Underwater Tasks Research Articles

Analysis of trans‐domain motion process of bullet‐shaped trans‐domain amphibious vehicle

AbstractA fully functional prototype of a bullet‐shaped trans‐domain amphibious vehicle with the ability to perform reciprocating cross‐medium movements has been developed. Once the bullet‐shaped underwater vehicle completes its designated underwater tasks, upon reaching a suitable location for surface observation, it will transform into a bullet‐shaped coaxial counter‐propeller aircraft to carry out cross‐domain out‐of‐water and performing aerial flight missions. The successful transition of the vehicle into amphibious mode is attributed to the design of an innovative energy attitude multiplexing mechanism. Simultaneously, a rational and effective hybrid‐switching strategy has been proposed to enhance the reliability of the vehicle's amphibious mode transition. In view of the complex and changeable cross‐domain environment, we have adopted a modular design concept, breaking down the entire cross‐domain movement process into three key phases: air operation flight, transient cross‐domain, and underwater active sailing. Detailed theoretical analysis, algorithm design, and experimental research have been conducted for each phase. This paper proposes and expounds the key design principles, evaluates the performance indicators of key components, and weighs the matching of body dynamics and propulsion performance to ensure that the vehicle achieves the expected performance. Finally, the success of the test at different phases further proves that the vehicle has the ability to achieve complete cross‐domain operation.

Fisher-Information-Matrix-Based USBL Cooperative Location in USV-AUV Networks.

With the development of underwater technology and the increasing demand for ocean development, more and more intelligent equipment is being applied to underwater scientific missions. Specifically, autonomous underwater vehicle (AUV) clusters are being used for their flexibility and the advantages of carrying communication and detection units, often performing underwater tasks in formation. In order to locate AUVs with high precision, we introduce an unmanned surface vehicle (USV) with global positioning system (GPS) and propose a USV-AUV network. Furthermore, we propose an ultra-short baseline (USBL) acoustic cooperative location scheme with an orthogonal array, which is based on underwater communication with sonar. Based on the derivation of the Fisher information matrix formula under Cartesian parameters, we analyze the positioning accuracy of AUVs in different positions under the USBL positioning mode to derive the optimal array of the AUV formation. In addition, we propose a USV path planning scheme based on Dubins path planning functions to assist in locating the AUV formation. The simulation results verify that the proposed scheme can ensure the positioning accuracy of the AUV formation and help underwater research missions.

Research on an Underwater Object Detection Network Based on Dual-Branch Feature Extraction

Underwater object detection is challenging in computer vision research due to the complex underwater environment, poor image quality, and varying target scales, making it difficult for existing object detection networks to achieve high accuracy in underwater tasks. To address the issues of limited data and multi-scale targets in underwater detection, we propose a Dual-Branch Underwater Object Detection Network (DB-UODN) based on dual-branch feature extraction. In the feature extraction stage, we design a dual-branch structure by combining the You Only Look Once (YOLO) v7 backbone with the Enhanced Channel and Dilated Block (ECDB). It allows for the extraction and complementation of multi-scale features, which enable the model to learn both global and local information and enhance its perception of multi-scale features in underwater targets. Furthermore, we employ the DSPACSPC structure to replace the SPPCSPC structure in YOLOv7. The DSPACSPC structure utilizes atrous convolutions with different dilation rates to capture contextual information at various scales, compensating for potential information loss caused by pooling operations. Additionally, we utilize a dense connection structure to facilitate feature reuse and enhance the network’s representation and generalization capabilities. Experimental results demonstrate that the proposed DB-UODN outperforms the most commonly used object detection networks in underwater scenarios. On the URPC2020 dataset, the network achieves an average detection accuracy of 87.36%.

Recent progress on underwater soft robots: adhesion, grabbing, actuating, and sensing.

