Dynamic Underwater Environment Research Articles

An adaptive frequency-hopping detection for slowly-varying fading dispersive channels.

Frequency hopping (FH) signals have been widely used to improve performance against frequency selective fading phenomenon of underwater channels. However, the channel is slowly varying in regard to changes in weather conditions, and thus the conventional FH detection transmitting signals with fixed frequency cannot guarantee good detection performance in the dynamic underwater environment. To overcome the performance degradation in slowly-varying fading dispersive channels, this paper proposes an adaptive frequency-hopping (AFH) target detection method. Compared with conventional FH detection methods, the AFH can adaptively select the optimal detection frequency based on premeasured background noise and channel frequency response measured from previous experiments. Numerical simulations and lake trials are conducted to verify the effectiveness of the AFH. The simulation results show that the AFH has better detection performance than the conventional FH. The lake trial results have also verified the validity and feasibility of AFH. Importantly, AFH also achieves a better output signal-to-noise ratio under actual noise interference.

A Method for Underwater Biological Detection Based on Improved YOLOXs

This article proposes a lightweight underwater biological target detection network based on the improvement of YOLOXs, addressing the challenges of complex and dynamic underwater environments, limited memory in underwater devices, and constrained computational capabilities. Firstly, in the backbone network, GhostConv and GhostBottleneck are introduced to replace standard convolutions and the Bottleneck1 structure in CSPBottleneck_1, significantly reducing the model’s parameter count and computational load, facilitating the construction of a lightweight network. Next, in the feature fusion network, a Contextual Transformer block replaces the 3 × 3 convolution in CSPBottleneck_2. This enhances self-attention learning by leveraging the rich context between input keys, improving the model’s representational capacity. Finally, the positioning loss function Focal_EIoU Loss is employed to replace IoU Loss, enhancing the model’s robustness and generalization ability, leading to faster and more accurate convergence during training. Our experimental results demonstrate that compared to the YOLOXs model, the proposed YOLOXs-GCE achieves a 1.1% improvement in mAP value, while reducing parameters by 24.47%, the computational load by 26.39%, and the model size by 23.87%. This effectively enhances the detection performance of the model, making it suitable for complex and dynamic underwater environments, as well as underwater devices with limited memory. The model meets the requirements of underwater target detection tasks.

Enhancing underwater target localization through proximity-driven recurrent neural networks

Environmental monitoring, ocean research, and underwater exploration are just a few of the marine applications that require precise underwater target localization. This study goes into the field of underwater target localization using Recurrent Neural Networks (RNNs) enhanced with proximity-based approaches, with a focus on mean estimation error as a performance metric. In complex and dynamic underwater environments, conventional localization systems frequently face challenges such as signal degradation, noise interference, and unstable hydrodynamic conditions. This paper presents a novel approach to employing RNNs to increase the accuracy of underwater target localization by exploiting the temporal dynamics of proximity-informed data. This method uses an RNN architecture to track changes in audio emissions from underwater targets sensed by a microphone network. Using the temporal correlations represented in the data, the RNN learns patterns indicative of target localization quickly and correctly. Furthermore, the addition of proximity-based features increases the model's ability to understand the relative distances between hydrophone nodes and the target, resulting in more accurate localization estimates. To evaluate the suggested methodology, thorough simulations and practical experiments were carried out in a variety of underwater environments. The results show that the RNN-based strategy beats conventional methods and works effectively even in difficult settings. The utility of the proximity-aware RNN model is demonstrated, in particular, by considerable reductions in the mean estimate error (MEE), an important performance measure.

