simulation results of thrust distribution. Finally, the underwater attitude control experiment and the application experiment of the actual scene are carried out. Combined with the simulation and experimental results, the feasibility of using the sequential quadratic programming method to optimize the thrust allocation is verified, and it is shown that the new ROV system can basically meet the expected design requirements. Full article

Marine mammal monitoring, a growing field of research, is critical to cetacean conservation. Traditional ‘tagging’ attaches sensors such as GPS to such animals, though these are intrusive and susceptible to infection and, ultimately, death. A less intrusive approach exploits UUV commanded by a human operator above ground. The development of AI for autonomous underwater vehicle navigation models training environments in simulation, providing visual and physical fidelity suitable for sim-to-real transfer. Previous solutions, including UVMS and L2D, provide only satisfactory results, due to poor environment generalisation while sensors including sonar create environmental disturbances. Though rich in features, image data suffer from high dimensionality, providing a state space too great for many machine learning tasks. Underwater environments, susceptible to image noise, further complicate this issue. We propose SWiMM_2.0, coupling a Unity simulation modelling of a BLUEROV UUV with a DRL backend. A pre-processing step exploits a state-of-the-art CMVAE, reducing dimensionality while minimising data loss. Sim-to-real generalisation is validated by prior research. Custom behaviour metrics, unbiased to the naked eye and unprecedented in current ROV simulators, link our objectives ensuring successful ROV behaviour while tracking targets. Our experiments show that SAC maximises the former, achieving near-perfect behaviour while exploiting image data alone. Full article

The remotely operated vehicle (ROV), a vital deep-sea platform, offers key advantages, including operational duration via continuous umbilical power, high task adaptability, and zero human risk. It has become indispensable for deep-sea scientific research and marine engineering. To enhance surveys of cobalt-rich crusts (CRCs) on complex seamount terrains, the 4500-m-class Haima ROV integrates advanced payloads, such as underwater positioning systems, multi-angle cameras, multi-functional manipulators, subsea shallow drilling systems, sediment samplers, and acoustic crust thickness gauges. Coordinated control between deck monitoring and subsea units enables stable multi-task execution within single dives, significantly improving operational efficiency. Survey results from Caiwei Guyot reveal the following: (1) ROV-collected data were highly reliable, with high-definition video mapping CRCs distribution across varied terrains. Captured crust-bearing rocks weighed up to 78 kg, drilled cores reached 110 cm, and acoustic thickness measurements had a 1–2 cm margin of error compared to in situ cores; (2) Video and cores analysis showed summit platforms (3–5° slopes) dominated by tabular crusts with gravel-type counterparts, summit margins (5–10° slopes) hosting gravel crusts partially covered by sediment, and steep slopes (12–15° slopes) exhibiting mixed crust types under sediment coverage. Thicker crusts clustered at summit margins (14 and 15 cm, respectively) compared to thinner crusts on platforms and slopes (10 and 7 cm, respectively). The Haima ROV successfully investigated CRC resources in complex terrains, laying the groundwork for seamount crust resource evaluations. Future advancements will focus on high-precision navigation and control, high-resolution crust thickness measurement, optical imaging optimization, and AI-enhanced image recognition. Full article

This study proposes a control method for Remotely Operated Vehicles (ROVs) to actively dock with AUVs, to address the limitations of traditional docking and recovery schemes for Autonomous Underwater Vehicles (AUVs), such as restricted maneuverability and external disturbances. Firstly, a process and control strategy for ROV active docking with AUVs is designed, improving docking safety. Secondly, a Nonlinear Model Predictive Controller (NMPC) based on a Gaussian Function Sliding Mode Observer (GFSMO) compensation is designed for the ROV, generating smooth control inputs to achieve high-precision trajectory tracking and real-time docking. Finally, a joint simulation experiment is established through WEBOTS 2023a and MATLAB 2023a, verifying the superiority and feasibility of the designed controller and the proposed method. After parameter optimization, the simulation results show the method proposed in this study has a 90% success rate in 10 docking experiments under different disturbances. Full article