The research on biomimetic robots, especially soft robots with flexible materials as the main structure, is constantly being explored. It integrates multi-disciplinary content, such as bionics, material science, mechatronics engineering, and control theory, and belongs to the cross-disciplinary field related to mechanical bionics and biological manufacturing. With the continuous development of various related disciplines, this area has become a hot research field. Particularly with the development of practical technologies such as 3D printing technology, shape memory alloy, piezoelectric materials, and hydrogels at the present stage, the functions and forms of soft robots are constantly being further developed, and a variety of new soft robots keep emerging. Soft robots, combined with their own materials or structural characteristics of large deformation, have almost unlimited degrees of freedom (DoF) compared with rigid robots, which also provide a more reliable structural basis for soft robots to adapt to the natural environment. Therefore, soft robots will have extremely strong adaptability in some special conditions. As a type of robot made of flexible materials, the changeable pose structure of soft robots is especially suitable for the large application environment of the ocean. Soft robots working underwater can better mimic the movement characteristics of marine life in the hope of achieving more complex underwater tasks. The main focus of this paper is to classify different types of underwater organisms according to their common motion modes, focusing on the achievements of some bionic mechanisms in different functional fields that have imitated various motion modes underwater in recent years (e.g., the underwater sucking glove, the underwater Gripper, and the self-powered soft robot). The development of various task types (e.g., grasping, adhesive, driving or swimming, and sensing functions) and mechanism realization forms of the underwater soft robot are described based on this article.

A transformer-based network for perceptual contrastive underwater image enhancement

Vision-based underwater image enhancement methods have received much attention for application in the fields of marine engineering and marine science. The absorption and scattering of light in real underwater scenes leads to severe information degradation in the acquired underwater images, thus limiting further development of underwater tasks. To solve these problems, a novel transformer-based perceptual contrastive network for underwater image enhancement methods (TPC-UIE) is proposed to achieve visually friendly and high-quality images, where contrastive learning is applied to the underwater image enhancement (UIE) task for the first time. Specifically, to address the limitations of the pure convolution-based network, we embed the transformer into the UIE network to improve its ability to capture global dependencies. Then, the limits of the transformer are then taken into account as convolution is reintroduced to better capture local attention. At the same time, the dual-attention module strengthens the network’s focus on the spatial and color channels that are more severely attenuated. Finally, a perceptual contrastive regularization method is proposed, where a multi-loss function made up of reconstruction loss, perceptual loss, and contrastive loss jointly optimizes the model to simultaneously ensure texture detail, contrast, and color consistency. Experimental results on several existing datasets show that the TPC-UIE obtains excellent performance in both subjective and objective evaluations compared to other methods. In addition, the visual quality of the underwater images is significantly improved by the enhancement of the method and effectively facilitates further development of the underwater task.

Research on Compliant Controller of Underwater Mechanical Capture System Based on Impedance Theory

Due to the requirement of the exploitation of marine resources, the execution of specific underwater tasks by onboard manipulators has become one of the key research fields in domestic and all over the world. Based on the underwater capture system designed for the UUV recycling task, which consists of an underwater manipulator and a mechanical capture device, this paper first constructs the kinematics and dynamics model of the capture system through theoretical analysis such as theoretical mechanics and theory of mechanism. Then, combined with the requirements of the recycling task, through the theoretical basis of fluid mechanics such as Morrison equation, dynamic of the capture system in underwater environment is analysed, with a compliant controller designed for the capture system based on impedance theory in order to reduce the impact of underwater environment in the capture task. Moreover, as the capture system modelled in the Adams dynamics simulation platform, it is verified that the designed compliant controller can reduce the underwater environmental impact through simulation experiments in the Adams dynamic platform.

Coordinating Tethered Autonomous Underwater Vehicles towards Entanglement-Free Navigation

This paper proposes an algorithm that provides operational strategies for multiple tethered autonomous underwater vehicle (T-AUV) systems for entanglement-free navigation. T-AUVs can perform underwater tasks under reliable communication and power supply, which is the most substantial benefit of their operation. Thus, if one can overcome the entanglement issues while utilizing multiple tethered vehicles, the potential applications of the system increase including ecosystem exploration, infrastructure inspection, maintenance, search and rescue, underwater construction, and surveillance. In this study, we focus on developing strategies for task allocation, path planning, and scheduling that ensure entanglement-free operations while considering workload balancing among the vehicles. We do not impose restrictions on the size or shape of the vehicles at this stage; our primary focus is on efficient tether management as an initial work on the topic. To achieve entanglement-free navigation, we propose a heuristic based on the primal-dual technique, which enables initial task allocation and path planning while minimizing the maximum travel cost of the vehicles. Although this heuristic often generates sectioned paths due to its workload-balancing nature, we also propose a mixed approach to provide feasible solutions for non-sectioned initial paths. This approach combines entanglement avoidance techniques with time scheduling and sectionalization methods. To evaluate the effectiveness of our algorithm, extensive simulations were conducted with varying problem sizes. The computational results demonstrate the potential of our algorithm to be applied in real-time operations, as it consistently generates reliable solutions within a reasonable time frame.