AquaKey

Underwater Visible Light Communication (UVLC) is promising due to its relatively strong penetration capability in water and large frequency bandwidth. Visible Light Communication (VLC) is also considered a safer wireless communication paradigm as light signals can be constrained within the area of interest with obstacles such as walls, reducing the chance of potential attack. However, this intuitional security assumption is not true anymore in underwater environment. Recent research shows that the eavesdropping risk of UVLC is more severe than we thought, attributed to the divergence and scattering effects of light beams in water. In this paper, we harness the dynamic nature of underwater environments as a true random resource to extract symmetric keys for UVLC. Specifically, the proposed AquaKey system incorporates instantaneous bidirectional channel probing, computation of relative channel characteristics, and an environment-adaptive quantization algorithm. The above design addresses unique challenges caused by the dynamic underwater environment, including self-interference, high-frequency disturbance, and mismatch, ensuring the practicality and applicability of AquaKey. Additionally, AquaKey has negligible impact on communication and has no effect on the illumination function. Through extensive real-world experiments, we show that AquaKey can achieve reliable key extraction with cheap hardware, generating a 512-bit key in just 0.5-1 seconds.

A robust and machine learning-driven identification scheme for malicious nodes in UASNs

Underwater Acoustic Sensor Networks (UASNs) have garnered widespread adoption across maritime domains and national security sectors. Their deployment, often in remote and challenging conditions, necessitates robust trust models to assess node integrity and to pinpoint compromised units, particularly under adversarial assault. Prevailing trust models, however, predominantly focus on nodes’ communicative actions and energy consumption, neglecting the influence of ambient aquatic noise on trust assessments. Moreover, these models typically falter amidst the UASN-specific impediments of high packet collision rates and elevated error probabilities inherent to underwater signal transmission, leading to consequential inaccuracies in node evaluation. To address these limitations, this paper proposes a robust and machine learning-driven malicious node identification scheme (RMIS) for UASNs. The proposed scheme first models and quantifies the impact of packet collisions and the underwater environment on node communication, utilizing existing environment models and MAC protocols. Second, communication traffic is exploited as effective and reliable evidence of trust. The traffic evidence can reflect multiple types of attacks by analyzing changes in traffic in a UASN. Third, the evaluation models are trained using support vector machine and K-means++ algorithms. Finally, two types of trust update mechanisms are proposed to handle the dynamic underwater environment and on–off attack. The simulation results indicate that compared to the other three identification schemes, RMIS is more effective in identifying malicious nodes. The effectiveness of the RMIS becomes particularly noticeable as the ratio of malicious nodes increases. Furthermore, the trust update mechanisms effectively limit the impact of the on–off attack and improve the robustness of the RMIS.

A hierarchical probabilistic underwater image enhancement model with reinforcement tuning

Underwater Image Enhancement (UIE) is a challenging problem due to the complex underwater environment. Traditional UIE methods can hardly adapt to various underwater environments. Deep learning-based UIE methods are more powerful but often rely on a large deal of real-world underwater images with distortion-free reference images. This gives rise to two issues: First, the reference images are highly uncertain because the ground-truth images cannot be are captured directly in underwater environment. Second, learning-based methods may lack generalization ability for diverse underwater environments. To tackle these issues, we propose HPUIE-RL, a hierarchical probabilistic UIE model facilitated by reinforcement learning. This model integrates UNet with hierarchical probabilistic modules to produce various enhanced candidate images that reflect the uncertainty of the enhancement. Then, a reinforcement learning fine-tuning framework is designed to fine-tune the pretrained model in an unsupervised manner, which responds to the dynamic underwater environment. Experiments on real-world datasets from diverse underwater environments demonstrate that our HPUIE-RL model outperforms state-of-the-art UIE methods regarding visual and quantitative performance and generalizability.

Expectation-maximization vector approximate message passing-based frequency-domain turbo equalization for underwater acoustic communications.