Autonomous underwater vehicles (AUVs) tasked with seafloor coverage require a robust integration of path planning and control strategies to operate in adverse real-world environments including obstacles, disturbances, and physical constraints. In this work, we present a fully integrated framework that combines an optimal coverage path planning approach with a robust constrained control algorithm. The path planner leverages a priori information of the target area to achieve maximal coverage, minimize path turns, and ensure obstacle avoidance. On the control side, we employ a reference modification technique that guarantees prescribed waypoint tracking performance under input constraints. The resulting integrated solution is validated in a high-fidelity simulation environment employing ROS, Gazebo, and ArduSub Software-in-the-Loop (SITL) on a BlueROV2 platform. The simulation results demonstrate the synergy between path planning and control, illustrating the framework’s effectiveness and readiness for practical seafloor operations such as underwater debris detection. Full article

Marine life exploration is constrained by factors such as limited scuba diving time, depth restrictions for divers, costly expeditions, safety risks to divers’ health, and minimizing harm to marine ecosystems, where traditional diving often risks disturbing marine life. This paper introduces Nu (named after an ancient Egyptian deity), a 3D-printed Remotely Operated Underwater Vehicle (ROUV) designed in an attempt to address these challenges. Nu employs Long Range (LoRa), a low-power and long-range communication technology, enabling wireless operation via a manual controller. The vehicle features an onboard live-feed camera with a separate communication system that transmits video to an external real-time machine learning (ML) pipeline for fish species classification, reducing human error by taxonomists. It uses Brushless Direct Current (BLDC) motors for long-distance movement and water pump motors for precise navigation, minimizing disturbance, and reducing damage to surrounding species. Nu’s functionality was evaluated in a controlled 2.5-m-deep body of water, focusing on connectivity, maneuverability, and fish identification accuracy. The fish detection algorithm achieved an average precision of 60% in identifying fish presence, while the classification model achieved 97% precision in assigning species labels, with unknown species flagged correctly. The testing of Nu in a controlled environment has met the system design expectations. Full article

This paper investigates the stability issues of the Unmanned Surface Vehicle (USV)–Unmanned Underwater Vehicle (ROV) system induced by cable loads under real marine conditions and high-speed operation. This study focuses on the dynamic coupling characteristics of cable forces affecting the unmanned platform and outlines the variation patterns of these forces under different operational scenarios. By developing the dynamic models of the USV, UC, and UUV, a comprehensive system model for the unmanned marine platform is constructed. The accuracy of the cable model is validated through experimental results, and the coupling interference effects of the cable during collaborative operations are systematically analyzed from multiple perspectives. Additionally, the cable tension and force behaviors under high-speed cruising conditions are thoroughly examined. The results provide a solid foundation for the development of cable load prediction models for collaborative marine unmanned platforms, and offer both theoretical and numerical insights for dynamic control strategies based on cable force adjustments. Full article

This study investigates underwater debris in a freshwater lake using remotely operated vehicles (ROVs) during two distinct survey periods: 2019 and 2024. The primary objective was to count and document visible debris (metal and plastic) on the lakebed based on ROV video recordings. A total of 356 debris items were observed in 2019, while only 39 items were recorded in 2024. The notable decrease in debris visibility in 2024 is likely attributed to dense algal growth during the survey months, which hindered the visual identification of objects on the lakebed. The study highlights the challenges of monitoring underwater debris in freshwater systems, particularly during periods of high algal activity, which can significantly impact visibility and detection efforts. While ROVs have proven effective in identifying submerged debris in clear water, this research underscores their limitations under reduced visibility conditions caused by algal blooms, turbidity diminishing the video quality. The results provide valuable insights into the temporal variation in debris visibility and contribute to ongoing efforts to improve freshwater debris monitoring techniques. Full article

The SLAM problem is a common challenge faced by ROVs working underwater, with the key issue being the accurate estimation of pose. In this work, we make full use of the positional information of point clouds and the surrounding pixel data. To obtain better feature extraction results in specific directions, we propose a method that accelerates the computation of the two-dimensional SO-CFAR algorithm, with the time cost being only a very slight increase compared to the one-dimensional SO-CFAR. We develop a sonar semi-direct method, adapted from the direct method used in visual SLAM. With the initialization from the ICP algorithm, we apply this method to further refine the pose estimation. To overcome the deficiencies of sonar images, we preprocess the images and reformulate the sonar imaging model in imitation of camera imaging models, further optimizing the pose by minimizing photometric error and fully leveraging pixel information. The improved front end and the accelerated two-dimensional SO-CFAR are assessed through quantitative experiments. The performance of SLAM in large real-world environments is assessed through qualitative experiments. Full article