Real-time underwater target detection for AUV using side scan sonar images based on deep learning

To overcome the shortcomings of traditional methods for underwater target detection in sonar images, a novel target detection algorithm based on deep learning is proposed for the real-time detection for an autonomous underwater vehicle equipped with a side scan sonar (SSS). First, the preprocessing of raw SSS images and data augmentation methods are proposed to improve the quality and quantity of the data set. Second, to improve the detection efficiency, a method based on threshold segmentation and pixel importance value is used to quickly determine whether there are suspected targets in the SSS images. Then, an MA-YOLOv7 network based on YOLOv7 with multi-scale information fusion and an attention mechanism is proposed to detect targets in the screened images, and a target localization method is proposed to obtain the location (latitude and longitude) of the target. Finally, the algorithm is verified through simulation experiments and field tests. The results demonstrate that the proposed algorithm achieves state-of-the-art performance and can be applied to real underwater tasks with a detection recall of 0.836 and time consumption of 0.355 s per image.

A Hybrid Quantum-Classical Algorithm for Underwater Target Classification

Offshore channel clearance is an essential underwater task to protect vessels and divers effectively, but current underwater target classification relies heavily on operator identification. Machine learning provides highly accurate methods for image classification as well as detection. In this paper, a new hybrid quantum-classical classification algorithm is proposed. It uses quantum devices to reduce dimension and denoise data sets, greatly reducing the difficulty of classical computer processing data. Using abundant classical classification algorithms, the classification problem of different scenarios can be processed, improving the classification efficiency. Using two kinds of underwater object data sets as examples, the numerical simulation results show that the quantum algorithm can accurately achieve dimensionality reduction. This hybrid algorithm has polynomial acceleration in dimension reduction than classical methods, even considering the classical readout of quantum data. The results also show that the classification accuracy of the training set improves from 0.772 to 0.821 compared to the original dataset. Furthermore, different classical classifiers can be selected in the case of different objects, so this hybrid algorithm has broad application prospects in different fields.

An underwater explorer remotely operated vehicle: Unraveling the secrets of the ocean

In recent years, underwater robots have been an essential focus of marine science and technology applications. Whether it is the application of military tasks or general civil affairs, underwater robots have played a significant role. For example, unmanned underwater vehicles (UUVs) can work in the sea for a long time, have high maneuverability, and perform various underwater tasks. There are many subcategories of UUVs, such as autonomous underwater vehicles (AUVs), remotely operated vehicles (ROVs), and autonomous and remotely operated vehicles (ARVs) (Kong et al., 2020).

Nested Deep Feature Attention Module for Underwater Image Enhancement

The captured underwater images always suffer degradations because of absorption and light scattering in water. Thus, underwater image enhancement becomes indispensable as a precondition to carry out underwater tasks. Thus, we put forward an end-to-end structure to solve the problem of underwater image degradation. Our network uses continuously stacked deep-layer feature extraction modules to exploit more significant features. For purpose of enhancing the image contrast, we recover high-frequency information by hiring the nested residual attention groups in feature extraction modules, which can adaptively extract more deeper features. Moreover, channel attention module is hired in residual groups to emphasize important information. Comparing with other state-of-the-art approaches, our network performs best on quantitative and qualitative evaluations at datasets EUVP and UIEBD.

Adaptive Scheduling MAC Protocol in Underwater Acoustic Broadcast Communications for AUV Formation

With the rapid development of autonomous underwater vehicles (AUVs) and the continuous improvement of marine exploration requirements, AUV formation has emerged as a promising technique for performing underwater tasks with greater flexibility, adaptability, and scalability. To achieve AUV formation control, underwater acoustic communication networks (UACNs) are widely used to support information exchange among AUVs. Considering broadcast communications in fully connected mobile UACNs, existing medium access control (MAC) protocols face severe packet collision risk or low reuse efficiency. To improve the timeliness and reliability of the information exchange among AUVs, we develop an efficient scheduling-based adaptive broadcasting MAC (AB-MAC) protocol. The AB-MAC protocol is incompletely centralized, which can be reflected in two aspects. First, to ensure the consistency of the transmission schedule in the network, the AB-MAC protocol selects a control node for each frame to schedule the transmission of all nodes according to the updated network topology. The slot lengths and transmission sequences are changeable in each frame to avoid packet collisions and minimize frame lengths. Second, to further improve the efficiency and robustness of the protocol, all nodes adaptively adjust their transmission time by integrating the information contained in their previously received control packets and ordinary packets. The transmission scheduling problem is formulated as a combinatorial optimization problem, which can be solved by our proposed improved Genetic Algorithm. Numerical results demonstrate that the AB-MAC protocol not only performs well in terms of network throughput and average update interval but also has a high level of robustness even in low-quality underwater acoustic channels.