Channel equalization plays a crucial role in single-carrier underwater acoustic (UWA) communications. Recently, a frequency-domain turbo equalization (FDTE) scheme enabled by the vector approximate message passing (VAMP) algorithm, was proposed, and it outperformed classic linear minimum mean square error FDTE at acceptable complexity cost. The operation of the VAMP-FDTE requires knowledge of noise power, which is predetermined before the equalization starts. In practice, however, it is difficult to obtain prior knowledge of noise power due to factors of unknown channel estimation errors and dynamic underwater environments. Motivated by this fact, we propose an enhanced VAMP-FDTE scheme, which learns the noise power knowledge during the equalization process via the expectation-maximization (EM) algorithm. The EM-based noise power estimation makes use of intermediate results of the VAMP-FDTE and, thus, only incurs a small extra computational overhead. The improved VAMP-FDTE, named EM-VAMP-FDTE, was tested by experimental data collected in shallow-sea horizontal UWA communication trials with MIMO configuration. It showed better performance than the existing VAMP-FDTE scheme, attributed to the online noise power learning.

ASVMR: Adaptive Support-Vector-Machine-Based Routing Protocol in the Underwater Acoustic Sensor Network for Smart Ocean

The underwater acoustic sensor network (UASN) plays a crucial role in collecting real-time data from remote areas of the ocean. However, the deployment of UASN poses significant challenges due to the demanding environmental conditions and the considerable expenses associated with its implementation. Therefore, it is essential to design an appropriate routing protocol to effectively address the issues of packet delivery delay, routing void, and energy consumption. In this paper, an adaptive support vector machine (SVM)-based routing (ASVMR) protocol is proposed for the UASN to minimize end-to-end delay and prolong the network lifetime. The proposed protocol employs a distributed routing approach that dynamically optimizes the routing path in real time by considering four types of node state information. Moreover, the ASVMR protocol establishes a “routing vector” spanning from the current node to the sink node and selects a suitable pipe radius according to the packet delivery ratio (PDR). In addition, the ASVMR protocol incorporates future states of sensor nodes into the decision-making process, along with the adoption of a waiting time mechanism and routing void recovery mechanism. Extensive simulation results demonstrate that the proposed ASVMR protocol performs well in terms of the PDR, the hop count, the end-to-end delay, and the energy efficiency in dynamic underwater environments.

A copula-based method of risk prediction for autonomous underwater gliders in dynamic environments.

Autonomous underwater gliders (AUGs) are effective platforms for oceanic research and environmental monitoring. However, complex underwater environments with uncertainties could pose the risk of vehicle loss during their missions. It is therefore essential to conduct risk prediction to assist decision making for safer operations. The main limitation of current studies for AUGs is the lack of a tailored method for risk analysis considering both dynamic environments and potential functional failures of the vehicle. Hence, this study proposed a copula-based approach for evaluating the risk of AUG loss in dynamic underwater environments. The developed copula Bayesian network (CBN) integrated copula functions into a traditional Bayesian belief network (BBN), aiming to handle nonlinear dependencies among environmental variables and inherent technical failures. Specifically, potential risk factors with causal effects were captured using the BBN. A Gaussian copula was then employed to measure correlated dependencies among identified risk factors. Furthermore, the dependence analysis and CBN inference were performed to assess the risk level of vehicle loss given various environmental observations. The effectiveness of the proposed method was demonstrated in a case study, which considered deploying a Slocum G1 Glider in a real water region. Risk mitigation measures were provided based on key findings. This study potentially contributes a tailored tool of risk prediction for AUGs in dynamic environments, which can enhance the safety performance of AUGs and assist in risk mitigation for decision makers.

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.