Vision-Based Underwater Target Following Control of an Agile Robotic Manta With Flexible Pectoral Fins

Manta-inspired robots have been increasingly applied in vision-based underwater tasks. However, owing to the refraction effect and motion coupling problem, their accurate target following control is still poorly understood. This paper proposes a vision-based underwater target following scheme for robotic manta. First, an agile robotic manta equipped with a binocular camera system is constructed. The motion modes are further detailed based on the propulsion analysis to the flexible pectoral fins. Second, a color-based underwater target detection and localization method is conceived. Specifically, the binocular refraction correction is employed to improve the localization accuracy. Third, combing the nonsingular terminal sliding mode controller and fuzzy inference system, a robust target following controller is presented to solve the coupling between distance and azimuth control of the robot. Finally, various aquatic experiments are conducted, verifying the effectiveness and robustness of the proposed underwater target following scheme. The obtained results provide valuable insights into the intelligent control of agile bioinspired robots performing vision-based tasks in dynamic underwater environments.

Underwater Target Detection Based on Improved YOLOv7

Underwater target detection is a crucial aspect of ocean exploration. However, conventional underwater target detection methods face several challenges such as inaccurate feature extraction, slow detection speed, and lack of robustness in complex underwater environments. To address these limitations, this study proposes an improved YOLOv7 network (YOLOv7-AC) for underwater target detection. The proposed network utilizes an ACmixBlock module to replace the 3 × 3 convolution block in the E-ELAN structure, and incorporates jump connections and 1 × 1 convolution architecture between ACmixBlock modules to improve feature extraction and network reasoning speed. Additionally, a ResNet-ACmix module is designed to avoid feature information loss and reduce computation, while a Global Attention Mechanism (GAM) is inserted in the backbone and head parts of the model to improve feature extraction. Furthermore, the K-means++ algorithm is used instead of K-means to obtain anchor boxes and enhance model accuracy. Experimental results show that the improved YOLOv7 network outperforms the original YOLOv7 model and other popular underwater target detection methods. The proposed network achieved a mean average precision (mAP) value of 89.6% and 97.4% on the URPC dataset and Brackish dataset, respectively, and demonstrated a higher frame per second (FPS) compared to the original YOLOv7 model. In conclusion, the improved YOLOv7 network proposed in this study represents a promising solution for underwater target detection and holds great potential for practical applications in various underwater tasks.

3U: Joint Design of UAV-USV-UUV Networks for Cooperative Target Hunting

A swarm of unmanned vehicles can provide fine-grained spatial-temporal information acquisition and monitoring in comparison to a single agent, which is beneficial in terms of environment mapping, terrain exploration, and target hunting. However, the cooperation of single type of unmanned vehicles may be not qualified for fulfilling complex underwater tasks considering the motion constraints. In this paper, a joint design of the unmanned aerial/surface/underwater vehicle (UAV-USV-UUV) network, also referred to as 3U network, is proposed for cooperative underwater target hunting. We first introduce the advantages of this 3U heterogeneous system in multi-task cooperation and portray its system model. Moreover, we propose an energy-oriented target hunting model by jointly optimizing the UAV's position, the UUV's trajectory as well as their inter-connectivity. Finally, DQN algorithms are conceived to solve the proposed target hunting problem. Simulation results show the proposed scheme is suitable for underwater target hunting with a high success rate considering a trade-off between the system energy consumption and inter-connectivity.

Fully Automatic Visual Servoing Control for Underwater Vehicle Manipulator Systems Based on a Heuristic Inverse Kinematics

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.

Multiple Attitude Estimation Models based on a Pressure Sensor Array

Autonomous navigation is critical for autonomous underwater vehicle to complete underwater tasks, and attitude is an essential parameter of autonomous navigation. Inspired by the biomimicry studies, three attitude estimation models based on a pressure sensor array are constructed, which are the direct method, the multi-layer perception model and the attitude estimation model based on physical knowledge respectively. The field tests are carried out to verify the effectiveness of the proposed methods, and the advantages and disadvantages of the three methods are compared. It turns out that the attitude estimation model based on physical knowledge achieves the optimal results, and the estimated error of pitch is lower than 1.9133°, and the estimated error of roll is lower than 2.6719°. Further, there is no cumulative attitude error, which complies that the attitude estimation model based on physical knowledge has a high potential for applications in autonomous navigation systems.