Hybrid Deep Learning-Based Adaptive Multiple Access Schemes Underwater Wireless Networks

Achieving sound communication systems in Under Water Acoustic (UWA) environment remains challenging for researchers. The communication scheme is complex since these acoustic channels exhibit uneven characteristics such as long propagation delay and irregular Doppler shifts. The development of machine and deep learning algorithms has reduced the burden of achieving reliable and good communication schemes in the underwater acoustic environment. This paper proposes a novel intelligent selection method between the different modulation schemes such as Code Division Multiple Access(CDMA), Time Division Multiple Access(TDMA), and Orthogonal Frequency Division Multiplexing(OFDM) techniques using the hybrid combination of the convolutional neural networks(CNN) and ensemble single feedforward layers(SFL). The convolutional neural networks are used for channel feature extraction, and boosted ensembled feedforward layers are used for modulation selection based on the CNN outputs. The extensive experimentation is carried out and compared with other hybrid learning models and conventional methods. Simulation results demonstrate that the performance of the proposed hybrid learning model has achieved nearly 98% accuracy and a 30% increase in BER performance which outperformed the other learning models in achieving the communication schemes under dynamic underwater environments.

Robust AUV Visual Loop-Closure Detection Based on Variational Autoencoder Network

The visual loop-closure detection for autonomous underwater vehicles (AUVs) is a key component to reduce the drift error accumulated in simultaneous localization and mapping tasks. However, due to viewpoint changes, textureless images, and fast-moving objects, the loop closure detection in dramatically changing underwater environments remains a challenging problem to traditional geometric methods. Inspired by strong feature learning ability of deep neural networks, we propose an underwater loop-closure detection method based on a variational autoencoder network in this article. Our proposed method can learn effective image representations to deal with the challenges caused by dynamic underwater environments. Specifically, the proposed network is an unsupervised method, which avoids the difficulty and cost of labeling a great quantity of underwater data. Also included is a semantic object segmentation module, which is utilized to segment the underwater environments and assign weights to objects in order to alleviate the impact of fast-moving objects. Furthermore, an underwater image description scheme is used to enable efficient access to geometric and object-level semantic information, which helps to build a robust and real-time system in dramatically changing underwater scenarios. Finally, we test the proposed system under complex underwater environments and get a recall rate of 92.31% in the tested environments.

Deep Reinforcement Learning Based Time-Domain Interference Alignment Scheduling for Underwater Acoustic Networks

Message conflicts caused by large propagation delays severely affect the performance of Underwater Acoustic Networks (UWANs). It is necessary to design an efficient transmission scheduling algorithm to improve the network performance. Therefore, we propose a Deep Reinforcement Learning (DRL) based Time-Domain Interference Alignment (TDIA) scheduling algorithm (called DRLSA-IA). The main objective of DRLSA-IA is to increase network throughput and reduce collisions. In DRLSA-IA, underwater nodes are regarded as agents of DRL. Nodes intelligently learn the scheduling by continuously interacting with the environment. Therefore, DRLSA-IA is suitable for the highly dynamic underwater environment. Moreover, we design a TDIA-based reward mechanism to improve the network throughput. With the TDIA-based reward mechanism, DRLSA-IA can achieve parallel transmissions and effectively reduce conflicts. Unlike other TDIA-based algorithms that require enumeration of the state space, nodes merely feed the current state to obtain the transmission decision. DRLSA-IA solves the problem of computational expense. Simulation results show that DRLSA-IA can greatly improve the network performance, especially in terms of throughput, packet delivery ratio and fairness under different network settings. Overall, DRLSA-IA can effectively improve network performance and is suitable for ever-changing underwater environments.

Partial Expert-Based Adversarial Relay Learning Strategy for Underwater Acoustic Sensor Networks

Cooperative transmission is a promising solution for reliable communication in underwater acoustic sensor networks. To fully exploit the benefits of cooperative system, efficient management of relay resources is required. However, the challenging working conditions, including imprecise channel information, limited observation feedback and dynamic underwater environment, call for an adaptive relay selection strategy for improving system capacity performance. In this paper, we present an innovative Partial Expert-based Reinforcement Adversarial Learning (PER-AL) strategy that unifies expert assisted learning and self-adjusting learning in a integral adversarial multi-armed bandit framework. The user constantly interacts with the environment and optimizes the relay decision by analyzing all gathered observation rewards, rather than relying on prior channel information. By introducing a novel expert learning mechanism into the initial learning stage, expert generator and expert learner are proposed to control the performance of experts and provide optimal expert advice to reinforce the initial relay learning for efficiency. With the deepening learning, the relay quality is then evaluated by analyzing the historical observable rewards directly through a Exp3 policy without engaging complexity too much. The proposed algorithm could automatically adapt to the underwater conditions and detect the optimal relay within a short time, significantly improving system capacity without jeopardizing the adversarial regret guarantee. Finally, extensive simulation results demonstrated the superior of PER-AL algorithm compared with recent existing CSI-based and CSI-free solution benchmarks. Particularly, PER-AL algorithm has a 28.3% improvement of the total network capacity and achieves a 44.5% decrease of implementation time.

Polarization Reconstruction Algorithm of Target Based on the Analysis of Noise in Complex Underwater Environment

How to effectively eliminate interference such as scattering, absorption, and attenuation is a hot topic of underwater photoelectric detection at present. Around the hot issues, this paper carries out studying the method of polarization-imaging recovery in a dynamic complex underwater environment from the theory of underwater radiation transfer, and numerical simulation of imaging interference characteristics to the simulation of underwater environment experiment. First, by conducting the analysis and simulation of scattering characteristics of underwater suspension particles and bubble by using the theory of radiation transfer, and taking advantage of quantitative description on changing tendency of radiation intensity and polarization properties of light waves in turbid water under the condition of scattering interference. Second, by constructing an underwater target polarization reconstruction model on the basis of the Mueller matrix analysis, and taking target polarization characteristic into reconstruction model on the basis of classical Schechner’s model, automatically estimating polarization information of target by the method of covariance. Finally, by building a polarization imaging system in the simulated complex underwater environment that contains bubble and suspended particles, obtaining reconstructed results with different underwater environments and different materials of target. According to experiment results, and compared with other traditional methods, using the proposed method in this paper can get higher resolution and higher contrast of target in the reconstructed result.

Packet Flow Based Reinforcement Learning MAC Protocol for Underwater Acoustic Sensor Networks.

Medium access control (MAC) is one of the key requirements in underwater acoustic sensor networks (UASNs). For a MAC protocol to provide its basic function of efficient sharing of channel access, the highly dynamic underwater environment demands MAC protocols to be adaptive as well. Q-learning is one of the promising techniques employed in intelligent MAC protocol solutions, however, due to the long propagation delay, the performance of this approach is severely limited by reliance on an explicit reward signal to function. In this paper, we propose a restructured and a modified two stage Q-learning process to extract an implicit reward signal for a novel MAC protocol: Packet flow ALOHA with Q-learning (ALOHA-QUPAF). Based on a simulated pipeline monitoring chain network, results show that the protocol outperforms both ALOHA-Q and framed ALOHA by at least 13% and 148% in all simulated scenarios, respectively.

Soft Origami Optical-Sensing Actuator for Underwater Manipulation.

Soft robots are ideal for underwater manipulation in sampling and other servicing applications. Their unique features of compliance, adaptability, and being naturally waterproof enable robotic designs to be compact and lightweight, while achieving uncompromized dexterity and flexibility. However, the inherent flexibility and high nonlinearity of soft materials also results in combined complex motions, which creates both soft actuator and sensor challenges for force output, modeling, and sensory feedback, especially under highly dynamic underwater environments. To tackle these limitations, a novel Soft Origami Optical-Sensing Actuator (SOSA) with actuation and sensing integration is proposed in this paper. Inspired by origami art, the proposed sensorized actuator enables a large force output, contraction/elongation/passive bending actuation by fluid, and hybrid motion sensing with optical waveguides. The SOSA design brings two major novelties over current designs. First, it involves a new actuation-sensing mode which enables a superior large payload output and a robust and accurate sensing performance by introducing the origami design, significantly facilitating the integration of sensing and actuating technology for wider applications. Secondly, it simplifies the fabrication process for harsh environment application by investigating the boundary features between optical waveguides and ambient water, meaning the external cladding layer of traditional sensors is unnecessary. With these merits, the proposed actuator could be applied to harsh environments for complex interaction/operation tasks. To showcase the performance of the proposed SOSA actuator, a hybrid underwater 3-DOFs manipulator has been developed. The entire workflow on concept design, fabrication, modeling, experimental validation, and application are presented in detail as reference for wider effective robot-environment applications.