Research progress on positioning methods of submersibles for underwater detection of dams in the deepwater environment

<p indent="0mm">China has the largest number of high dams and large reservoirs and the fastest dam construction rate in the world. Many countries in Europe and America have experienced high dam and large reservoir collapse accidents or disasters caused by hidden dangers of underwater structures. Relevant experience and lessons have shown that deepwater detection, repair and reinforcement technologies, and equipment are vital for the long-term safe operation of high dams and large reservoirs. Traditional underwater detection in deepwater environments is mainly implemented by underwater unmanned submersibles equipped with optical or acoustic equipment because of the complexity of high dam structures and the particularity of reservoir environments. During the 13th Five-Year Plan period, the National Key R&amp;D Program approved and developed a manned submersible that is suitable for the deepwater environment of dams and capable of carrying experts in the dam engineering field to the deepwater environment for on-site inspection. These two underwater detection technologies and equipment are effective technologies in detecting, repairing, and reinforcing dam structures in deepwater environments, and underwater precise positioning technology is required for unmanned and manned submersibles to complete various complex underwater tasks in deepwater. First, this paper summarizes existing underwater positioning technologies and methods of unmanned submersibles. According to the principle, underwater positioning methods are divided into four categories: inertial navigation, optics, acoustics, and other methods, and the advantages and disadvantages of the various positioning methods are analyzed. Furthermore, the adaptability of different underwater positioning technologies, in addition to the complexity of the deepwater environment of high dams, is analyzed from the perspectives of safety guarantee, equipment research and development, economic benefits, etc. The use of acoustic ultra-short baseline devices, buoys, inertial positioning, and physical calibration for underwater positioning is proposed as a development trend for improving the positioning accuracy of the underwater operation of dam detection submersibles in deepwater environments. Various underwater positioning and navigation modes were rationally combined and supplemented to improve the accuracy and reliability of underwater positioning.

Towards end-to-end formation control for robotic fish via deep reinforcement learning with non-expert imitation

Collaboration of multiple robotic fish can accomplish various underwater tasks effectively. However, controlling robotic fish to maintain a specific formation remains a huge challenge, especially in complex and changing flow fields. This paper presents an end-to-end formation control approach in the leader–follower topology by combining deep reinforcement learning and imitation learning. First, we build a high-fidelity environment based on computational fluid dynamics (CFD) to generate samples for training the formation controller. In this environment, we maneuver the robotic fish by adjusting the maximum swing of its tail. Then, we model the formation control problem as a Markov decision process (MDP), where a compound reward function is tailored to guide the training. To improve the learning efficiency of the deep reinforcement learning (DRL) based controller, we propose a novel DRL algorithm on the top of deep Q-networks (DQN) and behavior cloning, which we call dueling double DQN (D3QN) with imitation. Combining with the designed imitation-based action selection strategy, this algorithm significantly reduce the blindness of agent exploration at the beginning of training. A series of experiments demonstrate the advantages of the proposed algorithm in terms of control accuracy, training efficiency, as well as generalization ability for different formation configurations.

A computation effective singularity avoidance method for the underwater manipulator with a non-spherical wrist

In order to perform increasingly complex underwater tasks, we have designed a hydraulic underwater non-spherical wrist manipulator with a binocular vision system and a six-dimensional force sensor mounted behind the end-effector, which can improve the path accuracy and automation capabilities of the system. The system lays a foundation for the high precision and autonomous deep-sea operation and can improve its intelligence level. In this paper, we focus on solving the singularity avoidance problem of the hydraulic underwater manipulator for accurate control, and propose a computationally efficient singularity avoidance method to improve the path accuracy of the manipulator with the non-spherical wrist. Firstly, the singular configurations of the manipulator are analyzed. Secondly, the Jacobian is decomposed into sub-block matrices to obtain the singular factors according to the singular configurations. Thirdly, the singularities are avoided by the approximate damped reciprocal method. Theoretical analysis shows that the computation costs of the proposed method are only one-third to one-half of that of the traditional methods. The simulation results prove that the proposed method can largely improve the path accuracy of the manipulator with less computation costs, which shows that our method would have a certain significance in improving the precision and real-time response of deep-sea operations.