Semi-Reference Sonar Image Quality Assessment Based on Task and Visual Perception

In submarine and underwater detection tasks, conventional optical imaging and analysis methods are not universally applicable due to the limited penetration depth of visible light. Instead, sonar imaging has become a preferred alternative. However, the capture and transmission conditions in complicated and dynamic underwater environments inevitably lead to visual quality degradation of sonar images, which might also impede further recognition, analysis and understanding. To measure this quality decrease and provide a solid quality indicator for sonar image enhancement, we propose a task- and perception-oriented sonar image quality assessment (TPSIQA) method, in which a semi-reference (SR) approach is applied to adapt to the limited bandwidth of underwater communication channels. In particular, we exploit reduced visual features that are critical for both human perception of and object recognition in sonar images. The final quality indicator is obtained through ensemble learning, which aggregates an optimal subset of multiple base learners to achieve both high accuracy and a high generalization ability. In this way, we are able to develop a compact but generalized quality metric using a small database of sonar images. Experimental results demonstrate competitive performance, high efficiency, and strong robustness of our method compared to the latest available image quality metrics.

Multi-UUV Cooperative Dynamic Maneuver Decision-Making Algorithm Using Intuitionistic Fuzzy Game Theory

In this paper, a multi-unmanned underwater vehicle (UUV) cooperative dynamic maneuver decision-making algorithm is proposed based on the combination of game theory and intuitionistic fuzzy sets. Underwater environments with weak connectivity, underwater noise, and dynamic uncertainties are fully considered through intuitionistic fuzzy sets, which solves one of the main problems in making decisions underwater. Subsequently, the intuitionistic fuzzy multiattribute evaluation of a UUV maneuver strategy is conducted, and the intuitionistic fuzzy payment matrix of the cooperative dynamic maneuver game is obtained. Thereafter, the Nash equilibrium condition is proposed to satisfy the intuitionistic fuzzy total order, and the Nash equilibrium maneuver decision-making model under a dynamic underwater environment is established. Meanwhile, the modified particle swarm optimization method is presented to solve the established problem and find the optimal strategy. Finally, an example is used to verify the superiority of the proposed cooperative dynamic maneuver decision-making algorithm.

MARESye: A hybrid imaging system for underwater robotic applications

This article presents an innovative hybrid imaging system that provides dense and accurate 3D information from harsh underwater environments. The proposed system is called MARESye and captures the advantages of both active and passive imaging methods: multiple light stripe range (LSR) and a photometric stereo (PS) technique, respectively. This hybrid approach fuses information from these techniques through a data-driven formulation to extend the measurement range and to produce high density 3D estimations in dynamic underwater environments. This hybrid system is driven by a gating timing approach to reduce the impact of several photometric issues related to the underwater environments such as, diffuse reflection, water turbidity and non-uniform illumination. Moreover, MARESye synchronizes and matches the acquisition of images with sub-sea phenomena which leads to clear pictures (with a high signal-to-noise ratio). Results conducted in realistic environments showed that MARESye is able to provide reliable, high density and accurate 3D data. Moreover, the experiments demonstrated that the performance of MARESye is less affected by sub-sea conditions since the SSIM index was 0.655 in high turbidity waters. Conventional imaging techniques obtained 0.328 in similar testing conditions. Therefore, the proposed system represents a valuable contribution for the inspection of maritime structures as well as for the navigation procedures of autonomous underwater vehicles during close range operations.